CN102999939B - Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device - Google Patents
Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device Download PDFInfo
- Publication number
- CN102999939B CN102999939B CN201210353512.7A CN201210353512A CN102999939B CN 102999939 B CN102999939 B CN 102999939B CN 201210353512 A CN201210353512 A CN 201210353512A CN 102999939 B CN102999939 B CN 102999939B
- Authority
- CN
- China
- Prior art keywords
- image
- coordinate
- camera
- point
- infrared
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 230000002708 enhancing effect Effects 0.000 claims description 31
- 238000000605 extraction Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 26
- 238000004364 calculation method Methods 0.000 claims description 22
- 230000002452 interceptive effect Effects 0.000 claims description 9
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 4
- 230000002093 peripheral effect Effects 0.000 claims description 2
- 238000004513 sizing Methods 0.000 claims 1
- 230000008569 process Effects 0.000 description 8
- 239000000284 extract Substances 0.000 description 6
- 238000003384 imaging method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005530 etching Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/04—Interpretation of pictures
- G01C11/06—Interpretation of pictures by comparison of two or more pictures of the same area
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/239—Image signal generators using stereoscopic image cameras using two 2D image sensors having a relative position equal to or related to the interocular distance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- 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
- H04N13/20—Image signal generators
- H04N13/204—Image signal generators using stereoscopic image cameras
- H04N13/254—Image signal generators using stereoscopic image cameras in combination with electromagnetic radiation sources for illuminating objects
-
- 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
- G06T2207/10012—Stereo images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N13/00—Stereoscopic video systems; Multi-view video systems; Details thereof
- H04N2013/0074—Stereoscopic image analysis
- H04N2013/0081—Depth or disparity estimation from stereoscopic image signals
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Electromagnetism (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
This application discloses a kind of real-time three-dimensional Object reconstruction system and method based on computer vision and the three-dimensional coordinate information acquisition device used and a kind of three-dimensional interactive device.Wherein, coordinate acquiring device comprises: image capture module, for being taken same object by the first camera of infrared binocular camera and second camera, obtains the first image and the second image respectively; Region selection module, for determining area-of-interest based on gradation of image feature in the first image; Edge point extraction module, for carrying out marginal point extraction to area-of-interest; Depth calculation module, in the second image, searches for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, obtains the three-dimensional coordinate of match point.The scheme that the application provides is applicable to closely automatic object reconstruction.
Description
Technical field
The application relates to technical field of computer vision, particularly relates to a kind of real-time three-dimensional Object reconstruction system and method based on computer vision and the three-dimensional coordinate information acquisition device used and a kind of three-dimensional interactive device.
Background technology
Along with the demand of people to intelligent man-machine interaction field is more and more higher, machine perception people how is made to become a problem demanding prompt solution.Research shows, if some rule can be set make these information of machine perception by three-dimensional (3D) information of the behavior of various sensing equipment extract real-time people, to be the key link addressed this problem, wherein 3D Object reconstruction be the basis realizing this key link.3D Object reconstruction refers in a limited 3D visual field, extracts the positional information of target in the X-direction of rectangular coordinate system in space, Y-direction and Z-direction, realizes 3D accordingly and rebuild.
Summary of the invention
According to the first aspect of the application, a kind of coordinate acquiring device for real-time three-dimensional Object reconstruction is provided, comprising: image capture module, for being taken same object by the first camera of infrared binocular camera and second camera, obtaining the first image and the second image respectively; Region selection module, for determining area-of-interest based on gradation of image feature in the first image; Edge point extraction module, for carrying out marginal point extraction to area-of-interest; Depth calculation module, in the second image, searches for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, obtains the three-dimensional coordinate of match point.
According to the second aspect of the application, a kind of real-time three-dimensional Object reconstruction system using above-mentioned coordinate acquiring device is provided, it also comprises object reconstruction module, for in the first calibration chart picture, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second calibration chart picture, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
According to the third aspect of the application, provide a kind of three-dimensional interactive device using above-mentioned coordinate acquiring device or automatic object reconstruction system.
