WO2014128789A1 - 形状認識装置、形状認識プログラム、および形状認識方法 - Google Patents
形状認識装置、形状認識プログラム、および形状認識方法 Download PDFInfo
- Publication number
- WO2014128789A1 WO2014128789A1 PCT/JP2013/004486 JP2013004486W WO2014128789A1 WO 2014128789 A1 WO2014128789 A1 WO 2014128789A1 JP 2013004486 W JP2013004486 W JP 2013004486W WO 2014128789 A1 WO2014128789 A1 WO 2014128789A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- hand
- shape
- chord
- depth
- recognition
- Prior art date
Links
Images
Classifications
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/017—Gesture based interaction, e.g. based on a set of recognized hand gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/0304—Detection arrangements using opto-electronic means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0481—Interaction techniques based on graphical user interfaces [GUI] based on specific properties of the displayed interaction object or a metaphor-based environment, e.g. interaction with desktop elements like windows or icons, or assisted by a cursor's changing behaviour or appearance
- G06F3/0482—Interaction with lists of selectable items, e.g. menus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04845—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range for image manipulation, e.g. dragging, rotation, expansion or change of colour
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
- G06T19/006—Mixed reality
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/11—Hand-related biometrics; Hand pose recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
- G06V40/113—Recognition of static hand signs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/28—Recognition of hand or arm movements, e.g. recognition of deaf sign language
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/30—Image reproducers
- H04N13/388—Volumetric displays, i.e. systems where the image is built up from picture elements distributed through a volume
- H04N13/395—Volumetric displays, i.e. systems where the image is built up from picture elements distributed through a volume with depth sampling, i.e. the volume being constructed from a stack or sequence of 2D image planes
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/0101—Head-up displays characterised by optical features
- G02B2027/0138—Head-up displays characterised by optical features comprising image capture systems, e.g. camera
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/0101—Head-up displays characterised by optical features
- G02B2027/014—Head-up displays characterised by optical features comprising information/image processing systems
-
- G—PHYSICS
- G02—OPTICS
- G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G02B27/00—Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
- G02B27/01—Head-up displays
- G02B27/017—Head mounted
- G02B2027/0178—Eyeglass type
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20228—Disparity calculation for image-based rendering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/56—Particle system, point based geometry or rendering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/30—Image reproducers
- H04N13/332—Displays for viewing with the aid of special glasses or head-mounted displays [HMD]
Definitions
- the present invention relates to a shape recognition device, a shape recognition program, and a shape recognition method.
- the present invention relates to a shape recognition device, a shape recognition program, and a shape recognition method for recognizing a palm or the back of a hand.
- Patent Document 1 discloses a computer graphics that displays a high-quality image on a screen at high speed, that is, a high-speed image generation and display method.
- the high-speed image generation and display method described in Patent Literature 1 is a high-speed image generation and display method for projecting and displaying an object having a three-dimensional structure on a two-dimensional screen, and the constituent surface of the object is a region in the target coordinate system.
- the size of the object is hierarchically described as at least one element, and is displayed in the target coordinate system from the origin or viewpoint of the display reference coordinate system when projecting the constituent plane of the target when viewed from an arbitrary viewpoint onto the two-dimensional screen.
- the degree of hierarchy is set with the distance to an arbitrary point of the target being set as at least one parameter.
- Patent Document 2 discloses a stereoscopic image generation method and a stereoscopic image generation apparatus that efficiently generate a stereoscopic video without burden on an observer.
- object data to be planarly displayed among objects composed of polygons having three-dimensional coordinates is displayed in the standard camera coordinate system data with the reference camera as the origin.
- the data of the object in the right-eye parallax camera coordinate system is rendered in the video memory as the image data for the right eye, and the data of the object in the reference camera coordinate system and the data of the object in the parallax camera coordinate system for the left eye
- image data draw in video memory and combine right-eye image data and left-eye image data drawn in video memory Te, and displaying an image with mixed stereoscopic object in a plan view object in the stereoscopic display device.
- Patent Document 3 discloses a method using face recognition and gesture / position recognition techniques.
- the method described in Patent Document 3 is a method for applying an attribute indicating a user's temperament to a visual display, which includes a step of rendering the user's visual display and a step of receiving physical space data.
- the data is representative of the user in physical space, the step of analyzing at least one detectable feature to infer the user's temperament, and an attribute indicative of the user's temperament Applying to the display.
- Patent Document 4 discloses a system and method for supplying a multi-mode input to a space or gesture calculation system.
- the system disclosed in Patent Literature 4 includes an input device and a detector that is coupled to a processor and detects the orientation of the input device, and the input device has a plurality of mode orientations corresponding to the orientation.
- Patent Document 5 discloses a system, method, and computer-readable medium for manipulating virtual objects.
- the method described in Patent Document 5 is a method for operating a virtual object in a virtual space, the step of determining at least one controller used by a user to operate the virtual object, and the controller as a cursor in the virtual space.
- a method comprising: mapping; determining a controller input indicating that a user operates a virtual object with a cursor; and displaying an operation result.
- Patent Document 6 In Japanese Patent Application Laid-Open No. 2012-106005 (Patent Document 6), an observer of an image display device obtains a feeling as if it can directly operate a stereoscopic image that does not actually exist.
- An image display device, a game method, and a game control method are disclosed.
- the image display device described in Patent Literature 6 includes an image display unit that displays a parallax image on a display screen, and a virtual spatial coordinate of a stereoscopic image that is recognized between the display screen and the observer by an observer of the parallax image.
- An object of the present invention is to provide a shape recognition device, a shape recognition program, and a shape recognition method capable of obtaining more accurate information for identifying the outer shape of an object.
- a shape recognition device includes an outer shape detection unit, an extraction point setting unit, a depth detection unit, and a direction recognition unit.
- the outer shape detection unit detects the outer shape of the hand.
- the extraction point setting unit sets a plurality of points inside the detected outer shape as extraction points.
- the depth detection unit measures a spatial distance to a target point on the surface of the hand corresponding to each of the plurality of extraction points as a depth.
- the direction recognizing unit determines whether the hand is facing the palm side or the back side based on the scale indicating the variation in the measured depth.
- the determination can be made on the basis of the palm side when the variation in the measured depth is relatively large, and the dorsal side when the variation is relatively small.
- the side closer to the fingertip is distal, the side closer to the trunk is proximal, the palm side is palmer, and the back of the hand is dorsal
- the thumb side is described as the flex side (radial), and the little finger side is described as the ulnar side.
- the shape recognition device further includes a reference point extraction unit.
- the center point of the maximum inscribed circle of the outer shape is extracted as the reference point from the detected outer shape.
- the extraction point setting unit sets a chord of the maximum inscribed circle passing through the reference point, and sets a plurality of extraction points on the set chord at predetermined intervals.
- At least one of the horizontal chord and the vertical chord is set as the chord of the maximum inscribed circle passing through the reference point.
- the scale indicating the variation in depth is standard deviation, variance, range, quartile range, average difference And / or mean absolute deviation.
- the shape recognition apparatus in the shape recognition apparatus according to any of the second to fifth inventions, it is determined whether the hand is the right hand or the left hand based on the result of the linear regression analysis of the depth. And a left / right recognition unit.
- the left / right determination may be based on the fact that the depth tends to be larger on the scale side and the depth is smaller on the flex side, particularly when the hand is facing the back side.
- the depth tends to be larger on the shaku side and the depth tends to be smaller on the flex side. May be. Therefore, even if the hand is in a fist state, both the palm side and back side identification of the hand and the left and right identification of the hand can be performed.
- the outer shape detection unit and the depth detection unit are infrared sensors. Accordingly, the infrared sensor can serve as both the outer shape detection unit and the depth detection unit. Therefore, the configuration of the apparatus can be simplified.
- the shape recognition device in the shape recognition device according to any one of the seventh to seventh inventions, further includes a display device capable of displaying a stereoscopic image, and the outer shape detection unit is generated by the display device.
- the contour of the hand is detected in a shared region shared by the stereoscopic region of the stereoscopic image and the depth detection region.
- a shape recognition device is a head-mounted display device having the shape recognition device according to any one of the eighth aspect to the eighth invention.
- the shape recognition device is provided in the head mounted display device, the shape of the hand can be recognized while the device is worn on the body.
- the device since the device is mounted on the head, the shape of the detected hand and the shape of the hand that can be visually recognized by the user are almost the same, and the shape recognition device is used when operating a display object or registering a gesture. It is also possible to detect a hand while conscious of a mode that is easily detected.
- a shape recognition program includes an outer shape detection process, an extraction point setting process, a depth detection process, and a direction recognition process.
- the contour detection process detects the contour of the hand.
- the extraction point setting process sets a plurality of points inside the detected outer shape as extraction points.
- a spatial distance to a target point on the surface of the hand corresponding to each of a plurality of extraction points is measured as a depth.
- the direction recognition process it is determined whether the hand is facing the palm side or the back side based on the scale indicating the variation in the measured depth.
- the determination can be made on the basis of the palm side when the variation in the measured depth is relatively large, and the dorsal side when the variation is relatively small.
- the shape recognition program according to the eleventh invention further includes a reference point extraction process in the shape recognition program according to another aspect.
- the reference point extraction process the center point of the maximum inscribed circle of the outer shape is extracted as the reference point from the detected outer shape.
- the chord of the maximum inscribed circle passing through the reference point is set, and a plurality of extraction points are set at predetermined intervals on the set chord.
- At least one of the horizontal chord and the vertical chord is set as the chord of the maximum inscribed circle passing through the reference point.
- the chord having the direction connecting the distal and proximal hands as the chord of the maximum inscribed circle passing through the reference point And at least one of a string having a direction connecting the flexion side and the scale side of the hand.
- the shape recognition program according to the fourteenth invention in the shape recognition program according to any of the eleventh to thirteenth inventions, it is determined whether the hand is the right hand or the left hand based on the result of the linear regression analysis of the depth. Further included is a left / right recognition process.
- the left / right determination may be based on the fact that the depth tends to be larger on the scale side and the depth is smaller on the flex side, particularly when the hand is facing the back side.
- the depth tends to be larger on the shaku side and the depth tends to be smaller on the flex side. May be. Therefore, even if the hand is in a fist state, both the palm side and back side identification of the hand and the left and right identification of the hand can be performed.
- the shape recognition method includes an outer shape detection step, an extraction point setting step, a depth detection step, and a direction recognition step.
- the contour detection step detects the contour of the hand.
- the extraction point setting step a plurality of points inside the detected outer shape are set as extraction points.
- the depth detection step a spatial distance to a target point on the surface of the hand corresponding to each of a plurality of extraction points is measured as a depth.
- the orientation recognition step it is determined whether the hand is facing the palm side or the back side based on the scale indicating the variation in the measured depth.
- the determination can be made on the basis of the palm side when the variation in the measured depth is relatively large, and the dorsal side when the variation is relatively small.
- the shape recognition method according to the sixteenth invention further includes a reference point extracting step in the shape recognition method according to another aspect.
- the reference point extraction step the center point of the maximum inscribed circle of the outer shape is extracted as a reference point from the detected outer shape.
- a chord of a maximum inscribed circle passing through the reference point is set, and a plurality of extraction points are set at predetermined intervals on the set chord.
- At least one of a horizontal chord and a vertical chord is set as the chord of the maximum inscribed circle passing through the reference point.
- the chord having a direction connecting the distal end and the proximal portion of the hand as the maximum inscribed circle chord passing through the reference point. And at least one of a string having a direction connecting the flexion side and the scale side of the hand.
- the left / right determination may be based on the fact that the depth tends to be larger on the scale side and the depth is smaller on the flex side, particularly when the hand is facing the back side.
- the depth tends to be larger on the shaku side and the depth tends to be smaller on the flex side. May be. Therefore, even if the hand is in a fist state, both the palm side and back side identification of the hand and the left and right identification of the hand can be performed.
- a shape recognition device it is possible to provide a shape recognition device, a shape recognition program, and a shape recognition method that can obtain more accurate information for identifying the outer shape of an object.
- FIG. 2 is a schematic external front view showing an example of a basic configuration of the eyeglass display device 100.
- FIG. 1 is a schematic external perspective view showing an example of an eyeglass display device 100.
- FIG. 3 is a schematic diagram illustrating an example of a configuration of a control unit 450 of the operation system 400.
- FIG. 4 is a flowchart showing a flow of processing in the operation system 400. It is a schematic diagram which shows the concept according to the flowchart of FIG. 4 is a schematic perspective view for explaining a detection area of an infrared detection unit 410 and a virtual display area of a pair of transflective displays 220.
- FIG. FIG. 7 is a top view of FIG. 6.
- FIG. 7 is a side view of FIG. 6.
- FIG. 23 is a schematic diagram of the outer shape and extraction point setting of FIGS. 22A and 22B, illustrating an example of the palm-side and back-side identification processing of FIGS. 22A and 22B. It is the schematic diagram which piled up Drawing 23 (a) and Drawing 23 (b) of Drawing 22 (a) and Drawing 22 (b), respectively.
- FIG. 23 is a schematic diagram of the outer shape and extraction point setting of FIGS. 22A and 22B, illustrating an example of the palm-side and back-side identification processing of FIGS. 22A and 22B. It is the schematic diagram which piled up Drawing 23 (a) and Drawing 23 (b) of Drawing 22 (a) and Drawing 22 (b), respectively.
- FIG. 24 (a) and FIG. 24 (b) are schematic views showing a cross-sectional view of the hand H1 P and hand H1 D by a plane parallel to the y-z plane containing the chord C v.
- FIG. 24 (a) and FIG. 24 (b) are schematic views showing a cross-sectional view of the hand H1 P and hand H1 D by a plane parallel to the x-z plane containing the chord C h.
- FIG. 23 is a schematic diagram of the outer shape and extraction point setting of FIGS. 22A and 22B, showing another example of the palm-side and back-side identification processing of FIGS. 22A and 22B.
- FIG.26 It is a graph which shows the relationship between the depth in the target point S shown to Fig.26 (a) and FIG.26 (b), and the position in the direction which connects the scale side of a hand, and a bending side. It is a flowchart which shows an example of the registration process of gesture data. It is a flowchart which shows an example of the setting process of a gesture command. It is a flowchart which shows an example of the rewriting process of a gesture command. 4 is a schematic diagram illustrating an example of display on a transflective display 220 of the eyeglass display device 100.
- FIG.26 a
- gesture recognition It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition. It is a schematic diagram which shows the other example of gesture recognition.
- the present invention also provides: The present invention is not limited to the glasses display device described below, and can be applied to other wearable devices, other input / output devices, display devices, televisions, monitors, projectors, and the like.
- FIG. 1 is a schematic external front view showing an example of the basic configuration of a spectacle display device 100 according to an embodiment
- FIG. 2 is a schematic external perspective view showing an example of the spectacle display device 100.
- the glasses display device 100 is a glasses-type display device. As will be described later, the eyeglass display device 100 is used by being worn on the user's face.
- the eyeglass display device 100 mainly includes an eyeglass unit 200, a communication system 300, and an operation system 400.
- the spectacle unit 200 includes a spectacle frame 210 and a pair of transflective displays 220.
- the spectacle frame 210 mainly includes a rim unit 211 and a temple unit 212.
- a pair of transflective displays 220 is supported by the rim unit 211 of the spectacle frame 210.
- the pair of transflective displays 220 is provided on the rim unit 211 in the spectacle display device 100, but the present invention is not limited to this, and a normal sunglasses lens is provided on the rim unit 211 of the spectacle display device 100.
- lenses such as an ultraviolet cut lens or a spectacle lens may be provided, and a single transflective display 220 or a pair of transflective displays 220 may be provided separately. Further, the transflective display 220 may be embedded in a part of the lenses.
- the present embodiment is not limited to the eyeglass type, and can be used for a hat type or any other head mounted display device as long as it is a type that can be worn on the human body and disposed in the field of view of the wearer. .
- the communication system 300 includes a battery unit 301, an antenna module 302, a camera unit 303, a speaker unit 304, a GPS (Global Positioning System) unit 307, a microphone unit 308, a SIM (Subscriber Identity Module Card) unit 309, and a main unit 310.
- the camera unit may be provided with a CCD sensor.
- the speaker unit 304 may be a normal earphone or a bone conduction earphone.
- the SIM unit 309 includes an NFC (Near Field Communication) unit and other contact IC card units, and a non-contact IC card unit.