According to the fourth aspect of the application, a kind of real-time three-dimensional Object reconstruction method is provided, comprise: image acquisition step, by the first camera of infrared binocular camera and second camera, same object is taken, obtain the first image and the second image respectively, described first image comprises the first infrared image and the first infrared enhancing image, and described second image is the second infrared enhancing image; Region selection step, for each pixel in the first infrared enhancing image and each pixel in the first infrared image corresponding with this pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest; Marginal point extraction step, carries out marginal point extraction to area-of-interest; Depth calculation step, in the second image, search for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of match point; Object reconstruction step, in the first image, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second image, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
The beneficial effect of the application is: by extracting marginal point from the first image, the match point of this marginal point is found out in the second image, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, thus obtaining the 3 d space coordinate of match point, this scheme is applicable to closely automatic object reconstruction.
In a kind of embodiment, can obtain that there is lightness stabilized image in conjunction with the auxiliary of infrared light supply, the accuracy of subsequent calculations is increased, simple gray feature is only adopted when region is chosen, accelerate processing speed, only calculate with the marginal point of the area-of-interest selected, reach and reduce calculated amount and the object improving again speed.Further, eliminate the unreliable point at zone boundary place by corrosion treatment, thus reach and put forward high-precision object.
Accompanying drawing explanation
Fig. 1 is the structural representation of the coordinate acquiring device of a kind of embodiment of the application;
Fig. 2 is the schematic flow sheet of the depth computing method of a kind of embodiment of the application;
Fig. 3 is the structural representation of the binocular camera of a kind of embodiment of the application;
Fig. 4 is the structural representation of the coordinate acquiring device of the another kind of embodiment of the application;
Fig. 5 is the calibration of a kind of embodiment of the application and the structural representation of regional choice process;
Fig. 6 is the structural representation of the coordinate acquiring device of the another kind of embodiment of the application;
Fig. 7 is the structural representation of the coordinate acquiring device of the another kind of embodiment of the application;
Fig. 8 is the one application schematic diagram of the coordinate acquiring device of a kind of embodiment of the application.
Embodiment
By reference to the accompanying drawings the present invention is described in further detail below by embodiment.
Embodiment 1
The data that can be photographed by any one camera due to the real-time coordinates of target in the X-direction and Y-direction of rectangular coordinate system in space are obtained, and the coordinate information of Z-direction cannot directly obtain, so the real-time coordinates how calculating Z-direction is one of key point realizing automatic object reconstruction.
A kind of coordinate acquiring device for real-time three-dimensional Object reconstruction of the application with reference to figure 1, can comprise: image capture module 101, region selection module 103, edge point extraction module 105 and depth calculation module 107.
Image capture module 101, for being taken same object by the first camera of binocular camera and second camera, obtains the first image and the second image respectively.Binocular camera can adopt conventional binocular camera.Region selection module 103 for determining area-of-interest based on gradation of image feature in the first image.Edge point extraction module 105 is for carrying out marginal point extraction to area-of-interest.Depth calculation module 107 for searching for the match point corresponding with the marginal point of the first image in the second image, according to the coordinate of marginal point and the coordinate of match point, in conjunction with the focal length of binocular camera and the distance of two camera central points, be inversely proportional to fathom according to stereoscopic parallax between image and calculate, obtain the three-dimensional coordinate of match point.
Here the method for depth calculation can adopt the method based on region to calculate, and can improve speed like this when ensureing precision.As shown in Figure 2, be object to be captured in the dotted line frame of the top, centre is binocular camera (containing camera 1 and camera 2), the left side figure of bottom is that camera 1 takes the image L obtained, the right figure is that camera 2 takes the image R obtained, wherein T is the central point distance of camera 1 and camera 2, and f is camera focal length, d
1and d
2be respectively the image offset distance in the X direction that two cameras photograph.In image L by extract marginal point centered by P
c, choose the number that m*m(m is pixel) scanning area of size, in scan image R with P
cthe region of the formed objects (i.e. m*m) centered by the pixel that position is identical, the absolute value of pixel grey scale value difference in the corresponding scanning area in image L and image R is sued for peace, the minimum center position of the value sued for peace is exactly the relative position of the match point of marginal point in image R in image L, can obtain d thus
2value, utilize following formula:
Can obtain this match point coordinate in z-direction, so far, object is all determined at the coordinate of X-direction, Y-direction and Z-direction.
A kind of real-time three-dimensional Object reconstruction system can be realized based on this coordinate acquiring device, namely this system comprises this coordinate acquiring device and object reconstruction module, wherein, object reconstruction is used in the first calibration chart picture, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second calibration chart picture, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.Wherein, the method for search matching interpolation point can adopt and calculate based on the method in region as the aforementioned, and interpolation method can adopt linear interpolation, namely for the non-edge point P in area-of-interest
a, nearest marginal point can be searched for by left and right both direction on a same row, be designated as aL and aR, pass through formula:
Wherein .x .y .z row, column of denotation coordination point, value of short transverse respectively, can obtain the interpolated depths value of this non-edge point according to this formulae discovery.
Because the interior zone obtained in most cases in shooting at close range meets smoothness condition, therefore such interpolation theory is more accurate, and smoothness condition refers to that area-of-interest total interior is an approximate two dimensional surface here, does not have complicated fold; Closely determine according to calculating mechanism, such as tens centimetres etc.
Present invention also provides a kind of three-dimensional interactive device, it comprises coordinate acquiring device or the real-time three-dimensional Object reconstruction system of the present embodiment.
The present embodiment by extracting marginal point from the first image, the match point of this marginal point is found out in the second image, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, thus obtaining the 3 d space coordinate of match point, this scheme is applicable to closely automatic object reconstruction.
Based on the coordinate acquiring device of the present embodiment, the application also provides a kind of real-time three-dimensional Object reconstruction method, comprises the steps:
Image acquisition step, is taken same object by the first camera of binocular camera and second camera, obtains the first image and the second image respectively;
Region selection step, determines area-of-interest based on gradation of image feature in the first image;
Marginal point extraction step, carries out marginal point extraction to area-of-interest;
Depth calculation step, in the second image, searches for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, obtains the three-dimensional coordinate of match point.
Object reconstruction step, in the first calibration chart picture, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second calibration chart picture, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
Each step of the method can adopt the corresponding part related in the real-time three-dimensional Object reconstruction system of the present embodiment to realize, and is not described further at this.
Embodiment 2
A kind of coordinate acquiring device for real-time three-dimensional Object reconstruction of the present embodiment with reference to figure 4, can comprise: image capture module 401, calibration module 402, region selection module 403, edge point extraction module 405 and depth calculation module 407.
Image capture module 401, for being taken same object by the first camera of binocular camera and second camera, obtains the first image and the second image respectively.The infrared binocular camera that binocular camera adopts the application to provide, as shown in Figure 3, the structure of this infrared binocular camera comprises two common camera (camera 1 and camera 2), infrared light supply, infrared fileter and corresponding control circuit.Diagram mid-infrared light source is infrared LED, certainly, also can be the infrared light supply of other types.The camera lens that infrared light supply is arranged on camera 1 and camera 2 is peripheral, and infrared light supply can be evenly distributed on this periphery to reach best shooting effect; Infrared fileter is between camera lens and the imageing sensor of camera; Control circuit is used for the shooting controlling each camera as required.The technology that annexation between each components and parts of infrared binocular camera and control mode can adopt this area conventional realizes, and is not described further at this.
The advantage that the infrared binocular camera that the present embodiment provides compares common double lens camera is: common double lens camera is when occurring that light is very bright or light is very dark, the brightness extremely unstable of image, imaging results can be partially bright, partially dark or occur local shades, this gray scale for follow-up main dependence image carry out graphical analysis and computing be unfavorable, because brightness of image changes, mean that subsequent analysis and operation result also may change, finally cause result inaccurate.And the infrared enhancing image adopting the binocular camera of the application to generate under infrared light supply open and close state and infrared image, the gray scale difference of infrared enhancing image and infrared image is utilized to capture area-of-interest, make when frequent variations appears in ambient light line strength, reduce the error capturing area-of-interest.
Image capture module 401, when infrared light supply is in closed condition, utilizes camera 1 to take image and obtains image I
1OFF, utilize camera 1 and camera 2 shooting to obtain image I respectively when infrared light supply is in opening
1ONand I
2ON, image I
1OFFfor infrared image, image I
1ONand I
2ONfor infrared enhancing image.
Calibration module 402 for the calibrating parameters based on binocular camera, to image I
1OFF, I
1ONand I
2ONcarry out calibrating and output to region selection module 403.Concrete calibration process can adopt existing calibration steps to realize, namely according to the monocular internal reference data (focal length, imaging initial point, distortion factor) obtained after camera calibration and binocular relative position relation (rotation matrix and translation vector), the image taken camera 1 and camera 2 respectively carries out eliminations distortion and row is aimed at, make to take the imaging origin of the image obtained unanimously, two camera optical axises are parallel, left and right imaging plane is coplanar, to polar curve row alignment.