- the communication system 300 includes at least one of the functions of a mobile phone, a smartphone, and a tablet terminal. Specifically, it includes a telephone function, an Internet function, a browser function, a mail function, an imaging function, and the like. Therefore, the user can use a call function similar to that of a mobile phone by using the eyeglass display device 100 with the communication device, the speaker, and the microphone. Further, since it is a glasses type, it is possible to make a call without using both hands.
- the operation system 400 includes an infrared detection unit 410, a gyro sensor unit 420, an acceleration detection unit 430, and a control unit 450.
- the infrared detection unit 410 mainly includes an infrared irradiation element 411 and an infrared detection camera 412.
- FIG. 3 is a schematic diagram illustrating an example of the configuration of the control unit 450 of the operation system 400.
- the control unit 450 includes an image sensor calculation unit 451, a depth map calculation unit 452, an image processing unit 453, an anatomical recognition unit 454, a gesture data recording unit 455, a gesture identification unit 456, calibration data. It includes a recording unit 457, a composite arithmetic unit 458, an application software unit 459, an event service unit 460, a calibration service unit 461, a display service unit 462, a graphic arithmetic unit 463, a display arithmetic unit 464, and a six-axis drive driver unit 465.
- control unit 450 need not include all of the above, and may include one or more units as necessary.
- the gesture data recording unit 455 and the calibration data recording unit 457 may be arranged on the cloud, and the synthesis operation unit 458 may not be provided.
- FIG. 4 is a flowchart showing a flow of processing in the operation system 400
- FIG. 5 is a schematic diagram showing a concept corresponding to the flowchart of FIG.
- the target data is acquired from the infrared detection unit 410, and the depth calculation is performed by the depth map calculation unit 452 (step S1.
- the outer shape image data is processed by the image processing unit 453. (Step S2).
- the anatomical recognition unit 454 identifies anatomical features from the outline image data processed in step S2 based on the standard human body structure. Thereby, the outer shape is recognized (step S3).
- the gesture identification unit 456 identifies the gesture based on the anatomical features obtained in step S3 (step S4).
- the gesture identification unit 456 refers to the gesture data recorded in the gesture data recording unit 455 and identifies the gesture from the outer shape where the anatomical features are identified.
- the gesture identification unit 456 refers to the gesture data from the gesture data recording unit 455.
- the gesture identification unit 456 is not limited to referencing, and may refer to other arbitrary data without referring to it at all. It may be processed. As described above, the hand gesture is recognized as shown in FIG.
- the application software unit 459 and the event service unit 460 perform a predetermined event according to the gesture determined by the gesture identification unit 456 (step S5).
- the image by a photography application for example is displayed.
- the image data from the camera unit 303 may be displayed on the screen.
- the display service unit 462, the calibration service unit 461, the graphic operation unit 463, the display operation unit 464, and the composition operation unit 458 display an image on the translucent display 220 or a virtual display of the image (step).
- S6 As a result, a hand skeleton indicating a gesture is displayed as shown in FIG. 5C, and as shown in FIG. 5D, the shape and size of the photograph are changed to the shape and size of the skeleton. An image synthesized to match is displayed.
- the 6-axis drive driver unit 465 always detects signals from the gyro sensor unit 420 and the acceleration detection unit 430, and transmits the posture state to the display arithmetic unit 464.
- the 6-axis drive driver unit 465 When the user wearing the glasses display device 100 tilts the glasses display device 100, the 6-axis drive driver unit 465 always receives signals from the gyro sensor unit 420 and the acceleration detection unit 430, and displays an image. Take control. In this control, the display of the image may be kept horizontal, or the display of the image may be adjusted according to the inclination.
- FIG. 6 is a schematic perspective view for explaining a detection region of the infrared detection unit 410 and a virtual display region of the pair of transflective displays 220
- FIG. 7 is a top view of FIG. 6
- FIG. FIG. 7 is a side view of FIG. 6.
- a three-dimensional orthogonal coordinate system including an x-axis, a y-axis, and a z-axis is defined.
- the x-axis arrows in the following figures indicate the horizontal direction.
- the y-axis arrow points in the vertical direction or the long axis direction of the user's body.
- the z-axis arrow points in the depth direction.
- the z-axis positive direction refers to the direction of greater depth.
- the direction of each arrow is the same in other figures.
- a three-dimensional space detection area (3D space) 4103 ⁇ / b> D that can be detected by the infrared detection unit 410 of the operation system 400 is provided.
- the three-dimensional space detection area 4103D is formed of a conical or pyramidal three-dimensional space from the infrared detection unit 410.
- the infrared detection unit 410 can detect the infrared rays emitted from the infrared irradiation element 411 by the infrared detection camera 412, and thus can recognize a gesture in the three-dimensional space detection region 4103D.
- one infrared detection unit 410 is provided.
- the present invention is not limited to this, and a plurality of infrared detection units 410 may be provided, or one infrared irradiation element 411 may be provided.
- a plurality of detection cameras 412 may be provided.
- the pair of transflective displays 220 displays to the user a virtual image display that is not a part of the glasses display device 100 that is actually provided, but is located away from the glasses display device 100.
- the region 2203D is visually recognized as being virtually displayed with a depth.
- the depth corresponds to the thickness in the depth direction (z-axis direction) of the virtual three-dimensional shape of the virtual image display area 2203D. Therefore, the depth is provided according to the thickness of the virtual three-dimensional shape in the depth direction (z-axis direction).
- the user recognizes the right-eye image through the right-eye semi-transmissive display 220 in the three-dimensional space area 2203DR, and the left-eye image is The light is transmitted through the transflective display 220 on the left eye side and recognized by the three-dimensional space area 2203DL.
- both recognized images are synthesized in the user's brain, and can be recognized as a virtual image in the virtual image display area 2203D.
- the virtual image display area 2203D includes a frame sequential method, a polarization method, a linear polarization method, a circular polarization method, a top-and-bottom method, a side-by-side method, an anaglyph method, a lenticular method, and a parallax barrier method.
- the liquid crystal parallax barrier method, the two-parallax method, and the multi-parallax method using three or more parallaxes are used for display.
- the virtual image display area 2203D has a spatial area shared with the three-dimensional space detection area 4103D.
- the virtual image display area 2203D since the virtual image display area 2203D exists inside the three-dimensional space detection area 4103D, the virtual image display area 2203D serves as a shared area.
- the shape and size of the virtual image display area 2203D can be arbitrarily adjusted by the display method on the pair of transflective displays 220. Moreover, as shown in FIG. 8, although the case where the infrared detection unit 410 is arrange
- FIGS. 6 to 8 are schematic diagrams illustrating other examples of the detection area and the virtual display area illustrated in FIGS. 6 to 8.
- an input / output device 900 For example, as shown in FIGS. 9 to 11, other input / output devices, display devices, televisions, monitors, and the like may be used instead of the transflective display 220 of the eyeglass display device 100.
- other input / output devices, display devices, televisions, monitors, and projectors are collectively referred to as an input / output device 900.
- the virtual image display area 2203D is output from the input / output device 900 in the negative z-axis direction, and the infrared detection unit 410 disposed at a position facing the input / output device 900 in the z-axis direction outputs the z-axis.
- a three-dimensional space detection region 4103D may be formed in the positive direction.
- a virtual image display area 2203D by the input / output device 900 is generated as a space area shared with the three-dimensional space detection area 4103D.
- a virtual image display area 2203D is output from the input / output device 900, and the infrared detection unit 410 is in the same direction as the input / output device 900 (all directions on the z-axis positive side with respect to the xy plane).
- the three-dimensional space detection region 4103D may be formed. Even in this case, the virtual image display area 2203D by the input / output device 900 is generated as a space area shared with the three-dimensional space detection area 4103D.
- the virtual image display area 2203 ⁇ / b> D may be output from the input / output device 900 in a vertically upward direction (y-axis positive direction). Also in FIG. 11, similarly to FIGS. 9 and 10, the virtual image display area 2203 ⁇ / b> D by the input / output device 900 is generated as a space area shared with the three-dimensional space detection area 4103 ⁇ / b> D.
- the input / output device 900 is arranged above the three-dimensional space detection region 4103D (y-axis positive direction side), and the virtual image display region 2203D is vertically downward (y-axis negative direction). It may be output, may be output from the horizontal direction (x-axis direction), or may be output from the rear upper side (z-axis positive direction and y-axis positive direction) like a projector or a movie theater.
- FIGS. 12 and 13 are schematic diagrams illustrating examples of the operation area and the gesture area in the detection area.
- the user horizontally moves both hands around the shoulder joints of the right shoulder joint RP and the left shoulder joint LP, so that the area where both hands can move is surrounded by a dotted line.
- the moving area L and the moving area R become the same.
- the user vertically moves both hands around the shoulder joints of the right shoulder joint RP and the left shoulder joint LP, so that the area where both hands can move is surrounded by a dotted line.
- the moving area L and the moving area R become the same.
- the user has a spherical shape (having an arch-shaped curved surface convex in the depth direction) with both hands rotating around the right shoulder joint RP and the left shoulder joint LP, respectively. Can be moved.
- the three-dimensional space detection area 4103D by the infrared detection unit 410 the area where the virtual image display area may exist (the virtual image display area 2203D is illustrated in FIG. 12), the arm movement area L, and the movement area R are combined.
- a space area that overlaps with the selected area is set as the operation area 410c.
- a portion other than the operation region 410c in the three-dimensional space detection region 4103D and a portion overlapping with the combined region of the arm movement region L and the movement region R is set as the gesture region 410g.
- the operation region 410c has a three-dimensional shape in which the surface farthest in the depth direction is a curved surface curved in an arch shape convex in the depth direction (z-axis positive direction), whereas the virtual image display region 2203D has a depth of The surface farthest in the direction has a three-dimensional shape that is a plane.
- the user feels uncomfortable in the operation.
- adjustment is performed by a calibration process. Details of the calibration process will be described later.
- FIG. 14 is a flowchart for explaining the calibration process.
- a calibration process is performed to facilitate the operation in the virtual image display area 2203D by a recognition process described later.
- the finger length, hand length, and arm length that are different for each user are also adjusted.
- the user wears the eyeglass display device 100 and extends both arms to the maximum.
- the infrared detection unit 410 recognizes the maximum area of the operation area 410c (step S11). That is, since the length of the finger, the length of the hand, and the length of the arm, which are different for each user, are different depending on the user, the operation area 410c is adjusted.
- the display position of the virtual image display area 2203D is determined (step S12). That is, if the virtual image display area 2203D is arranged outside the operation area 410c, the operation by the user becomes impossible, so the virtual image display area 2203D is arranged inside the operation area 410c.
- the maximum area of the gesture area 410g is set in a position that does not overlap the display position of the virtual image display area 2203D within the three-dimensional space detection area 4103D of the infrared detection unit 410 of the eyeglass display device 100 (step S13).
- the gesture region 410g is preferably arranged so as not to overlap the virtual image display region 2203D and has a thickness in the depth direction (z-axis positive direction).
- the operation area 410c, the virtual image display area 2203D, and the gesture area 410g are set by the above method.
- step) S14 When it is determined that the user's finger, hand, or arm exists outside the virtual image display area 2203D in the operation area 410c, rounding is performed so that the user's finger, hand, or arm exists inside the virtual image display area 2203D (step) S14).
- both hands remain in the virtual image display area 2203D. Without any deviation in the depth direction (z-axis positive direction). Further, at the end of the virtually displayed image, it is not determined that both hands are present in the virtual image display area 2203D unless both arms are extended to the maximum. Therefore, if the signal from the infrared detection unit 410 is used without processing, even if the user moves away from the virtual image display area 2203D, it is difficult for the user to experience such a state.
- the signal from the infrared detection unit 410 is processed so as to correct the hand protruding outside from the virtual image display area 2203D within the virtual image display area 2203D. To do. As a result, the user can operate from the center to the end of the flat virtual image display area 2203D having a depth with both arms extended to the maximum or slightly bent.
- the virtual image display area 2203D is made up of a three-dimensional space area whose plane farthest in the depth direction is a plane, but is not limited to this, and is the plane area farthest in the depth direction. It is good also as consisting of the three-dimensional space area
- the transflective display 220 displays a rectangular image in the virtual image display area 2203D. For example, as shown in FIG. 5B, a rectangular image is displayed (step S15). Subsequently, display is performed when the periphery of the image is surrounded by a finger on the transflective display 220 (step S16).
- a finger-shaped image may be displayed lightly in the vicinity of the image, or an instruction may be transmitted from the speaker to the user by voice instead of being displayed on the transflective display 220.
- the user places his / her finger on the portion where the image can be seen as shown in FIG. Then, the correlation between the display area of the virtual image display area 2203D and the infrared detection unit 410 is automatically adjusted (step S17).
- a rectangle is formed with a finger, and is matched with the rectangle thus determined and the rectangle of the outer edge of the image.
- the rectangular viewing size and position determined by the finger are matched with the rectangular viewing size and position of the outer edge of the image.
- the method of determining the shape with the finger is not limited to this, and any other method such as a method of tracing the outer edge of the displayed image with a finger, a method of pointing a plurality of points on the outer edge of the displayed image with a finger, etc. It may be. Moreover, you may perform these methods about the image of several sizes.
- FIG. 15 is a schematic diagram illustrating an example of finger recognition.
- 15A is an enlarged view of the vicinity of the tip of the finger
- FIG. 15B is an enlarged view of the vicinity of the base of the finger.
- FIG. 16 is a flowchart illustrating an example of finger recognition processing.
- the device is initialized (step S21).
- the infrared ray irradiated from the infrared irradiation element 411 and reflected by the hand is detected by the infrared detection camera 412 (step S22).
- the image data is replaced with a distance in units of pixels by the infrared detection unit 410 (step S23).
- the brightness of infrared rays is inversely proportional to the cube of the distance.
- a depth map is created (step S24).
- an appropriate threshold value is provided for the created depth map.
- the image data is binarized (step S25), that is, noise in the depth map is removed.
- a polygon having about 100 vertices is created from the binarized image data (step S26).
- a low-pass filter (LPF) so the vertex becomes smooth, by creating a new polygon having more vertexes p n, it extracts the outline OF hand shown in FIG. 15 (step S27).
- the number of vertices extracted to create a polygon from the binarized data in step S26 is about 100.
- the number of vertices is not limited to this, and 1000 or any other arbitrary number is used. It may be a number.
- step S28 From the set of vertices p n of new polygons created in step S27, using Convex Hull, it extracts the hull (step S28). Thereafter, a shared vertex p 0 between the new polygon created in step S27 and the convex hull created in step S28 is extracted (step S29).
- the shared vertex p 0 itself extracted in this way can be used as the finger tip point. Further, another point calculated based on the position of the vertex p 0 may be used as the tip point of the finger. For example, it is also possible to calculate the center of the inscribed circle of the contour OF as the tip points P0 at the vertex p 0 as shown in FIG. 15 (A).
- a vector of the reference line segment PP 1 passing through the pair of left and right vertices p 1 adjacent to the vertex p 0 is calculated.
- the side pp 2 connecting the vertex p 1 and the adjacent vertex p 2 is selected, and its vector is calculated.
- the vertex p n constituting the outer OF was selected, and its vector is calculated.
- Examined the reference line segment PP 1 direction by the processing direction and step S30 of each side determines that the sides pp k comprising parallel close to the reference line segment PP 1 is present at the position of the crotch of the finger.
- the root point P1 of the finger is calculated (step S30).
- a finger skeleton is obtained by connecting the finger tip point P0 and the finger root point P1 with a straight line (step S31).
- the extension direction of the finger can be recognized.
- skeletons for all fingers are obtained. Thereby, the hand pose can be recognized. That is, it is possible to recognize which of the thumb, the index finger, the middle finger, the ring finger, and the little finger is spread and which finger is gripped.
- a difference in hand pose is detected in comparison with the image data of several frames performed immediately before (step S32). That is, the hand movement can be recognized by comparing with the image data of the last several frames.
- the recognized hand shape is delivered to the event service unit 460 as gesture data (step S33).
- step S34 the application software unit 459 performs a behavior corresponding to the event.
- the display service unit 462 requests drawing in the three-dimensional space (step S35).
- the graphic operation unit 463 refers to the calibration data recording unit 457 using the calibration service unit 461, and corrects the display (step S36).
- display is performed on the transflective display 220 by the display arithmetic unit 464 (step S37).
- the root point of the finger is detected by the process of step S30 and the process of step S31, but the root point detection method is not limited to this.
- the length of the reference line segment PP 1 that connects a pair of adjacent vertices p 1 on one side and the other side of the vertex p 0 is calculated.
- the length of a line connecting between the pair of vertices p 2 at the one side and the other side is calculated.
- the length of the line segment connecting the pair of vertices on the one side and the other side is calculated in the order from the vertex located closer to the vertex p 0 to the vertex located further away.
- Such line segments are approximately parallel to each other without intersecting within the outer shape OF.
- the root point can be determined by detecting the line segment that does not exceed the predetermined amount and the farthest from the apex p 0 and extracts one point on the detected line segment. .
- FIG. 17 is a schematic diagram illustrating another example of finger recognition
- FIG. 18 is a graph illustrating an example of the process of FIG. 17,
- FIG. 19 is a schematic diagram illustrating still another example of finger recognition. .
- a polygon having about 100 vertices is created from image data obtained by depth map processing using the infrared detection camera 412 (FIG. 16). Step S26). Even in the present embodiment, the apex is a low pass filter (LPF) treated to be smooth, by creating a new polygon having more vertexes a n, the contour OF hand shown in FIG. 17 extraction (Refer to FIG. 16, step S27).
- LPF low pass filter
- the maximum inscribed circle C of the hand outline OF is extracted.
- the maximum inscribed circle C can be recognized as the position of the palm (or instep) as will be described later with reference to FIG.
- the center C0 of the maximum inscribed circle C is extracted as a reference point (hereinafter referred to as a reference point C0).
- the distance d between the reference point C0 measures to form the outer shape OF, and the vertex a n respectively set at predetermined intervals, the distance d between the reference point C0.
- the closer to the tip of the finger there is a distance d greater tendency between the reference point C0 and vertex a n, the closer to the interdigital reference point C0 and vertex a n
- the distance d tends to be small. Based on such a tendency, it is possible to identify the tip portion of the finger and the inter-finger portion.
- the vertex a n a distance between the reference point C0 and vertex a n a vertical axis by scanning in one direction to the ulnar side flexures from (little finger side) (thumb side) along the contour OF Measure and examine the relationship between the number of scanning points n and the distance d.
- a graph showing the relationship is shown in FIG. 18 (vertical axis: distance d, horizontal axis, number of scanning points n).
- the horizontal axis may represent a scanning distance instead of the number of scanning points n.
- the distance d with respect to the number n of scanning points exhibits a curve having an extreme value.
- the distance d is the vicinity of the position of the vertex a n corresponding to the scan number n when showing the extreme value may be a feature of the finger.
- the position of the vertex a i corresponding to the number of scanning points i (see FIG. 17) when the distance d indicates one maximum L in FIG. 18 can be determined as the tip of the finger.
- the vertex a i used for the determination of the tip of the finger is treated as the tip of the finger in the same manner as the shared vertex p 0 (see (A) in FIG. 15) extracted in step S29 of FIG. You can also. Further, as in FIG. 15 and (A), the vertex a i, calibrated to the center of the inscribed circle of the contour OF at vertex a i, can also be treated the center of the inscribed circle as center point P0.
- the position of the vertex ak (see FIG. 17) corresponding to the number of scanning points k when the distance d indicates one minimum value LR can be determined as the inter-finger portion.
- the vertex a k used for the determination of the inter-finger portion is, for example, a determination between the scale side and the flexure side based on the fact that the distance d between the thumb and the index finger (FIG. 18FT) is smaller than the distance between the other fingers. Can be used for. Further, the vertex a k used for the determination of the inter-finger portion is handled in the same manner as the vertex p k (see (B) in FIG. 15) in step S30 in FIG. 16 for extracting the root point of the finger. May be. The vertex a k used for the determination of the inter-finger part may be handled differently from the root point of the finger, as illustrated above, or may conform to the root point of the finger by performing appropriate calibration. May be treated as
- FIG. 17 illustrates an example in which all fingers are stretched and spread. For example, when only the index and middle fingers are stretched and spread, the same maximum values as F and M appear in the graph of FIG. The same maximum does not appear for. Moreover, the minimum similar to MF or MF and RM appears, but the same minimum does not appear about others.
- the method obtains a distance d, which form the outer shape OF, and the vertex a n respectively set at predetermined intervals, but the distance between the reference point C0 shows a mode of measuring, the distance d
- the acquisition method is not limited to this method.
- an outline point b n is obtained as an intersection of a half line HL that rotates at a predetermined angle around the reference point C0 and the outline OF, and the outline point b n and the reference point C0
- the distance d may be acquired.
- the distance d between the reference point C0 and the outline point b n tends to increase as the distance from the finger tip increases, and the reference point C0 and the outline point b n increase as the distance between the fingers increases.
- the distance d tends to be small. Based on such a tendency, it is possible to identify the tip portion of the finger and the inter-finger portion.
- the relationship between the number of scanning points n and the distance d when the outline point b n is scanned in one direction along the outline OF from the scale side (little finger side) to the flexion side (thumb side) has the same characteristics as FIG. To do. For this reason, it is possible to determine the tip portion of the finger based on the outer shape point b j in the case of showing the maximum value and the inter-finger portion based on the outer shape point b k in the case of showing the minimum value.
- FIG. 20 is a schematic diagram illustrating an example of palm recognition.
- the maximum inscribed circle C inscribed in the outer shape OF of the image data is extracted.
- the position of the maximum inscribed circle C can be recognized as the palm position.
- FIG. 21 is a schematic diagram showing an example of thumb recognition.
- the thumb has characteristics different from the other four fingers of the index finger, the middle finger, the ring finger, and the little finger.
- ⁇ 1 involving the thumb tends to be the largest.
- ⁇ 11 involving the thumb tends to be the largest.
- the thumb is determined based on such a tendency. As a result, it is possible to determine whether it is the right hand or the left hand, or the front or back of the palm.
- arm recognition Next, arm recognition will be described. In the present embodiment, arm recognition is performed after any of a finger, palm, and thumb is recognized. Note that the arm recognition may be performed before recognizing any one of the finger, the palm, and the thumb, or at least one of them.
- the polygon is extracted in a larger area than the hand-shaped polygon of the image data.
- the process of steps S21 to S27 is performed in a range of 5 cm to 100 cm in length, and more preferably in a range of 10 cm to 40 cm to extract the outer shape.
- a rectangular frame circumscribing the extracted outer shape is selected.
- the square frame is a parallelogram or a rectangle.
- the extension direction of the arm can be recognized from the extension direction of the long side, and the direction of the arm can be determined from the direction of the long side. I can do it.
- the movement of the arm may be detected in comparison with the image data of the previous few frames.
- the finger, palm, thumb, and arm are detected from the two-dimensional image.
- the present invention is not limited to the above, and the infrared detection unit 410 may be further added, and only the infrared detection camera 412 is used. May be added to recognize a three-dimensional image from a two-dimensional image. As a result, the recognition accuracy can be further increased.
- FIG. 22A is a schematic external view of a hand (right hand) in the shape of a fist to be recognized from the palm side (hereinafter, hand H1 P ), and FIG. It is a typical external view when observing from the back side (hereinafter, hand H1 D ).
- a polygon having about 100 vertices is created from image data obtained by depth map processing using the infrared detection camera 412 (see FIG. 16).
- the palm-side fist shown in FIG. 23A is created by performing a low-pass filter (LPF) process so that the vertices are smooth and creating a new polygon having more vertices.
- LPF low-pass filter
- the outer shape OF P of the hand and the outer shape OF D of the dorsal fist hand shown in FIG. 23B are extracted (see FIG. 16, step S27).
- the outer OF D contour OF P and Oyobi view 23 (b) of FIG. 23 (a), is similar to each other, it is difficult not. Therefore, it is possible to determine whether the recognition target is the palm side or the back side by performing the following processing.
- Contour OF P in order to extract a plurality of points in the OF D, first extracts the maximum inscribed circle C of the outer OF P, OF D. Further, the center C0 of the maximum inscribed circle C is extracted as a reference point (hereinafter referred to as a reference point C0).
- chord of the maximum inscribed circle C passing through the reference point C0 is set.
- the reference point C0 is also set as the extraction point E.
- five extraction points E including the reference point C0 are set for each string.
- FIGS. 24A and 24B are schematic views in which the outer shape OF P of FIG. 23A and the outer shape OF D of FIG. 23B are superimposed and displayed on the hands H1 P and H1 D , respectively. Indicates.
- the distance from the infrared detection unit 410 is measured.
- the measured depth DP is aggregated statistically. Specifically, a measure of variation in measured depth is obtained.
- a measure of variation for example, at least one of standard deviation, variance, range (that is, a range having a maximum value and a minimum value at an upper limit and a lower limit), a quartile range, an average difference, and an average absolute deviation, for example. May be used.
- FIG. 25 (a) in FIG. 24 (a) a is a schematic diagram showing a cross-sectional view of the hand H1 P by a plane parallel to the y-z plane containing the chord C v
- Fig 25 (b) is in FIG. 24 (b)
- FIG. 26 (a) in FIG. 24 (a) a is a schematic diagram showing a cross-sectional view of the hand H1 P by a plane parallel to the x-z plane containing the chord C h
- FIG. 26 (b) in FIG. 24 (b) the is a schematic view showing a cross-sectional view of the hand H1 D by a plane parallel to the x-z plane containing the chord C h.
- a standard value of standard deviation as a judgment standard is set, and if it is equal to or higher than the standard value, it is judged as a palm side, and when it is below the standard value, it is judged as a back side. it can.
- FIG. 27 is a schematic diagram of the outer shape and extraction point setting in FIGS. 22A and 22B, showing another example of the identification processing on the palm side and the back side in FIGS. 22A and 22B.
- FIG. 27 as a chord passing through the reference point C0, a chord C pd in a direction connecting the proximal and distal ends of the hands H1 P and H1 D and a chord C ur perpendicular to the chord C pd are set.
- the string C pd can be set as a string parallel to the extending direction of the arm.
- a plurality of extraction points E are set at predetermined intervals in the determined chords C pd and C ur , and a plurality of target points S projected onto the hands H1 P and H1 D in the z-axis direction. Is set, the variation in depth DP for a plurality of target points S is examined, and the palm side and the back side are identified. The identification of the palm side and the dorsal side can be based on the relationship between the variation in the depth DP and the hands H1 P and H1 D , as in FIGS.
- chord C pd and chord C ur of the chord C v and chord C h either alone (e.g. chord C v only, or chord C pd only) may define.
- any other number of strings may be defined by an arbitrary number regardless of whether or not they pass through the reference point C0.
- a chord passing through the reference point C0 is set to determine the extraction point E.
- a concentric circle centered on the reference point C0 is set inside the maximum inscribed circle C.
- the extraction point E may be determined thereon, or a polygon having a center of gravity as the reference point C0 and other arbitrary figures may be set, and the extraction point E may be determined thereon.
- the recognition target is exemplified by the hands H1 P and H1 D in the shape of the fist with all fingers bent, but the shape of the hand is not limited to this mode. Any shape may be used as long as at least one of the fingers is bent inward (that is, palm side).
- the right and left of the hand can be identified by examining the tendency of the depth of the target point S in the direction connecting the ulnar side and the flexion side of the hand (hereinafter referred to as direction UR).
- the direction UR connecting the hand side and the flex side is preferably the direction of the chord Cur in FIG.
- any chord having a chord C h a as illustrated, the direction and -30 ° or + 30 ° or less angle chord C ur in Fig. 23 The direction of is also allowed.
- linear regression analysis is performed on the obtained depth DP data of the target point S. Specifically, the tendency of the depth DP at each position in the UR direction is analyzed.
- the relationship between the depth DP shown in FIGS. 26 (a) and 26 (b) and the position in the UR direction is shown in the graphs of FIGS. 28 (a) and 28 (b), respectively.
- the horizontal axis represents the relative distance (U) of the target point S from the flexure side in the UR direction
- the vertical axis represents the depth (DP) of the target point S.
- Gesture data stocked in the gesture data recording unit 455 (see FIG. 3) is registered by the user.
- the gesture data is set as a gesture command by the user, and further rewritten as necessary.
- FIG. 29 is a flowchart showing an example of processing for registering gesture data in the gesture data recording unit 455.
- the application software unit 459 activates the gesture setting application in accordance with a user operation.
- a gesture data registration function is selected from the functions displayed on the application screen (step S41).
- preparation for imaging starts.
- imaging preparation a user uses a hand and an arm to represent a form desired to be registered as a gesture. Imaging is waited until the user determines the shape of the hand representing the gesture (step S42).
- the imaging standby time can be set to 5 seconds, for example.
- a part including at least a part of the hand and arm representing the gesture is photographed (step S43).
- outer shape data is acquired as a series of detected outer shapes.
- a moving image is acquired by photographing a hand and an arm showing a gesture for a certain period of time.
- the shooting time can be set to 10 seconds, for example.
- outer shape data may be acquired as a plurality of detected outer shapes by shooting a still image a plurality of times.
- a plurality of frames can be acquired by performing continuous shooting while the gesture is shown.
- a plurality of frames can be acquired by shooting the same gesture at different times and places.
- Photographing is performed by the infrared detection unit 410, for example.
- the infrared detection unit 410 detects the outer shape of the hand and arm indicating a gesture.
- the outer shape detection is performed by the same processing as steps S22 to S25 in FIG. This outer shape detection process is performed for each of a plurality of frames.
- the hand and arm feature portions indicating the gesture are analyzed (step S44).
- the analysis of the characteristic part is performed for each of the detected plurality of external shapes.
- Features to be analyzed include portions of interest that exhibit anatomical features such as the number and position of fingers in a predetermined form.
- the position and / or angle value of the feature portion is analyzed (step S45).
- an anatomical feature point in the object such as a point representing the fingertip and the base of the finger, can be represented by adding coordinate information.
- the angle of the feature portion can be expressed by adding angle information based on the extending direction of the finger and the extending direction of the arm.
- step S44 and step S45 the same processing as the above-described finger recognition, palm recognition, and arm recognition is performed. More specifically, the same processing as steps S26 to S31 in FIG. 16 is performed. As a result, the skeleton of all fingers is obtained by performing the same process for all fingers. Thereby, the extending direction of the finger, specifically, the angle of the finger around the finger joint can be recognized. Further, the position of the feature point indicating the fingertip, the finger base, or the like can be recognized by adding coordinate information. Furthermore, the form of the hand can be recognized. For example, it is possible to recognize the form of each finger (specifically, which one of the thumb, forefinger, middle finger, ring finger, and little finger is bent and which finger is extended).
- the palm position can be recognized by palm recognition as in FIG. 20, and the right hand or left hand, or the front or back of the palm can be determined by thumb recognition as in FIG. Thereby, the position of a predetermined finger can be recognized. Furthermore, by arm recognition, it is possible to determine the arm extending direction, specifically the arm angle around the elbow joint.
- step S45 the range of movement of the hand and arm showing the gesture to be photographed in step S43 is also derived by integrating the information of the above-described feature portions extracted for a plurality of external shapes.
- the movable range can be derived by obtaining a range including the maximum value and the minimum value of the angle obtained by the above-described extraction of the characteristic portion.
- the movable range can be derived by obtaining a range including the coordinate locus of the feature point indicating the fingertip or the like.
- the plurality of outer shapes are compared with each other over time based on the difference between the characteristic portions extracted for the plurality of outer shapes. Thereby, it is possible to recognize the transition of the outer shape accompanying the gesture operation.
- the user determines whether or not to record the analysis result as gesture data (step S46). In this case, it may be possible to confirm the form of the hand and arm taken by reproducing the taken moving image and displaying the analysis result.
- recording as gesture data Yes in step S46
- it is recorded in the gesture data recording unit 455 (step S47).
- the recording standby can be performed again (step S42) to record another moving image without recording in the gesture data recording unit 455.
- the aspect which acquires a series of external shape or a some external shape was mentioned, it is not limited to this aspect.
- one outline may be acquired, the feature point and the value of the position and / or direction of the acquired outline may be analyzed and recorded in the gesture data recording unit 455.
- FIG. 30 is a flowchart illustrating an example of association processing in which gesture data is recorded in association with an operation of an application that should use the gesture data as a command in the gesture data recording unit 455.
- a gesture command setting function is selected from the functions displayed on the screen of the gesture setting application in accordance with a user operation (step S51).
- the application software unit 459 calls and refers to the application operation command (step S52).
- the application operation includes any operation used when using the application, such as activation and termination of the application, selection and determination of each function in the application, and movement of the screen.