Region selection module 403 for determining area-of-interest based on gradation of image feature in the first image.In the present embodiment, region selection module comprises calculating selection unit, for for calibration after image I
1OFFin each pixel and image I after the calibration corresponding with this pixel
1ONin each pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest.First predetermined threshold value and the second predetermined threshold value can be determined according to actual experiment data, are empirical value.Easy understanding, the ratio of gray-scale value or difference relevant with the environment residing for equipment (i.e. three-dimensional reconstruction system or three-dimensional interactive device), under the environment that light is brighter, this ratio can be very little of to prevent from collecting area-of-interest, under the environment of dark, this ratio can suitably improve to prevent from collecting the background area because of infrared light supply impact change.
The work for the treatment of flow process of the present embodiment alignment module and region selection module as shown in Figure 5, comprising:
Take step during closedown, infrared light supply is in closed condition, utilizes camera 1 to take image, and obtains image Ref after calibration;
Take step during unlatching, infrared light supply is in opening, utilizes camera 1 and 2 to take image, and obtain image L and image R after calibration;
Gray count step, by image L and image Ref pointwise traversal, the ratio of the gray-scale value of each pixel corresponding in computed image L and image Ref or difference, extract more than the first predetermined threshold value or difference ratio, thus obtain area-of-interest more than the pixel of the second predetermined threshold value.
Edge point extraction module 405 is for carrying out marginal point extraction to area-of-interest.Marginal point extracts and can adopt some extraction algorithm conventional in image procossing.A kind of simple marginal point extracting method judges to obtain by pointwise, namely judge whether the point in area-of-interest is marginal point just point centered by this point, Kan Gai center neighborhood of a point (such as 3*3 neighborhood, i.e. around 8 points) in whether there is certain point not in area-of-interest, if had, then this central point is marginal point.Why extract marginal point, be because these points represent operating point in three-dimensional interactive device usually, so just in order to avoid calculate all pixels of whole area-of-interest, thus calculated amount can be reduced.
Depth calculation module 407 adopts the depth calculation module as embodiment 1, does not repeat at this.
The algorithm of the regional choice employing of the present embodiment, only based on the gray-scale value of image, can make processing speed accelerate.In addition, selecting, infrared light supply can be made to glimmer with certain frequency for realizing real-time region, namely a flicker process cycle is less than the human eye distinguishable minimum delay.
Similarly, based on the coordinate acquiring device of the present embodiment, also can provide a kind of real-time three-dimensional Object reconstruction system, it comprises this coordinate acquiring device and object reconstruction module, and wherein, the process of object reconstruction can reference example 1, does not repeat at this.Present invention also provides a kind of three-dimensional interactive device, it comprises coordinate acquiring device or the real-time three-dimensional Object reconstruction system of the present embodiment.
Based on the coordinate acquiring device of the present embodiment, present invention also provides a kind of real-time three-dimensional Object reconstruction method, comprising:
Image acquisition step, by the first camera of infrared binocular camera and second camera, same object is taken, obtain the first image and the second image respectively, described first image comprises the first infrared image and the first infrared enhancing image, and described second image is the second infrared enhancing image;
Calibration steps, based on the calibrating parameters of binocular camera, calibrates the first infrared image, the first infrared enhancing image and the second infrared enhancing image and exports for subsequent step.
Region selection step, for each pixel in the first infrared enhancing image and each pixel in the first infrared image corresponding with this pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest;
Marginal point extraction step, carries out marginal point extraction to area-of-interest;
Depth calculation step, in the second infrared enhancing image, search for the match point corresponding with the marginal point of the first infrared enhancing image, according to the coordinate of marginal point and the coordinate of match point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of match point;
Object reconstruction step, in the first infrared enhancing image, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second infrared enhancing image, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
Each step of the method can adopt the corresponding part related in the coordinate acquiring device of the present embodiment to realize, and is not described further at this.