- the command to be generated by the gesture is selected from the referenced command data (step S53). Furthermore, the gesture data is called from the gesture data recording unit 455 and referred to (step S54). A gesture to be associated with the command selected in step S53 is selected (step S55). The user determines whether or not to set with the selected gesture (step S56). In the case of setting with the selected gesture (Yes in step S56), the gesture data is recorded in the gesture data recording unit 455 in a state in which the gesture data is to be generated as a command (step S57). When canceling the selected gesture (No in step S56), it is possible to select the gesture data again (step S54) and select another gesture (step S55).
- the application operation command is first called and selected, and then the gesture data is associated with the selected application command.
- the present invention is not limited to this mode. For example, after calling and selecting gesture data first, an application operation command may be associated with the selected gesture data. Further, for example, after calling an application operation command, the gesture data may be directly recorded and associated.
- FIG. 31 is a flowchart showing an example of a process in which a gesture command is rewritten in the gesture data recording unit 455.
- a gesture command rewriting function is selected from the functions displayed on the screen of the gesture setting application in accordance with a user operation (step S61).
- the gesture data is called from the gesture data recording unit 455 and referred to (step S62).
- a gesture command to be rewritten is selected (step S63), and it is determined whether or not to cancel the association with the application operation associated with the gesture command (step S64).
- the cancellation is executed, and the relationship between the gesture data constituting the gesture command and the application operation is lost (step S65). If the association is not cancelled (No in step S64), this process ends.
- step S65 After the relationship between the gesture data and the application operation is canceled in step S65, it is further determined whether or not to delete the gesture data itself whose relationship has been canceled (step S66). When the gesture data itself is also deleted (Yes in step S66), the gesture data is deleted from the gesture data recording unit 455 (step S67).
- step S67 When the gesture data is deleted in step S67, the gesture data registration process described in FIG. 29 is performed (step S68). Thereafter, the gesture command setting process described with reference to FIG. 30 is performed to set a new gesture command (step S69).
- Step S69 when the gesture data is not deleted (No in step S66), the gesture command setting process described in FIG. 30 is performed, and a new gesture command is set by associating the gesture data with another application operation.
- the method of performing gesture identification using the gesture data in the gesture data recording unit 455 recorded as described above is as described in steps S1 to S4 in FIG. More specifically, as in the above-described gesture data registration, a plurality of frames of target outline image data are acquired in step S2, and information on the outline feature and its movable range is acquired in step S3, respectively. . Further, in step S4, the feature part of the outer shape of the gesture data recorded in the gesture data recording unit 455 and its movable range are compared with the feature part of the outer shape of the gesture to be identified and its movable range. By determining the coincidence between the two data, it is determined which of the gesture data recorded in the gesture data recording unit 455 corresponds to the gesture to be identified.
- step S5 the application software unit 459 performs a predetermined application operation using the gesture determined by the gesture identification unit 456 as a command.
- FIG. 32 is a schematic diagram illustrating an example of display on the transflective display 220 of the eyeglass display device 100.
- an advertisement 221 is displayed on a part of the semi-transparent display 220 of the eyeglass display device 100, a map 222 is displayed on a part of the display, and the other part is a half of the eyeglass display device 100.
- a landscape 223 is viewed through the transmissive display 220, and a weather forecast 224 and a time 225 are displayed.
- FIG. 33A illustrates an example of the field of view of the translucent display 220
- FIG. 33B illustrates an example of the display of the translucent display 220.
- the display that can be viewed by the eyeglass display device 100 is composed of a plurality of displays 701 to 707.
- a plurality of displays are segments forming a part of a continuous image in which all of them are integrated. By switching the visible portion of the continuous image, a switching display is performed in which a plurality of displays are smoothly transitioned without being interrupted.
- displays 703, 702, 701, 704, and 705 are provided in the vertical direction, and displays 706 and 707 are provided on the left and right with the display 701 as the center.
- the displays 701 to 707 can be freely deleted or changed by the user, and other displays can be added.
- the displays 701 to 707 are seamless continuous images, but the display to be switched may be an independent non-continuous image.
- the display 701 is displayed when the posture of the eyeglass display device 100 is horizontal, that is, when the user wears the eyeglass display device 100 and faces horizontally.
- a display 702 is displayed. That is, the direction in which the user faces is recognized based on a signal from at least one of the gyro sensor unit 420 and the acceleration detection unit 430 in the eyeglass display device 100.
- the display 702 may display a screen of a face recognition application, for example.
- a display 703 is displayed.
- a weather forecast may be displayed on the display 703.
- other sky information may be displayed on the display 703.
- an image of a constellation may be displayed depending on the time zone.
- a display 704 for example, a mail screen
- Display 705 for example, a map
- a display 706 for example, an Internet browser
- a display 707 for example, a call screen
- the display 701 to the display 707 are switched based on a signal from at least one of the gyro sensor unit 420 and the acceleration detection unit 430.
- the present invention is not limited to this. Switching may be performed by palm and arm recognition.
- the gyro sensor unit is a condition for switching at least one of the display 701 to the display 702, the display 701 to the display 704, the display 701 to the display 707, and the display 701 to the display 706.
- the level of the signal from at least one of 420 and the acceleration detection unit 430 may be set higher. Thereby, it is possible to prevent the display 701 from being switched to another display in a short time during walking. Moreover, when turning around urgently, a setting that is not particularly switched may be provided.
- the sky information display 703 and the map information display 705 may be panoramic displays. In this case, the displays 703 and 705 may be scrolled in accordance with the movement in the left-right direction.
- FIG. 34 is a schematic diagram showing an example of the occurrence of a predetermined event
- FIG. 35 is a schematic diagram showing another example of the event occurrence of FIG. 34
- FIG. 36 is a schematic diagram showing an example of the occurrence of another event.
- the shape of the hand H1 detected by the infrared detection unit 410 is displayed on the virtual image. Further, when the user's hand is away from the operation area 410c, a shadow H2 having the shape of the hand H1 is displayed as an example of the event. Thereby, the user can easily recognize that the hand is present in the gesture region 410g.
- the virtual image displays the shape of the hand H1 detected by the infrared detection unit 410, and a shadow H3 that is darker than the shadow H2 has a small area around the shape of the hand H1. Is displayed. Therefore, the user can easily recognize that the hand is closer to the operation area 410c than in the case of FIG. Further, when the hand is in the operation area 410c, the shadows H2 and H3 are not displayed.
- the user does not need to search the operation area 410c by trial and error or groping. That is, the distance to the operation area 410c can be easily recognized based on the density of the shadow and how the hand shape deviates from the shadow.
- the circle display H4 may be performed on the fingertip.
- the present invention is not limited to this, and a ripple is generated in the display when it is within the operation area 410c.
- the vibration generation device may be provided in the eyeglass display device 100 to generate vibration, sound may be generated, or the display may be changed depending on at least one of the display blinking mode and the lighting illuminance. Good.
- the distance to the operation area 410c may be represented by a blinking interval, and the distance to the operation area 410c may be represented by lighting illuminance.
- lighting in darker colors red, black, purple, etc.
- lighting in lighter colors blue, yellow, pink, etc.
- Other human senses typically visual, auditory and tactile) ) May be triggered by any event.
- the virtual image display can be operated.
- the virtual image display can be enlarged or reduced, the display can be scrolled, or a point can be selected.
- additional display may be performed by touching the display of the advertisement 221.
- the advertisement 221 displays information such as merchandise and services of the store.
- more detailed information regarding the store may be additionally displayed.
- the advertisement 221 may be an image of the store itself taken by the camera unit 303, or automatically starts store recognition based on image data of the store by the camera unit 303.
- the store recognition application It may be recognition result information displayed on the screen.
- Display in parody mode Further, as shown in FIG. 38, when a logo mark of one company (XX company) is displayed on the transflective display 220, a competition or non-competition is made by touching the logo mark on the screen. Information related to other companies ( ⁇ company) can be displayed. In this case, for example, a logo of the other company may be displayed as a parody mode.
- FIG. 39 to FIG. 46 are schematic diagrams showing examples of gesture recognition.
- a menu screen V1 is displayed between the thumb and index finger. Also good.
- a predetermined image V2 may be displayed between the index finger and the middle finger.
- the face recognition application when the hand H1 is lightly opened and moved in the direction of the arrow by greeting, the face recognition application is automatically activated. Face recognition is automatically started based on the face data of the other person acquired by the camera unit 303, and information such as name, company name, job title, date and place of the last meeting is displayed on the face recognition application screen V3. . Further, a flag may be set each time the same person is recognized by the recognition of the face recognition application, and the number of flags may be displayed on the face recognition application screen V3. In this case, the background and color of the face recognition application screen V3 may be varied depending on the number of flags.
- an SNS (SOCIAL NETWORKING SERVICE) application can be automatically started by drawing the letter S of the alphabet with the finger of the hand H1, and the SNS application screen V5 can be displayed.
- the kanji application is started and the index finger of the hand H1 is recognized to display an additional brush image at the position of the index finger. .
- the sword application is started, and a sword image is additionally displayed at the position of the hand on the sword, and the virtual image display screen V7 is cut. it can.
- the camera application is automatically activated, and the scenery in the imaging frame extracted from the formed square in the camera application screen V8. Etc. may be imaged.
- the reference point C0 is the center of the maximum inscribed circle C of the OF D Since a plurality of extraction points E are set at predetermined intervals on the string, whether the hand is facing the palm side or the back side even though the number of extraction points is as few as 5 per string. Judgment can be made accurately.
- the position of the hand H1 P, H1 target point in ulnar wrinkles side and the connecting I direction (corresponding to the chord C h direction or chord C ur direction) of the D S By finding a linear relationship with the depth D, it can be determined that the hands H1 P and H1 D are the right hand.
- the infrared detection unit 410 serves both as the detection of the outer shapes OF P and OF D and the measurement of the depth DP, so that the configuration of the device can be simplified.
- the stereoscopic region (virtual image display region 2203D) of the stereoscopic image generated by the transflective display 220 and the depth detection region (three-dimensional space detection region) of the infrared detection unit 410 are used. 4103D) can detect the outlines OF P and OF D of the hands H1 P and H1 D in the shared area, and thus recognizes the shapes of the hands H1 P and H1 D while displaying a stereoscopic image. Can do.
- the shape recognition device of the present embodiment since the eyeglass display device 100 is provided, it is possible to perform hand shape recognition with the eyeglass display device 100 put on. Further, the outer shapes OF P and OF D of the hands H1 P and H1 D to be detected are almost the same as the outer shapes of the hands H1 P and H1 D that can be visually recognized by the user, and when the display object is operated and the gesture is registered. For example, the hands H1 P and H1 D can be detected while being aware of the form that is easily detected by the shape recognition device.
- control unit 450 corresponds to a “shape recognition device”
- the hands H1 P and H1 D correspond to “hands”
- the infrared detection unit 410 corresponds to an “outer shape detection unit”
- the outer shapes OF P , OF D corresponds to “detected outline”
- extraction point E corresponds to “extraction point”
- target point S corresponds to “target point”
- depth DP corresponds to “depth”
- maximum inscribed circle C corresponds to the "maximum inscribed circle”
- the reference point C0 corresponds to the "reference point”
- chord C h corresponds to the "horizontal chord” chord C v is the "vertical direction of the strings”
- the chord C pd corresponds to “a chord having a direction connecting the distal end and the proximal end”
- the chord C ur corresponds to “a chord having a direction connecting the flexure side and the scale side”
- a transflective display 220 corresponds to the “display device”
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Optics & Photonics (AREA)
- Signal Processing (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- Software Systems (AREA)
- User Interface Of Digital Computer (AREA)
- Image Analysis (AREA)
- Position Input By Displaying (AREA)
- Testing, Inspecting, Measuring Of Stereoscopic Televisions And Televisions (AREA)
- Eyeglasses (AREA)
- Controls And Circuits For Display Device (AREA)
Abstract
Description
特許文献1に記載の高速画像生成表示方法においては、立体構造をもつ対象を2次元画面に投影して表示する高速画像生成表示方法であって、対象の構成面は、対象座標系において、領域の大きさを少なくとも1つの要素として階層的に記述され、任意の視点から見た時の該対象の構成面を2次元画面へ投影するに際して、表示基準座標系原点または視点から対象座標系で表される該対象の任意の点までの距離を少なくとも1つのパラメータとして階層度を設定することを特徴とする。
特許文献2に記載の立体視画像生成方法は、三次元座標を有するポリゴンで構成されるオブジェクトのうち、平面視表示させるオブジェクトデータを基準カメラを原点とする基準カメラ座標系データに、立体視表示させるオブジェクトのデータを所定の視差角を有する右眼用及び左眼用視差カメラをそれぞれ原点とする右眼用及び左眼用視差カメラ座標系データに変換し、基準カメラ座標系のオブジェクトのデータと、右眼用視差カメラ座標系のオブジェクトのデータを右眼用画像データとして、ビデオメモリに描画し、基準カメラ座標系のオブジェクトのデータと、左眼用視差カメラ座標系のオブジェクトのデータを左眼用画像データとして、ビデオメモリに描画し、ビデオメモリに描画された右眼用画像データと左眼用画像データを合成して、立体視オブジェクトと平面視オブジェクトの混在する画像を立体視表示装置に表示することを特徴とする。
特許文献3に記載の方法は、ユーザの気質を示す属性を視覚表示に適用するための方法であって、ユーザの視覚表示をレンダリングするステップと、物理的な空間のデータを受信するステップであって、データが、物理的な空間内のユーザを代表しているものと、ユーザの気質を推論するために、少なくとも1つの検出可能な特徴を解析するステップと、ユーザの気質を示す属性を視覚表示に適用するステップと、を含む。
特許文献4に記載のシステムは、入力デバイスと、プロセッサに結合され、入力デバイスの方位を検出する検出器と、を備えているシステムであって、入力デバイスが、方位に対応する複数のモード方位を有し、複数のモード方位が、ジェスチャ制御システムの複数の入力モードに対応し、検出器が、ジェスチャ制御システムに結合され、方位に応答して、複数の入力モードからの入力モードの選択を自動的に制御する。
一局面に従う形状認識装置は、外形検知部と、抽出点設定部と、深度検知部と、向き認識部とを含む。外形検知部は、手の外形を検知する。抽出点設定部は、検知された外形の内部における複数の点を抽出点として設定する。深度検知部は、複数の抽出点にそれぞれ対応する手の表面上の対象点までの空間距離を深度として測定する。向き認識部は、計測された深度のばらつきを示す尺度に基づいて、手が掌側および背側のいずれを向いているかを判断する。
第2の発明に従う形状認識装置においては、第1の発明に従う形状認識装置において、基準点抽出部をさらに含む。基準点抽出部においては、検知された外形から、当該外形の最大内接円の中心点を基準点として抽出する。さらに、抽出点設定部は、基準点を通る最大内接円の弦を設定し、設定された弦上に所定の間隔で複数の抽出点を設定する。
第3の発明に従う形状認識装置においては、第2の発明に従う形状認識装置において、基準点を通る最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する。
第4の発明に従う形状認識装置においては、第2または第3の発明に従う形状認識装置において、基準点を通る最大内接円の弦として、手の遠位および近位を結んだ方向を有する弦と、手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する。
第5の発明に従う形状認識装置においては、一局面から第4の発明のいずれかに従う形状認識装置において、深度のばらつきを示す尺度が、標準偏差、分散、範囲、四分位数範囲、平均差、および平均絶対偏差の少なくともいずれかである。
第6の発明に従う形状認識装置においては、第2から第5の発明のいずれかに従う形状認識装置において、深度の線形回帰分析の結果に基づいて、手が右手および左手のいずれであるかを判断する左右認識部をさらに含む。
したがって、たとえ手が握りこぶし状態であっても、手の掌側および背側の識別と手の左右の識別との両方を行うことができる。
第7の発明に従う形状認識装置においては、一局面から第6の発明のいずれかに従う形状認識装置において、外形検知部および深度検知部が赤外線センサである。
これによって、赤外線センサが、外形検知部と深度検知部との両方を兼ねることができる。したがって、装置の構成を簡素化することができる。
第8の発明に従う形状認識装置においては、一局面から第7の発明のいずれかに従う形状認識装置において、立体視像を表示可能な表示装置をさらに含み、外形検知部が、表示装置により生成された立体視像の立体視領域と深度検知領域とが共有する共有領域において、手の外形を検知する。
他の局面に従う形状認識装置は、一局面から第8の発明のいずれかに従う形状認識装置を有するヘッドマウントディスプレイ装置である。
また、装置を頭に装着するため、検知される手の外形とユーザが視認できる手の外形とがほぼ同じとなり、表示オブジェクトの操作を行う場合およびジェスチャの登録を行う場合などに、形状認識装置に検知されやすい態様を意識しながら手を検知させることもできる。
さらに他の局面に従う形状認識プログラムは、外形検知処理と、抽出点設定処理と、深度検知処理と、向き認識処理とを含む。外形検知処理は、手の外形を検知する。抽出点設定処理は、検知された外形の内部における複数の点を抽出点として設定する。深度検知処理は、複数の抽出点にそれぞれ対応する手の表面上の対象点までの空間距離を深度として測定する。向き認識処理は、計測された深度のばらつきを示す尺度に基づいて、手が掌側および背側のいずれを向いているかを判断する。
第11の発明に従う形状認識プログラムにおいては、さらに他の局面に従う形状認識プログラムにおいて、基準点抽出処理をさらに含む。基準点抽出処理においては、検知された外形から、当該外形の最大内接円の中心点を基準点として抽出する。さらに、抽出点設定処理は、基準点を通る最大内接円の弦を設定し、設定された弦上に所定の間隔で複数の抽出点を設定する。
第12の発明に従う形状認識プログラムにおいては、第11の発明に従う形状認識プログラムにおいて、基準点を通る最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する。
第13の発明に従う形状認識プログラムにおいては、第11または第12の発明に従う形状認識プログラムにおいて、基準点を通る最大内接円の弦として、手の遠位および近位を結んだ方向を有する弦と、手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する。
第14の発明に従う形状認識プログラムにおいては、第11から第13の発明のいずれかに従う形状認識プログラムにおいて、深度の線形回帰分析の結果に基づいて、手が右手および左手のいずれであるかを判断する左右認識処理をさらに含む。
したがって、たとえ手が握りこぶし状態であっても、手の掌側および背側の識別と手の左右の識別との両方を行うことができる。
さらに他の局面に従う形状認識方法は、外形検知工程と、抽出点設定工程と、深度検知工程と、向き認識工程とを含む。外形検知工程は、手の外形を検知する。抽出点設定工程は、検知された外形の内部における複数の点を抽出点として設定する。深度検知工程は、複数の抽出点にそれぞれ対応する手の表面上の対象点までの空間距離を深度として測定する。向き認識工程は、計測された深度のばらつきを示す尺度に基づいて、手が掌側および背側のいずれを向いているかを判断する。
第16の発明に従う形状認識方法においては、さらに他の局面に従う形状認識方法において、基準点抽出工程をさらに含む。基準点抽出工程においては、検知された外形から、当該外形の最大内接円の中心点を基準点として抽出する。さらに、抽出点設定工程は、基準点を通る最大内接円の弦を設定し、設定された弦上に所定の間隔で複数の抽出点を設定する。
第17の発明に従う形状認識方法においては、第16の発明に従う形状認識方法において、基準点を通る最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する。
第18の発明に従う形状認識方法においては、第16または第17の発明に従う形状認識方法において、基準点を通る最大内接円の弦として、手の遠位および近位を結んだ方向を有する弦と、手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する。
第19の発明に従う形状認識方法においては、第16から第18の発明のいずれかに従う形状認識方法において、深度の線形回帰分析の結果に基づいて、手が右手および左手のいずれであるかを判断する左右認識工程をさらに含む。
したがって、たとえ手が握りこぶし状態であっても、手の掌側および背側の識別と手の左右の識別との両方を行うことができる。
220 半透過ディスプレイ
2203D 仮想イメージ表示領域(共有領域)
410 赤外線検知ユニット
4103D 三次元空間検知領域
450 制御ユニット
H1P,H1D 手
OFP,OFD 外形
C 最大内接円
C0 基準点
Ch,Cv,Cpd,Cur 弦
E 抽出点
S 対象点
DP 深度
また、本発明は、
以下に説明する眼鏡表示装置に限定されるものではなく、他のウェアラブル機器、その他入出力装置、表示装置、テレビジョン、モニタ、プロジェクタ等にも適用することができる。
図1は、一実施の形態にかかる眼鏡表示装置100の基本構成の一例を示す模式的外観正面図であり、図2は、眼鏡表示装置100の一例を示す模式的外観斜視図である。
図1および図2に示すように、眼鏡ユニット200は、眼鏡フレーム210および一対の半透過ディスプレイ220からなる。眼鏡フレーム210は、主にリムユニット211、テンプルユニット212を含む。
眼鏡フレーム210のリムユニット211により一対の半透過ディスプレイ220が支持される。
また、当該レンズ類の一部に、半透過ディスプレイ220を埋め込んで設けてもよい。
次に、通信システム300について説明を行なう。
通信システム300は、バッテリーユニット301、アンテナモジュール302、カメラユニット303、スピーカユニット304、GPS(Global Positioning System)ユニット307、マイクユニット308、SIM(Subscriber Identity Module Card)ユニット309およびメインユニット310を含む。
なお、カメラユニットにはCCDセンサが備えられてよい。スピーカユニット304は、ノーマルイヤホンであってもよいし、骨伝導イヤホンであってもよい。SIMユニット309には、NFC(Near Field Communication:近距離無線通信)ユニットおよび他の接触式ICカードユニット、ならびに非接触式ICカードユニットを含む。
したがって、ユーザは、眼鏡表示装置100を用いて、通信装置、スピーカおよびマイクにより、携帯電話と同様の通話機能を使用することができる。また、眼鏡型であるので、両手を利用せず、通話を行なうことができる。
続いて、操作システム400は、赤外線検知ユニット410、ジャイロセンサユニット420、加速度検知ユニット430および制御ユニット450からなる。赤外線検知ユニット410は、主に赤外線照射素子411および赤外線検知カメラ412からなる。
ジェスチャ識別ユニット456は、ジェスチャデータ記録ユニット455に記録されたジェスチャデータを参照し、解剖学的特徴が識別された外形からジェスチャの識別を行なう。なお、ジェスチャ識別ユニット456は、ジェスチャデータ記録ユニット455からのジェスチャデータを参照することとしているが、参照することに限定されず、他の任意のデータを参照してもよく、全く参照することなく処理してもよい。
以上により、図5(a)に示すように、手のジェスチャを認識する。
これによって、図5(b)に示すように、たとえば写真アプリによる画像が表示される。この際、当該画面には、カメラユニット303からの撮像データが表示されてよい。
次に、操作システム400の赤外線検知ユニット410の検知領域と、一対の半透過ディスプレイ220の仮想表示領域との関係について説明を行なう。
図6は、赤外線検知ユニット410の検知領域と、一対の半透過ディスプレイ220の仮想表示領域とを説明するための模式的斜視図であり、図7は図6の上面図であり、図8は、図6の側面図である。
三次元空間検知領域4103Dは、赤外線検知ユニット410からの円錐状または角錐状の三次元空間からなる。
また、本実施の形態においては、赤外線検知ユニット410を1個設けることとしているが、これに限定されず、赤外線検知ユニット410を複数個設けてもよいし、赤外線照射素子411を1個、赤外線検知カメラ412を複数個設けてもよい。
すなわち、実際には眼鏡表示装置100の半透過ディスプレイ220に表示されるものの、ユーザは、右目のイメージは右目側の半透過ディスプレイ220を透過し三次元空間領域2203DRで認識し、左目のイメージは左目側の半透過ディスプレイ220を透過し三次元空間領域2203DLで認識する。その結果、認識された両イメージがユーザの脳内で合成されることにより、仮想イメージ表示領域2203Dで仮想イメージとして認識することができる。
また、図8に示すように、一対の半透過ディスプレイ220よりも赤外線検知ユニット410が上方(y軸正方向)に配設されている場合について説明しているが、鉛直方向(y軸方向)に対して、赤外線検知ユニット410の配設位置が半透過ディスプレイ220よりも下方(y軸負方向)または半透過ディスプレイ220と同位置であっても、同様に、仮想イメージ表示領域2203Dは、三次元空間検知領域4103Dと共有する空間領域を有する。
続いて、図9から図11は、図6から図8において示した検知領域と仮想表示領域との他の例を示す模式図である。
この場合、入出力装置900による仮想イメージ表示領域2203Dが、三次元空間検知領域4103Dと共有の空間領域として生じる。
この場合でも、入出力装置900による仮想イメージ表示領域2203Dが、三次元空間検知領域4103Dと共有の空間領域として生じる。
続いて、検知領域における操作領域とジェスチャ領域とについて説明する。図12および図13は、検知領域における操作領域と、ジェスチャ領域との一例を示す模式図である。
また、三次元空間検知領域4103D内における操作領域410c以外の部分で、かつ腕の移動領域Lおよび移動領域Rを合わせた領域と重なる部分をジェスチャ領域410gとして設定する。
次いで、キャリブレーション処理について説明を行なう。図14は、キャリブレーション処理の説明を行なうためのフローチャートである。
また、キャリブレーション処理には、ユーザの個々で異なる指の長さ、手の長さ、腕の長さの調整も行なう。
すなわち、ユーザによりユーザの個々で異なる指の長さ、手の長さ、腕の長さが異なるので、操作領域410cの調整を行なうものである。
なお、ジェスチャ領域410gは、仮想イメージ表示領域2203Dと重ならないように配置しかつ深さ方向(z軸正方向)に厚みを持たせることが好ましい。
そのため、赤外線検知ユニット410からの信号を無処理のまま使用すると、ユーザは、手先が仮想イメージ表示領域2203Dから外れたとしても、そのような状態であることを体感しにくい。
その結果、ユーザは、両腕を最大限に伸ばした状態、または少し曲げた状態で、奥行きのある平面状の仮想イメージ表示領域2203D内の中央部から端部まで操作することができる。
続いて、半透過ディスプレイ220に、像の周囲を指で囲んでくださいと、表示を行なう(ステップS16)。ここで、像の近傍に指の形の像を薄く表示してもよいし、半透過ディスプレイ220に表示を行なう代わりにスピーカから音声により指示をユーザに伝えてもよい。
なお、上記においては、指で矩形を形作り、そのように定められた矩形と、像の外縁の矩形にあわせる。このことによって、指により定められた矩形の視認サイズおよび位置と像の外縁の矩形の視認サイズ及び位置とを合わせることとした。しかしながら、指によって形状を定める手法はこれに限定されず、表示された像の外縁を指でなぞる手法、表示された像の外縁上の複数の点を指で指し示す手法等、他の任意の手法であってもよい。また、これらの手法を複数のサイズの像について行ってもよい。
次いで、指認識について説明を行い、その後掌認識、腕認識の順で説明を行なう。図15は、指認識の一例を示す模式図である。図15において、(A)は指の先端付近の拡大図であり、(B)は指の根元付近の拡大図である。図16は、指認識の処理の一例を示すフローチャートである。
次に、赤外線検知ユニット410により画像データをピクセル単位で距離に置き換える(ステップS23)。この場合、赤外線の明るさは、距離の三乗に反比例する。これを利用し、デプスマップを作成する(ステップS24)。
続いて、二値化した画像データから約100個の頂点を持つポリゴンを作成する(ステップS26)。そして、頂点が滑らかになるようにローパスフィルタ(LPF)により、より多くの頂点pnを有する新たな多角形を作成することによって、図15に示す手の外形OFを抽出する(ステップS27)。
なお、本実施の形態においては、ステップS26において二値化したデータからポリゴンを作成するために抽出する頂点の数を約100個としているが、これに限定されず、1000個、その他の任意の個数であってもよい。
ステップS27で作成した新たな多角形の頂点pnの集合から、Convex Hullを用いて、凸包を抽出する(ステップS28)。
その後、ステップS27で作成された新たな多角形と、ステップS28で作成された凸包との共有の頂点p0を抽出する(ステップS29)。このように抽出された共有の頂点p0自体を指の先端点として用いることができる。
さらに、頂点p0の位置に基づいて算出される他の点を指の先端点として用いてもよい。例えば、図15(A)に示すように頂点p0における外形OFの内接円の中心を先端点P0として算出することもできる。
全ての指について同様の処理を行なうことで、全ての指のスケルトンを得る。これにより、手のポーズを認識することができる。すなわち、親指、人差し指、中指、薬指、小指のいずれの指が広げられ、いずれの指が握られているかを認識することができる。
グラフィック演算ユニット463は、キャリブレーションサービスユニット461を用いてキャリブレーションデータ記録ユニット457を参照し、表示の補正を行なう(ステップS36)。
最後に、ディスプレイ演算ユニット464により半透過ディスプレイ220に表示を行なう(ステップS37)。
図17は、指認識の他の例を示す模式図であり、図18は、図17の処理の一例を示すグラフであり、図19は、指認識のさらなる他の例を示す模式図である。
また、指間部の判定に用いられた頂点akは、指の根元点を抽出するための図16のステップS30で、頂点pk(図15中(B)参照)と同様の取扱がされてもよい。
指間部の判定に用いられた頂点akは、上記例示のように、指の根元点とは別の取扱がされてもよいし、適宜較正を行うことによって、指の根元点に準じる点として取り扱われてもよい。
例えば図19に示すように、基準点C0を中心として所定の角度毎に回転する半直線HLと外形OFとの交点として外形点bnを得て、外形点bnと、基準点C0との距離dを取得してもよい。
次いで、図20は、掌認識の一例を示す模式図である。
次いで、腕認識について説明を行なう。本実施の形態において、腕認識は、指、掌および親指のいずれかを認識した後に実施する。なお、腕認識は、指、掌および親指のいずれかを認識する前、またはそれらの少なくともいずれかと同時に実施してもよい。
その後、抽出した外形に外接する四角枠を選定する。本実施の形態においては、当該四角枠は、平行四辺形または長方形からなる。
この場合、平行四辺形または長方形は、対向する長辺を有するので、長辺の延在方向から腕の延在方向を認識することができ、長辺の向きから腕の向きを判定することが出来る。なお、ステップS32の処理と同様に、直前の数フレームの画像データと比較して、腕の動きを検知させてもよい。
図22(a)は、認識対象となる握りこぶしの形状の手(右手)を掌側から視認した場合(以下、手H1P)の模式的外観図であり、図22(b)は、当該手を背側から視認した場合(以下、手H1D)の模式的外観図である。
図24(a)および図24(b)は、図23(a)の外形OFPと及び図23(b)の外形OFDとをそれぞれ手H1P,H1Dに重ね合わせて表示した模式図を示す。
このように、掌側の手H1Pと背側の手H1Dとは、当該深度DPのばらつきの尺度が相対的に異なることに基づいて識別することができる。
図27は、図22(a)および図22(b)の掌側および背側の識別処理の他の例を示す、図22(a)および図22(b)の外形および抽出点設定の模式図である。図27においては、基準点C0を通る弦として、手H1P,H1Dの近位および遠位を結ぶ方向の弦Cpdと、当該弦Cpdに垂直な弦Curとを設定する。なお、弦Cpdの設定は、腕の延在方向と平行な弦として設定することができる。
図23および図27の例では、基準点C0を通る弦として、弦Cvと弦Chとの両方、および弦Cpdと弦Curとの両方を定めたが、いずれか一方のみ(たとえば弦Cvのみ、または弦Cpdのみ)を定めてもよい。さらに、基準点C0を通ると通らないとを問わず、他の任意の弦を任意の数で定めてもよい。
さらに、手の尺側と撓側とを結ぶ方向(以下、方向UR)における対象点Sの深度の傾向を調べることによって、手の左右の識別を行うことができる。
ジェスチャデータ記録ユニット455(図3参照)にストックされるジェスチャデータは、ユーザによって登録される。また、ジェスチャデータは、ユーザによってジェスチャコマンドとして設定され、さらに必要に応じて書換えもされる。
図29は、ジェスチャデータ記録ユニット455へジェスチャデータを登録する処理の一例を示すフローチャートである。
動作の遷移が意図されないジェスチャの場合は、当該ジェスチャのサインを示したまま、ユーザ自身が当該ジェスチャとして意識する態様を逸脱しない程度に手および腕を様々に動かした様子を撮影することができる。
さらに、特徴部の位置および/または角度の値を分析する(ステップS45)。特徴部の位置としては、指先および指の根元を表す点など、対象における解剖学的特徴点を座標情報の付加により表すことができる。また、特徴部の角度としては、指の延在方向および腕の延在方向などに基づいた角度情報の付加により表すことができる。
より具体的には、図16のステップS26からS31と同じ処理が行われる。これによって、全ての指について同様の処理を行なうことで、全ての指のスケルトンを得る。これにより、指の延在方向、具体的には指の関節を中心とした指の角度を認識することができる。また、指先および指の根元等を示す特徴点の位置を、座標情報を付加することにより認識することができる。さらに、手の形態を認識することができる。たとえば、それぞれの指の形態(具体的には、親指、人差し指、中指、薬指、小指のいずれの指が曲げられ、いずれの指が伸びているか等)を認識することができる。
さらに、腕認識によって、腕の延在方向、具体的には肘の関節を中心とした腕の角度を判定することができる。
上述のほか、指先等を示す特徴点の座標の軌跡を含む範囲を求めることによって、可動範囲を導出することができる。
図30は、ジェスチャデータ記録ユニット455において、ジェスチャデータが、当該ジェスチャデータをコマンドとすべきアプリケーションの操作と関連付けられて記録される関連付け処理の一例を示すフローチャートである。
また、たとえば、アプリケーション操作コマンドを呼び出した後に、ジェスチャデータを直接記録させ、関連付ける態様としてもよい。
図31は、ジェスチャデータ記録ユニット455において、ジェスチャコマンドが書換えられる処理の一例を示すフローチャートである。
上述のように記録されたジェスチャデータ記録ユニット455内のジェスチャデータを利用してジェスチャの識別を行なう方法は、図4のステップS1からステップS4で説明した通りである。より具体的には、上述のジェスチャデータ登録時と同様に、ステップS2において、対象の外形イメージデータを複数フレーム取得し、それぞれ、ステップS3において、外形の特徴部およびその可動範囲の情報を取得する。さらに、ステップS4において、ジェスチャデータ記録ユニット455に記録されたジェスチャデータの外形の特徴部およびその可動範囲と、識別すべきジェスチャの外形の特徴部およびその可動範囲とを比較する。双方のデータの一致性を判断することによって、識別すべきジェスチャが、ジェスチャデータ記録ユニット455に記録されたジェスチャデータのうちどれに該当するかを判断する。
次に、図32は、眼鏡表示装置100の半透過ディスプレイ220の表示の一例を示す模式図である。
次に、眼鏡表示装置100の半透過ディスプレイ220に表示される表示の一例について説明を行なう。図33(a)は、半透過ディスプレイ220の視野の一例、図33(b)は、半透明ディスプレイ220の表示の一例を説明する図である。
図33に示すように、縦方向に表示703、702、701、704、705の表示が設けられており、表示701を中央として、左右に表示706,707が設けられる。なお、当然のことながら、当該表示701,~,707は、ユーザによって自由に削除または変更することができ、さらに他の表示を追加することもできる。
なお、本実施の形態においては、表示701,~,707はシームレスに連続した画像であるが、切換えされるべき表示は、それぞれが独立した非連続の像であってもよい。
一方、天空情報の表示703および地図情報の表示705はパノラマ表示であってよく、この場合、左右方向の動きに伴ってそれら表示703,705をスクロールさせてよい。
続いて、指、掌、手、腕が操作領域410cに存在する場合と、ジェスチャ領域410gに存在する場合との違いをユーザが認識し易いように、所定のイベントを発生させる。以下、所定のイベントについて説明を行なう。図34は、所定のイベント発生の一例を示す模式図であり、図35は、図34のイベント発生の他の例を示す模式図であり、図36は、他のイベント発生の一例を示す模式図である。
これにより、ユーザは、ジェスチャ領域410gに手が存在することを容易に認識できる。
以上の指、掌、腕認識およびイベント発生を伴う眼鏡表示装置100の使用態様について説明する。
例えば、広告221には、店舗の、商品、サービス等の情報が表示されている。ユーザがその広告221をタッチした場合、当該店舗に関するさらに詳しい情報を追加表示させてもよい。たとえば、飲食店の場合には、当該飲食店の代表メニュ、ユーザからの評価、価格帯等を表示させてもよい。
なお、広告221は、店舗をカメラユニット303で撮影された像そのものであってもよいし、カメラユニット303による当該店舗の撮像データに基づいて店舗認識を自動で開始し、その結果、店舗認識アプリ画面に表示された認識結果情報であってもよい。
また、図38に示すように、半透過ディスプレイ220に一の企業(○○社)のロゴマークが表示されている際に、画面中のロゴマークにタッチ等行なうことで、競合又は非競合の他の企業(△△社)に関連する情報を表示させることができる。この場合、例えばパロディモードとして、当該他の企業のロゴを表示させてもよい。
また、ユーザがジェスチャ領域410g内で所定の手のポーズを作ることにより、予め設定された動作が実施される。図39から図46は、ジェスチャ認識の例を示す模式図である。
Claims (19)
- 手の外形を検知する外形検知部と、
検知された前記外形の内部における複数の点を抽出点として設定する、抽出点設定部と、
前記複数の抽出点にそれぞれ対応する前記手の表面上の対象点までの空間距離を深度として測定する深度検知部と、
計測された前記深度のばらつきを示す尺度に基づいて、前記手が掌側および背側のいずれを向いているかを判断する向き認識部とを含む、形状認識装置。 - 検知された前記外形から、前記外形の最大内接円の中心点を基準点として抽出する、基準点抽出部をさらに含み、
前記抽出点設定部が、前記基準点を通る前記最大内接円の弦を設定し、前記設定された弦上に所定の間隔で前記複数の抽出点を設定する、請求項1に記載の形状認識装置。 - 前記基準点を通る前記最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する、請求項2に記載の形状認識装置。
- 前記基準点を通る前記最大内接円の弦として、前記手の遠位および近位を結んだ方向を有する弦と、前記手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する、請求項2または3に記載の形状認識装置。
- 前記深度のばらつきを示す尺度が、標準偏差、分散、範囲、四分位数範囲、平均差、および平均絶対偏差の少なくともいずれかである、請求項1から4のいずれか1項に記載の形状認識装置。
- 前記深度の線形回帰分析の結果に基づいて、前記手が右手および左手のいずれであるかを判断する左右認識部をさらに含む、請求項2から5のいずれか1項に記載の形状認識装置。
- 前記外形検知部および前記深度検知部が赤外線センサである、請求項1から6のいずれか1項に記載の形状認識装置。
- 立体視像を表示可能な表示装置をさらに含み、
前記外形検知部が、前記表示装置により生成された立体視像の立体視領域と前記深度検知領域とが共有する共有領域において、前記手の外形を検知する、請求項1から7のいずれか1項に記載の形状認識装置。 - 請求項1から請求項8のいずれか1項に記載の形状認識装置を有するヘッドマウントディスプレイ装置。
- 手の外形を検知する外形検知処理と、
検知された前記外形の内部における複数の点を抽出点として設定する、抽出点設定処理と、
前記複数の抽出点にそれぞれ対応する前記手の表面上の対象点までの空間距離を深度として測定する深度検知処理と、
計測された前記深度のばらつきを示す尺度に基づいて、前記手が掌側および背側のいずれを向いているかを判断する向き認識処理とを含む、形状認識プログラム。 - 検知された前記外形から、前記外形の最大内接円の中心点を基準点として抽出する、基準点抽出処理をさらに含み、
前記抽出点設定処理が、前記基準点を通る前記最大内接円の弦を設定し、前記設定された弦上に所定の間隔で前記複数の抽出点を設定する、請求項10に記載の形状認識プログラム。 - 前記基準点を通る前記最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する、請求項11に記載の形状認識プログラム。
- 前記基準点を通る前記最大内接円の弦として、前記手の遠位および近位を結んだ方向を有する弦と、前記手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する、請求項11または12に記載の形状認識プログラム。
- 前記深度の線形回帰分析の結果に基づいて、前記手が右手および左手のいずれであるかを判断する左右認識処理をさらに含む、請求項11から13のいずれか1項に記載の形状認識プログラム。
- 手の外形を検知する外形検知工程と、
検知された前記外形の内部における複数の点を抽出点として設定する、抽出点設定工程と、
前記複数の抽出点にそれぞれ対応する前記手の表面上の対象点までの空間距離を深度として測定する深度検知工程と、
計測された前記深度のばらつきを示す尺度に基づいて、前記手が掌側および背側のいずれを向いているかを判断する向き認識工程とを含む、形状認識方法。 - 検知された前記外形から、前記外形の最大内接円の中心点を基準点として抽出する、基準点抽出工程をさらに含み、
前記抽出点設定工程が、前記基準点を通る前記最大内接円の弦を設定し、前記設定された弦上に所定の間隔で前記複数の抽出点を設定する、請求項15に記載の形状認識方法。 - 前記基準点を通る前記最大内接円の弦として、水平方向の弦および垂直方向の弦の少なくともいずれかを設定する、請求項16に記載の形状認識方法。
- 前記基準点を通る前記最大内接円の弦として、前記手の遠位および近位を結んだ方向を有する弦と、前記手の撓側および尺側を結んだ方向を有する弦との少なくともいずれかを設定する、請求項16または17に記載の形状認識方法。
- 前記深度の線形回帰分析の結果に基づいて、前記手が右手および左手のいずれであるかを判断する左右認識工程をさらに含む、請求項16から18のいずれか1項に記載の形状認識方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/768,485 US10095030B2 (en) | 2013-02-19 | 2013-07-23 | Shape recognition device, shape recognition program, and shape recognition method |
JP2015501083A JP6074494B2 (ja) | 2013-02-19 | 2013-07-23 | 形状認識装置、形状認識プログラム、および形状認識方法 |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
PCT/JP2013/000909 WO2014128749A1 (ja) | 2013-02-19 | 2013-02-19 | 形状認識装置、形状認識プログラム、および形状認識方法 |
JPPCT/JP2013/000909 | 2013-02-19 | ||
PCT/JP2013/002524 WO2014128773A1 (ja) | 2013-02-19 | 2013-04-12 | ジェスチャ登録装置、ジェスチャ登録プログラムおよびジェスチャ登録方法 |
JPPCT/JP2013/002524 | 2013-04-12 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014128789A1 true WO2014128789A1 (ja) | 2014-08-28 |
Family
ID=51390597
Family Applications (5)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/000909 WO2014128749A1 (ja) | 2013-02-19 | 2013-02-19 | 形状認識装置、形状認識プログラム、および形状認識方法 |
PCT/JP2013/002524 WO2014128773A1 (ja) | 2013-02-19 | 2013-04-12 | ジェスチャ登録装置、ジェスチャ登録プログラムおよびジェスチャ登録方法 |
PCT/JP2013/003946 WO2014128787A1 (ja) | 2013-02-19 | 2013-06-24 | 追従表示システム、追従表示プログラム、および追従表示方法、ならびにそれらを用いたウェアラブル機器、ウェアラブル機器用の追従表示プログラム、およびウェアラブル機器の操作方法 |
PCT/JP2013/004485 WO2014128788A1 (ja) | 2013-02-19 | 2013-07-23 | 形状認識装置、形状認識プログラム、および形状認識方法 |
PCT/JP2013/004486 WO2014128789A1 (ja) | 2013-02-19 | 2013-07-23 | 形状認識装置、形状認識プログラム、および形状認識方法 |
Family Applications Before (4)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/000909 WO2014128749A1 (ja) | 2013-02-19 | 2013-02-19 | 形状認識装置、形状認識プログラム、および形状認識方法 |
PCT/JP2013/002524 WO2014128773A1 (ja) | 2013-02-19 | 2013-04-12 | ジェスチャ登録装置、ジェスチャ登録プログラムおよびジェスチャ登録方法 |
PCT/JP2013/003946 WO2014128787A1 (ja) | 2013-02-19 | 2013-06-24 | 追従表示システム、追従表示プログラム、および追従表示方法、ならびにそれらを用いたウェアラブル機器、ウェアラブル機器用の追従表示プログラム、およびウェアラブル機器の操作方法 |
PCT/JP2013/004485 WO2014128788A1 (ja) | 2013-02-19 | 2013-07-23 | 形状認識装置、形状認識プログラム、および形状認識方法 |
Country Status (3)
Country | Link |
---|---|
US (5) | US10295826B2 (ja) |
JP (6) | JP6195893B2 (ja) |
WO (5) | WO2014128749A1 (ja) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140139463A1 (en) * | 2012-11-21 | 2014-05-22 | Bokil SEO | Multimedia device for having touch sensor and method for controlling the same |
WO2015122079A1 (ja) * | 2014-02-14 | 2015-08-20 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置および情報処理方法 |
JP2015153179A (ja) * | 2014-02-14 | 2015-08-24 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置および情報処理方法 |
WO2016052061A1 (ja) * | 2014-09-30 | 2016-04-07 | コニカミノルタ株式会社 | ヘッドマウントディスプレイ |
JP2016186680A (ja) * | 2015-03-27 | 2016-10-27 | セイコーエプソン株式会社 | インタラクティブプロジェクターおよびインタラクティブプロジェクターの制御方法 |
WO2016190057A1 (ja) * | 2015-05-22 | 2016-12-01 | コニカミノルタ株式会社 | ウェアラブル電子機器およびウェアラブル電子機器のジェスチャー検知方法 |
JP2017111722A (ja) * | 2015-12-18 | 2017-06-22 | 株式会社ブリリアントサービス | ヘッドマウントディスプレイ、ヘッドマウントディスプレイの表示方法、およびヘッドマウントディスプレイのプログラム |
JP2018067875A (ja) * | 2016-10-21 | 2018-04-26 | 京セラドキュメントソリューションズ株式会社 | メガネ型端末及び画像形成システム |
DE102017210317A1 (de) * | 2017-06-20 | 2018-12-20 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum Erfassen einer Nutzereingabe anhand einer Geste |
JPWO2021199730A1 (ja) * | 2020-03-31 | 2021-10-07 |
Families Citing this family (98)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB0905457D0 (en) | 2009-03-30 | 2009-05-13 | Touchtype Ltd | System and method for inputting text into electronic devices |
US10191654B2 (en) * | 2009-03-30 | 2019-01-29 | Touchtype Limited | System and method for inputting text into electronic devices |
JP6333801B2 (ja) * | 2013-02-19 | 2018-05-30 | ミラマ サービス インク | 表示制御装置、表示制御プログラム、および表示制御方法 |
US10295826B2 (en) * | 2013-02-19 | 2019-05-21 | Mirama Service Inc. | Shape recognition device, shape recognition program, and shape recognition method |
EP3061084A4 (en) * | 2013-10-23 | 2017-10-04 | Dock Technologies Inc. | Indicators |
JP6241230B2 (ja) * | 2013-11-28 | 2017-12-06 | 富士通株式会社 | 生体情報判定装置及びプログラム |
JP6091407B2 (ja) * | 2013-12-18 | 2017-03-08 | 三菱電機株式会社 | ジェスチャ登録装置 |
JPWO2015108112A1 (ja) * | 2014-01-15 | 2017-03-23 | 株式会社Juice Design | 操作判定装置、操作判定方法、および、プログラム |
JP2015149634A (ja) | 2014-02-07 | 2015-08-20 | ソニー株式会社 | 画像表示装置および方法 |
USD776710S1 (en) * | 2014-04-08 | 2017-01-17 | Samsung Electronics Co., Ltd. | Display screen or portion thereof with graphical user interface |
USD766951S1 (en) | 2014-05-01 | 2016-09-20 | Beijing Qihoo Technology Co. Ltd | Display screen with a graphical user interface |
US10304248B2 (en) * | 2014-06-26 | 2019-05-28 | Korea Advanced Institute Of Science And Technology | Apparatus and method for providing augmented reality interaction service |
JP5989725B2 (ja) * | 2014-08-29 | 2016-09-07 | 京セラドキュメントソリューションズ株式会社 | 電子機器及び情報表示プログラム |
USD767633S1 (en) * | 2014-08-29 | 2016-09-27 | Nike, Inc. | Display screen with emoticon |
JP6413521B2 (ja) * | 2014-09-08 | 2018-10-31 | 富士通株式会社 | 表示制御方法、情報処理プログラム、及び情報処理装置 |
US20170302904A1 (en) * | 2014-09-30 | 2017-10-19 | Mirama Service Inc. | Input/output device, input/output program, and input/output method |
US20170310944A1 (en) * | 2014-09-30 | 2017-10-26 | Mirama Service Inc. | Input/output device, input/output program, and input/output method |
USD828845S1 (en) | 2015-01-05 | 2018-09-18 | Dolby International Ab | Display screen or portion thereof with transitional graphical user interface |
US10477090B2 (en) * | 2015-02-25 | 2019-11-12 | Kyocera Corporation | Wearable device, control method and non-transitory storage medium |
JP6585355B2 (ja) * | 2015-03-04 | 2019-10-02 | 株式会社メガチップス | 画像認識装置 |
US9965029B2 (en) * | 2015-03-30 | 2018-05-08 | Sony Corporation | Information processing apparatus, information processing method, and program |
JP6354653B2 (ja) * | 2015-04-25 | 2018-07-11 | 京セラドキュメントソリューションズ株式会社 | 拡張現実操作システムおよび拡張現実操作プログラム |
JP6483514B2 (ja) * | 2015-04-28 | 2019-03-13 | 京セラ株式会社 | ウェアラブル装置、制御方法及び制御プログラム |
US9959677B2 (en) * | 2015-05-26 | 2018-05-01 | Google Llc | Multidimensional graphical method for entering and exiting applications and activities in immersive media |
EP3101629B1 (en) * | 2015-06-04 | 2021-03-17 | Nokia Technologies Oy | Mediated reality |
EP4374942A3 (en) * | 2015-08-04 | 2024-07-10 | Google LLC | Input via context sensitive collisions of hands with objects in virtual reality |
US10303254B2 (en) * | 2015-09-24 | 2019-05-28 | Stmicroelectronics Sa | Device and method for identifying tap or wipe hand gestures using time-of-flight sensing |
US9886095B2 (en) | 2015-09-24 | 2018-02-06 | Stmicroelectronics Sa | Device and method for recognizing hand gestures using time-of-flight sensing |
JP2017102598A (ja) * | 2015-11-30 | 2017-06-08 | 富士通株式会社 | 認識装置、認識方法および認識プログラム |
JP6597235B2 (ja) * | 2015-11-30 | 2019-10-30 | 富士通株式会社 | 画像処理装置、画像処理方法および画像処理プログラム |
JP2017099686A (ja) * | 2015-12-02 | 2017-06-08 | 株式会社ブリリアントサービス | ゲーム用ヘッドマウントディスプレイ、ゲーム用ヘッドマウントディスプレイのプログラム、およびゲーム用ヘッドマウントディスプレイの制御方法 |
CN108369451B (zh) * | 2015-12-18 | 2021-10-29 | 索尼公司 | 信息处理装置、信息处理方法及计算机可读存储介质 |
JP6630607B2 (ja) * | 2016-03-28 | 2020-01-15 | 株式会社バンダイナムコエンターテインメント | シミュレーション制御装置及びシミュレーション制御プログラム |
JP6200023B1 (ja) * | 2016-03-28 | 2017-09-20 | 株式会社バンダイナムコエンターテインメント | シミュレーション制御装置及びシミュレーション制御プログラム |
DE102016206142A1 (de) * | 2016-04-13 | 2017-10-19 | Volkswagen Aktiengesellschaft | Anwenderschnittstelle, Fortbewegungsmittel und Verfahren zur Erkennung einer Hand eines Anwenders |
KR102529119B1 (ko) * | 2016-06-27 | 2023-05-04 | 삼성전자주식회사 | 객체의 깊이 정보를 획득하는 방법, 디바이스 및 기록매체 |
JP6691015B2 (ja) * | 2016-08-03 | 2020-04-28 | ソフトバンク株式会社 | 機器制御装置 |
JP6851745B2 (ja) | 2016-08-04 | 2021-03-31 | 富士通株式会社 | 画像制御方法、装置、及びプログラム |
CN109923500B (zh) * | 2016-08-22 | 2022-01-04 | 奇跃公司 | 具有深度学习传感器的增强现实显示装置 |
US10609018B2 (en) * | 2016-12-05 | 2020-03-31 | Google Llc | Gesture-based access control in virtual environments |
JP6816528B2 (ja) * | 2017-01-25 | 2021-01-20 | 凸版印刷株式会社 | 携帯通信端末を制御するための方法およびプログラム、ならびに、携帯通信端末 |
JP2018132986A (ja) * | 2017-02-16 | 2018-08-23 | 株式会社東海理化電機製作所 | 画像認識装置 |
JP6776155B2 (ja) * | 2017-02-28 | 2020-10-28 | 株式会社コロプラ | 仮想現実を提供するための方法、および当該方法をコンピュータに実行させるためのプログラム、および当該プログラムを実行するための情報処理装置 |
US10620779B2 (en) * | 2017-04-24 | 2020-04-14 | Microsoft Technology Licensing, Llc | Navigating a holographic image |
US10578869B2 (en) | 2017-07-24 | 2020-03-03 | Mentor Acquisition One, Llc | See-through computer display systems with adjustable zoom cameras |
WO2019032967A1 (en) | 2017-08-10 | 2019-02-14 | Google Llc | HAND INTERACTION SENSITIVE TO THE CONTEXT |
KR102026475B1 (ko) * | 2017-08-20 | 2019-09-30 | 네이버 주식회사 | 시각적 입력의 처리 |
DE102017128588A1 (de) * | 2017-12-01 | 2019-06-06 | Prüftechnik Dieter Busch AG | System und verfahren zur erfassung und darstellung von messpunkten auf einer körperfläche |
DE102017130137A1 (de) * | 2017-12-15 | 2019-06-19 | Endress+Hauser SE+Co. KG | Verfahren zur vereinfachten Inbetriebnahme eines Feldgeräts |
WO2019178114A1 (en) * | 2018-03-13 | 2019-09-19 | Magic Leap, Inc. | Gesture recognition system and method of using same |
WO2019176009A1 (ja) * | 2018-03-14 | 2019-09-19 | マクセル株式会社 | 携帯情報端末 |
CN109104693A (zh) * | 2018-07-13 | 2018-12-28 | 安徽捷峰电子科技有限公司 | 一种老人监护用电子围栏 |
US11449586B2 (en) | 2018-07-20 | 2022-09-20 | Massachusetts Institute Of Technology | Authenticated intention |
US10679393B2 (en) | 2018-07-24 | 2020-06-09 | Snap Inc. | Conditional modification of augmented reality object |
US10855978B2 (en) * | 2018-09-14 | 2020-12-01 | The Toronto-Dominion Bank | System and method for receiving user input in virtual/augmented reality |
CN113227941B (zh) | 2018-12-26 | 2024-10-18 | 三星电子株式会社 | 用于识别用户的真正的手的方法以及用于该方法的可穿戴设备 |
US11442549B1 (en) * | 2019-02-07 | 2022-09-13 | Apple Inc. | Placement of 3D effects based on 2D paintings |
KR102102309B1 (ko) * | 2019-03-12 | 2020-04-21 | 주식회사 피앤씨솔루션 | 머리 착용형 디스플레이 장치의 3차원 가상공간을 위한 객체 인식 방법 |
WO2020209624A1 (en) * | 2019-04-11 | 2020-10-15 | Samsung Electronics Co., Ltd. | Head mounted display device and operating method thereof |
CN110052030B (zh) * | 2019-04-26 | 2021-10-29 | 腾讯科技(深圳)有限公司 | 虚拟角色的形象设置方法、装置及存储介质 |
US11194438B2 (en) * | 2019-05-09 | 2021-12-07 | Microsoft Technology Licensing, Llc | Capture indicator for a virtual world |
TWI719483B (zh) * | 2019-05-17 | 2021-02-21 | 雅得近顯股份有限公司 | 便利備忘操作系統 |
WO2020240835A1 (ja) * | 2019-05-31 | 2020-12-03 | 堺ディスプレイプロダクト株式会社 | 空中映像表示装置 |
US11043192B2 (en) * | 2019-06-07 | 2021-06-22 | Facebook Technologies, Llc | Corner-identifiying gesture-driven user interface element gating for artificial reality systems |
KR20190106851A (ko) * | 2019-08-27 | 2019-09-18 | 엘지전자 주식회사 | Xr 컨텐츠 제공 방법 및 xr 컨텐츠 제공 디바이스 |
US11275453B1 (en) | 2019-09-30 | 2022-03-15 | Snap Inc. | Smart ring for manipulating virtual objects displayed by a wearable device |
US12231613B2 (en) | 2019-11-06 | 2025-02-18 | Hes Ip Holdings, Llc | System and method for displaying an object with depths |
EP3846004B1 (en) | 2019-12-30 | 2024-12-18 | Dassault Systèmes | Selection of an edge with an immersive gesture in 3d modeling |
JP6821832B2 (ja) * | 2020-01-06 | 2021-01-27 | 株式会社バンダイナムコエンターテインメント | シミュレーション制御装置及びシミュレーション制御プログラム |
CN115443445A (zh) * | 2020-02-26 | 2022-12-06 | 奇跃公司 | 用于可穿戴系统的手部手势输入 |
US11277597B1 (en) | 2020-03-31 | 2022-03-15 | Snap Inc. | Marker-based guided AR experience |
US11798429B1 (en) | 2020-05-04 | 2023-10-24 | Snap Inc. | Virtual tutorials for musical instruments with finger tracking in augmented reality |
US11520399B2 (en) | 2020-05-26 | 2022-12-06 | Snap Inc. | Interactive augmented reality experiences using positional tracking |
TWI862393B (zh) | 2020-08-14 | 2024-11-11 | 美商海思智財控股有限公司 | 在即時影像上疊加虛擬影像的頭戴式虛擬影像模組 |
TWI838640B (zh) | 2020-09-03 | 2024-04-11 | 美商海思智財控股有限公司 | 改善雙眼視覺的系統與方法 |
US11925863B2 (en) | 2020-09-18 | 2024-03-12 | Snap Inc. | Tracking hand gestures for interactive game control in augmented reality |
KR102229758B1 (ko) * | 2020-09-24 | 2021-03-19 | 주식회사 플레임 | 모션 입력 기능을 가지는 안경 |
JPWO2022064827A1 (ja) * | 2020-09-25 | 2022-03-31 | ||
US11546505B2 (en) | 2020-09-28 | 2023-01-03 | Snap Inc. | Touchless photo capture in response to detected hand gestures |
JP7582690B2 (ja) | 2020-09-30 | 2024-11-13 | ヒーズ アイピー ホールディングス エルエルシー | 仮想現実機器および拡張現実機器用の仮想画像表示システム |
CN112305945B (zh) * | 2020-10-21 | 2021-07-13 | 丽水市正明机械科技有限公司 | 防护机构误动作规避平台 |
CN116724285A (zh) | 2020-12-29 | 2023-09-08 | 美国斯耐普公司 | 用于控制虚拟和图形元素的微手势 |
EP4272051A1 (en) | 2020-12-30 | 2023-11-08 | Snap, Inc. | Augmented reality precision tracking and display |
US11740313B2 (en) | 2020-12-30 | 2023-08-29 | Snap Inc. | Augmented reality precision tracking and display |
EP4248300A1 (en) * | 2021-01-25 | 2023-09-27 | HES IP Holdings, LLC | Systems and methods for object interactions |
EP4094120A4 (en) | 2021-02-08 | 2024-02-28 | HES IP Holdings, LLC | SYSTEM AND METHOD FOR IMPROVING VISUAL ACUITY |
US11531402B1 (en) | 2021-02-25 | 2022-12-20 | Snap Inc. | Bimanual gestures for controlling virtual and graphical elements |
US11809633B2 (en) | 2021-03-16 | 2023-11-07 | Snap Inc. | Mirroring device with pointing based navigation |
US11908243B2 (en) | 2021-03-16 | 2024-02-20 | Snap Inc. | Menu hierarchy navigation on electronic mirroring devices |
US11798201B2 (en) | 2021-03-16 | 2023-10-24 | Snap Inc. | Mirroring device with whole-body outfits |
US11734959B2 (en) | 2021-03-16 | 2023-08-22 | Snap Inc. | Activating hands-free mode on mirroring device |
US11978283B2 (en) | 2021-03-16 | 2024-05-07 | Snap Inc. | Mirroring device with a hands-free mode |
CN117178247A (zh) | 2021-04-19 | 2023-12-05 | 斯纳普公司 | 用于动画化及控制虚拟和图形元素的手势 |
US11947728B2 (en) | 2021-04-30 | 2024-04-02 | Samsung Electronics Co., Ltd. | Electronic device for executing function based on hand gesture and method for operating thereof |
CN113762093A (zh) * | 2021-08-18 | 2021-12-07 | 北京格灵深瞳信息技术股份有限公司 | 跑道冲刺计时方法、装置、电子设备和存储介质 |
EP4398072A4 (en) * | 2021-08-30 | 2025-01-29 | Softbank Corp | ELECTRONIC DEVICE AND PROGRAM |
CN113901971B (zh) * | 2021-12-09 | 2022-03-25 | 北京的卢深视科技有限公司 | 健身姿势矫正方法、装置、电子设备和存储介质 |
KR102570418B1 (ko) * | 2022-08-11 | 2023-08-25 | 주식회사 엠브이아이 | 사용자 행동을 분석하는 웨어러블 디바이스 및 이를 이용한 대상인식방법 |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH086708A (ja) * | 1994-04-22 | 1996-01-12 | Canon Inc | 表示装置 |
JP2011215922A (ja) * | 2010-03-31 | 2011-10-27 | Namco Bandai Games Inc | プログラム、情報記憶媒体及び画像生成システム |
Family Cites Families (81)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH0831140B2 (ja) | 1990-04-13 | 1996-03-27 | 株式会社エイ・ティ・アール通信システム研究所 | 高速画像生成表示方法 |
WO1994015286A1 (en) | 1992-12-23 | 1994-07-07 | Taligent, Inc. | Object oriented framework system |
JPH07210687A (ja) * | 1994-01-18 | 1995-08-11 | Matsushita Electric Ind Co Ltd | 形状検出装置 |
JPH0831140A (ja) | 1994-07-15 | 1996-02-02 | Victor Co Of Japan Ltd | テープリール |
US6002808A (en) * | 1996-07-26 | 1999-12-14 | Mitsubishi Electric Information Technology Center America, Inc. | Hand gesture control system |
JPH10207681A (ja) | 1997-01-17 | 1998-08-07 | Nec Corp | カーソル表示装置 |
JP4049877B2 (ja) | 1997-03-31 | 2008-02-20 | 株式会社ワコム | 電子ペンを用いたコンピュータシステム |
JP3491189B2 (ja) * | 1997-07-08 | 2004-01-26 | 松下電器産業株式会社 | 手の状態検出装置 |
US6363160B1 (en) * | 1999-01-22 | 2002-03-26 | Intel Corporation | Interface using pattern recognition and tracking |
JP2002290529A (ja) | 2001-03-28 | 2002-10-04 | Matsushita Electric Ind Co Ltd | 携帯通信端末、情報表示装置、制御入力装置および制御入力方法 |
JP3863809B2 (ja) | 2002-05-28 | 2006-12-27 | 独立行政法人科学技術振興機構 | 手の画像認識による入力システム |
JP4228646B2 (ja) | 2002-10-02 | 2009-02-25 | 株式会社セガ | 立体視画像生成方法および立体視画像生成装置 |
JP3903968B2 (ja) * | 2003-07-30 | 2007-04-11 | 日産自動車株式会社 | 非接触式情報入力装置 |
JP2005050284A (ja) | 2003-07-31 | 2005-02-24 | Toyota Motor Corp | 動き認識装置および動き認識方法 |
JP2005092419A (ja) * | 2003-09-16 | 2005-04-07 | Casio Comput Co Ltd | 情報処理装置およびプログラム |
JP2005301668A (ja) * | 2004-04-12 | 2005-10-27 | Seiko Epson Corp | 情報処理装置および情報処理プログラム |
CN101111817B (zh) | 2005-01-30 | 2011-05-04 | 斯威福波音特有限公司 | 电脑鼠标周边装置 |
AU2006252490A1 (en) | 2005-06-02 | 2006-12-07 | Poly Vision Corporation | Virtual flip chart method and apparatus |
US20090002342A1 (en) * | 2006-02-03 | 2009-01-01 | Tomohiro Terada | Information Processing Device |
US8665213B2 (en) * | 2006-02-08 | 2014-03-04 | Oblong Industries, Inc. | Spatial, multi-modal control device for use with spatial operating system |
JP2007164814A (ja) * | 2007-02-09 | 2007-06-28 | Toshiba Corp | インタフェース装置 |
WO2008137708A1 (en) * | 2007-05-04 | 2008-11-13 | Gesturetek, Inc. | Camera-based user input for compact devices |
US8005263B2 (en) * | 2007-10-26 | 2011-08-23 | Honda Motor Co., Ltd. | Hand sign recognition using label assignment |
KR100931403B1 (ko) * | 2008-06-25 | 2009-12-11 | 한국과학기술연구원 | 손 동작에 의한 네트워크 상의 기기 및 정보 제어 시스템 |
CN102144206B (zh) * | 2008-09-03 | 2013-12-04 | 日本电气株式会社 | 姿势输入操作设备、方法、程序和便携式设备 |
JP5262681B2 (ja) * | 2008-12-22 | 2013-08-14 | ブラザー工業株式会社 | ヘッドマウントディスプレイ及びそのプログラム |
US9046924B2 (en) * | 2009-03-04 | 2015-06-02 | Pelmorex Canada Inc. | Gesture based interaction with traffic data |
US9256282B2 (en) | 2009-03-20 | 2016-02-09 | Microsoft Technology Licensing, Llc | Virtual object manipulation |
US8503720B2 (en) * | 2009-05-01 | 2013-08-06 | Microsoft Corporation | Human body pose estimation |
WO2010138743A2 (en) | 2009-05-27 | 2010-12-02 | Oblong Industries, Inc. | Spatial, multi-modal control device for use with spatial operating system |
US8379101B2 (en) * | 2009-05-29 | 2013-02-19 | Microsoft Corporation | Environment and/or target segmentation |
US8390680B2 (en) | 2009-07-09 | 2013-03-05 | Microsoft Corporation | Visual representation expression based on player expression |
TW201104494A (en) | 2009-07-20 | 2011-02-01 | J Touch Corp | Stereoscopic image interactive system |
JP2011081480A (ja) | 2009-10-05 | 2011-04-21 | Seiko Epson Corp | 画像入力システム |
US20110107216A1 (en) * | 2009-11-03 | 2011-05-05 | Qualcomm Incorporated | Gesture-based user interface |
TW201123031A (en) * | 2009-12-24 | 2011-07-01 | Univ Nat Taiwan Science Tech | Robot and method for recognizing human faces and gestures thereof |
US9128281B2 (en) * | 2010-09-14 | 2015-09-08 | Microsoft Technology Licensing, Llc | Eyepiece with uniformly illuminated reflective display |
JP5464661B2 (ja) * | 2010-03-12 | 2014-04-09 | Kddi株式会社 | 情報端末装置 |
JP5564300B2 (ja) * | 2010-03-19 | 2014-07-30 | 富士フイルム株式会社 | ヘッドマウント型拡張現実映像提示装置及びその仮想表示物操作方法 |
WO2011142317A1 (ja) * | 2010-05-11 | 2011-11-17 | 日本システムウエア株式会社 | ジェスチャー認識装置、方法、プログラム、および該プログラムを格納したコンピュータ可読媒体 |
FR2960986A1 (fr) * | 2010-06-04 | 2011-12-09 | Thomson Licensing | Procede de selection d’un objet dans un environnement virtuel |
JP5609416B2 (ja) * | 2010-08-19 | 2014-10-22 | ソニー株式会社 | 情報処理装置、情報処理方法およびプログラム |
US9013430B2 (en) * | 2010-08-20 | 2015-04-21 | University Of Massachusetts | Hand and finger registration for control applications |
JP2012048659A (ja) | 2010-08-30 | 2012-03-08 | Canon Inc | 画像処理装置、画像処理方法 |
CN102402680B (zh) * | 2010-09-13 | 2014-07-30 | 株式会社理光 | 人机交互系统中手部、指示点定位方法和手势确定方法 |
JP2012088819A (ja) * | 2010-10-15 | 2012-05-10 | Sharp Corp | 表示装置および表示方法 |
JP2012094060A (ja) | 2010-10-28 | 2012-05-17 | Sharp Corp | 電子装置 |
JP2012098988A (ja) * | 2010-11-04 | 2012-05-24 | Sony Corp | 画像処理装置および方法、並びにプログラム |
US9111138B2 (en) * | 2010-11-30 | 2015-08-18 | Cisco Technology, Inc. | System and method for gesture interface control |
US20120206584A1 (en) * | 2011-02-10 | 2012-08-16 | Meijo University | Integrated input interface |
JP5737748B2 (ja) | 2011-02-10 | 2015-06-17 | 学校法人 名城大学 | 統合入力インターフェース |
JP5641970B2 (ja) | 2011-02-18 | 2014-12-17 | シャープ株式会社 | 操作装置、再生装置及びテレビ受信装置 |
JP2012181809A (ja) * | 2011-03-03 | 2012-09-20 | Panasonic Corp | 機器制御装置、機器制御方法、機器制御プログラム、及び集積回路 |
JP2012208705A (ja) | 2011-03-29 | 2012-10-25 | Nec Casio Mobile Communications Ltd | 画像操作装置、画像操作方法およびプログラム |
JP5784818B2 (ja) * | 2011-03-29 | 2015-09-24 | クアルコム,インコーポレイテッド | 拡張現実システムにおける実世界表面への仮想画像のアンカリング |
US8929612B2 (en) * | 2011-06-06 | 2015-01-06 | Microsoft Corporation | System for recognizing an open or closed hand |
JP5845002B2 (ja) * | 2011-06-07 | 2016-01-20 | ソニー株式会社 | 画像処理装置および方法、並びにプログラム |
US9207767B2 (en) * | 2011-06-29 | 2015-12-08 | International Business Machines Corporation | Guide mode for gesture spaces |
US8558759B1 (en) * | 2011-07-08 | 2013-10-15 | Google Inc. | Hand gestures to signify what is important |
WO2013008236A1 (en) * | 2011-07-11 | 2013-01-17 | Pointgrab Ltd. | System and method for computer vision based hand gesture identification |
US8179604B1 (en) * | 2011-07-13 | 2012-05-15 | Google Inc. | Wearable marker for passive interaction |
US8751972B2 (en) * | 2011-09-20 | 2014-06-10 | Google Inc. | Collaborative gesture-based input language |
US9497501B2 (en) * | 2011-12-06 | 2016-11-15 | Microsoft Technology Licensing, Llc | Augmented reality virtual monitor |
US9141194B1 (en) * | 2012-01-04 | 2015-09-22 | Google Inc. | Magnetometer-based gesture sensing with a wearable device |
JP2012106005A (ja) | 2012-01-25 | 2012-06-07 | Konami Digital Entertainment Co Ltd | 画像表示装置、ゲームプログラム、ゲーム制御方法 |
US20130229396A1 (en) * | 2012-03-05 | 2013-09-05 | Kenneth J. Huebner | Surface aware, object aware, and image aware handheld projector |
US8933912B2 (en) * | 2012-04-02 | 2015-01-13 | Microsoft Corporation | Touch sensitive user interface with three dimensional input sensor |
US9477303B2 (en) * | 2012-04-09 | 2016-10-25 | Intel Corporation | System and method for combining three-dimensional tracking with a three-dimensional display for a user interface |
US9448636B2 (en) * | 2012-04-18 | 2016-09-20 | Arb Labs Inc. | Identifying gestures using gesture data compressed by PCA, principal joint variable analysis, and compressed feature matrices |
JP5174978B1 (ja) * | 2012-04-26 | 2013-04-03 | 株式会社三菱東京Ufj銀行 | 情報処理装置、電子機器およびプログラム |
US20130328925A1 (en) * | 2012-06-12 | 2013-12-12 | Stephen G. Latta | Object focus in a mixed reality environment |
US8836768B1 (en) * | 2012-09-04 | 2014-09-16 | Aquifi, Inc. | Method and system enabling natural user interface gestures with user wearable glasses |
US20140071061A1 (en) * | 2012-09-12 | 2014-03-13 | Chih-Ping Lin | Method for controlling execution of camera related functions by referring to gesture pattern and related computer-readable medium |
US10133342B2 (en) * | 2013-02-14 | 2018-11-20 | Qualcomm Incorporated | Human-body-gesture-based region and volume selection for HMD |
US10295826B2 (en) * | 2013-02-19 | 2019-05-21 | Mirama Service Inc. | Shape recognition device, shape recognition program, and shape recognition method |
JP6333801B2 (ja) * | 2013-02-19 | 2018-05-30 | ミラマ サービス インク | 表示制御装置、表示制御プログラム、および表示制御方法 |
US9906778B2 (en) * | 2013-02-19 | 2018-02-27 | Mirama Service Inc. | Calibration device, calibration program, and calibration method |
WO2014128750A1 (ja) * | 2013-02-19 | 2014-08-28 | 株式会社ブリリアントサービス | 入出力装置、入出力プログラム、および入出力方法 |
WO2014128747A1 (ja) * | 2013-02-19 | 2014-08-28 | 株式会社ブリリアントサービス | 入出力装置、入出力プログラム、および入出力方法 |
US20150169070A1 (en) * | 2013-12-17 | 2015-06-18 | Google Inc. | Visual Display of Interactive, Gesture-Controlled, Three-Dimensional (3D) Models for Head-Mountable Displays (HMDs) |
US9304674B1 (en) * | 2013-12-18 | 2016-04-05 | Amazon Technologies, Inc. | Depth-based display navigation |
-
2013
- 2013-02-19 US US14/768,479 patent/US10295826B2/en active Active
- 2013-02-19 WO PCT/JP2013/000909 patent/WO2014128749A1/ja active Application Filing
- 2013-02-19 JP JP2015501061A patent/JP6195893B2/ja active Active
- 2013-04-12 JP JP2015501077A patent/JP6095763B2/ja active Active
- 2013-04-12 US US14/768,241 patent/US9857589B2/en active Active
- 2013-04-12 WO PCT/JP2013/002524 patent/WO2014128773A1/ja active Application Filing
- 2013-06-24 JP JP2015501081A patent/JPWO2014128787A1/ja active Pending
- 2013-06-24 US US14/768,482 patent/US9651782B2/en active Active
- 2013-06-24 WO PCT/JP2013/003946 patent/WO2014128787A1/ja active Application Filing
- 2013-07-23 JP JP2015501083A patent/JP6074494B2/ja not_active Expired - Fee Related
- 2013-07-23 WO PCT/JP2013/004485 patent/WO2014128788A1/ja active Application Filing
- 2013-07-23 US US14/768,484 patent/US9778464B2/en active Active
- 2013-07-23 WO PCT/JP2013/004486 patent/WO2014128789A1/ja active Application Filing
- 2013-07-23 US US14/768,485 patent/US10095030B2/en active Active
- 2013-07-23 JP JP2015501082A patent/JP6195894B2/ja active Active
-
2017
- 2017-05-18 JP JP2017098814A patent/JP6393367B2/ja active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH086708A (ja) * | 1994-04-22 | 1996-01-12 | Canon Inc | 表示装置 |
JP2011215922A (ja) * | 2010-03-31 | 2011-10-27 | Namco Bandai Games Inc | プログラム、情報記憶媒体及び画像生成システム |
Non-Patent Citations (2)
Title |
---|
HIROSHI SASAKI: "Hand-Menu System : A Deviceless Virtual Input Interface for Wearable Computer", TRANSACTIONS OF THE VIRTUAL REALITY SOCIETY OF JAPAN, vol. 7, no. 3, 30 September 2002 (2002-09-30), pages 393 - 401 * |
KAI INOUE: "A Study on Finger Character Recognition using Kinect", IEICE TECHNICAL REPORT, vol. 112, no. 417, 18 January 2013 (2013-01-18), pages 45 - 50 * |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140139463A1 (en) * | 2012-11-21 | 2014-05-22 | Bokil SEO | Multimedia device for having touch sensor and method for controlling the same |
US10210629B2 (en) | 2014-02-14 | 2019-02-19 | Sony Interactive Entertainment Inc. | Information processor and information processing method |
WO2015122079A1 (ja) * | 2014-02-14 | 2015-08-20 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置および情報処理方法 |
JP2015153179A (ja) * | 2014-02-14 | 2015-08-24 | 株式会社ソニー・コンピュータエンタテインメント | 情報処理装置および情報処理方法 |
WO2016052061A1 (ja) * | 2014-09-30 | 2016-04-07 | コニカミノルタ株式会社 | ヘッドマウントディスプレイ |
JP2016186680A (ja) * | 2015-03-27 | 2016-10-27 | セイコーエプソン株式会社 | インタラクティブプロジェクターおよびインタラクティブプロジェクターの制御方法 |
WO2016190057A1 (ja) * | 2015-05-22 | 2016-12-01 | コニカミノルタ株式会社 | ウェアラブル電子機器およびウェアラブル電子機器のジェスチャー検知方法 |
JP2017111722A (ja) * | 2015-12-18 | 2017-06-22 | 株式会社ブリリアントサービス | ヘッドマウントディスプレイ、ヘッドマウントディスプレイの表示方法、およびヘッドマウントディスプレイのプログラム |
JP2018067875A (ja) * | 2016-10-21 | 2018-04-26 | 京セラドキュメントソリューションズ株式会社 | メガネ型端末及び画像形成システム |
DE102017210317A1 (de) * | 2017-06-20 | 2018-12-20 | Volkswagen Aktiengesellschaft | Verfahren und Vorrichtung zum Erfassen einer Nutzereingabe anhand einer Geste |
US11430267B2 (en) | 2017-06-20 | 2022-08-30 | Volkswagen Aktiengesellschaft | Method and device for detecting a user input on the basis of a gesture |
JPWO2021199730A1 (ja) * | 2020-03-31 | 2021-10-07 | ||
WO2021199730A1 (ja) * | 2020-03-31 | 2021-10-07 | パイオニア株式会社 | 情報処理装置、コンピュータプログラム、記録媒体、表示データ作成方法 |
Also Published As
Publication number | Publication date |
---|---|
US20160004907A1 (en) | 2016-01-07 |
JPWO2014128773A1 (ja) | 2017-02-02 |
JP2017199379A (ja) | 2017-11-02 |
WO2014128773A1 (ja) | 2014-08-28 |
JPWO2014128787A1 (ja) | 2017-02-02 |
JP6393367B2 (ja) | 2018-09-19 |
US20160004320A1 (en) | 2016-01-07 |
WO2014128749A1 (ja) | 2014-08-28 |
US9778464B2 (en) | 2017-10-03 |
US9651782B2 (en) | 2017-05-16 |
WO2014128787A1 (ja) | 2014-08-28 |
JP6074494B2 (ja) | 2017-02-01 |
JPWO2014128749A1 (ja) | 2017-02-02 |
US20150378158A1 (en) | 2015-12-31 |
JPWO2014128788A1 (ja) | 2017-02-02 |
US10095030B2 (en) | 2018-10-09 |
WO2014128788A1 (ja) | 2014-08-28 |
JP6095763B2 (ja) | 2017-03-15 |
JPWO2014128789A1 (ja) | 2017-02-02 |
JP6195893B2 (ja) | 2017-09-13 |
US9857589B2 (en) | 2018-01-02 |
US20160004908A1 (en) | 2016-01-07 |
US20150370321A1 (en) | 2015-12-24 |
JP6195894B2 (ja) | 2017-09-13 |
US10295826B2 (en) | 2019-05-21 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6074494B2 (ja) | 形状認識装置、形状認識プログラム、および形状認識方法 | |
JP6177872B2 (ja) | 入出力装置、入出力プログラム、および入出力方法 | |
JP6333801B2 (ja) | 表示制御装置、表示制御プログラム、および表示制御方法 | |
JP6250024B2 (ja) | キャリブレーション装置、キャリブレーションプログラム、およびキャリブレーション方法 | |
WO2014128751A1 (ja) | ヘッドマウントディスプレイ装置、ヘッドマウントディスプレイ用プログラム、およびヘッドマウントディスプレイ方法 | |
JP6250025B2 (ja) | 入出力装置、入出力プログラム、および入出力方法 | |
JP6446465B2 (ja) | 入出力装置、入出力プログラム、および入出力方法 | |
JP2017191546A (ja) | 医療用ヘッドマウントディスプレイ、医療用ヘッドマウントディスプレイのプログラムおよび医療用ヘッドマウントディスプレイの制御方法 | |
JP6479835B2 (ja) | 入出力装置、入出力プログラム、および入出力方法 | |
JP2017111537A (ja) | ヘッドマウントディスプレイおよびヘッドマウントディスプレイのプログラム | |
JP6479836B2 (ja) | 入出力装置、入出力プログラム、および入出力方法 | |
JP2017111724A (ja) | 配管用ヘッドマウントディスプレイ | |
JP2017111721A (ja) | クリーンルーム用ヘッドマウントディスプレイ、クリーンルーム用ヘッドマウントディスプレイの制御方法、およびクリーンルーム用ヘッドマウントディスプレイの制御プログラム |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13875413 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2015501083 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14768485 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13875413 Country of ref document: EP Kind code of ref document: A1 |