Embodiment 3
A kind of coordinate acquiring device for real-time three-dimensional Object reconstruction of the present embodiment with reference to figure 6, can comprise: image capture module 501, region selection module 503, calibration module 504, edge point extraction module 505 and depth calculation module 507.Image capture module 401 adopts the image capture module as embodiment 2, does not repeat at this.The region selection module of region selection module 503 similar embodiment 2, difference is, now directly process based on taking the image obtained, this image is not yet through calibration, calibrated by calibration module 504 again after process, the realization of region selection module 503, calibration module 504, edge point extraction module 505 and depth calculation module 507 can be corresponding in reference example 2 module, do not repeat at this.
Similarly, based on the coordinate acquiring device of the present embodiment, also can provide a kind of real-time three-dimensional Object reconstruction system, it comprises this coordinate acquiring device and object reconstruction module, and wherein, the process of object reconstruction can reference example 1, does not repeat at this.Present invention also provides a kind of three-dimensional interactive device, it comprises coordinate acquiring device or the real-time three-dimensional Object reconstruction system of the present embodiment.
Based on the coordinate acquiring device of the present embodiment, present invention also provides a kind of real-time three-dimensional Object reconstruction method, comprising: image acquisition step, region selection step, calibration steps, marginal point extraction step, depth calculation step and object reconstruction step.
Each step of the method can adopt the corresponding part related in the real-time three-dimensional Object reconstruction system of the present embodiment to realize, and is not described further at this.
Embodiment 4
A kind of coordinate acquiring device for real-time three-dimensional Object reconstruction of the present embodiment as shown in Figure 7, comprise: image capture module 601, calibration module 602, region selection module 603, Null Spot removes module 604, edge point extraction module 605 and depth calculation module 607, wherein, image capture module 601, calibration module 602, region selection module 603, edge point extraction module 605 and depth calculation module 607 can adopt the respective modules of embodiment 3 or embodiment 4 to realize, that is, the calibration module of the present embodiment and the sequence of positions of region selection module can be first calibrate rear region as shown in Figure 7 to select, also can be calibrating mode after the first regional choice as embodiment 3.Null Spot removes module 604 for carrying out Morphological scale-space to area-of-interest before extraction marginal point.Adopt etching operation in the present embodiment, object eliminates the unreliable point at region of interest border place.The number of times of etching operation and the thickness of object and the distance dependent with binocular camera, more heavy thickness is less for distance usually, then corrode number of times less.
Be illustrated in figure 8 the schematic diagram of a kind of example adopting the present embodiment, upper left figure takes the image Ref obtained when being infrared light supply closedown, the figure of lower left is the image L of infrared light supply opening shooting, " hand " area-of-interest for determining in intermediate image, the rightest figure is Corrosion results figure.
It will be appreciated by those skilled in the art that, in above-mentioned embodiment, all or part of step of various method can be carried out instruction related hardware by program and completes, this program can be stored in a computer-readable recording medium, and storage medium can comprise: ROM (read-only memory), random access memory, disk or CD etc.
The application is under closely application conditions, assisting in conjunction with infrared LED, accurate extraction effective coverage, remove Null Spot, and compute depth information, thus reach the object realizing real-time 3D Object reconstruction, referring in real time can the 3D information of Dynamic Extraction target, and is less than the minimum delay time of eye recognition dynamic object its time delay; Also can utilize these 3D information in conjunction with the working rule set under practical application scene to realize 3D body sense manipulation simultaneously.
Above content is in conjunction with concrete embodiment further description made for the present invention, can not assert that specific embodiment of the invention is confined to these explanations.For general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, some simple deduction or replace can also be made.
Claims (9)
1. for a coordinate acquiring device for real-time three-dimensional Object reconstruction, it is characterized in that, comprising:
Image capture module, takes object for the first camera by infrared binocular camera, obtains the first image, is taken, obtain the second image by the second camera of described infrared binocular camera to described object;
Region selection module, for determining area-of-interest based on gradation of image feature in the first image;
Edge point extraction module, for carrying out marginal point extraction to area-of-interest;
Depth calculation module, for in the second image, search for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of match point;
Wherein said image capture module comprises the binocular camera of tool first camera and second camera, infrared light supply, infrared fileter and control circuit; The camera lens that described infrared light supply is arranged on described first camera and second camera is peripheral; Described infrared fileter is between camera lens and the imageing sensor of camera; Described control circuit takes to obtain the first infrared image for controlling the first camera when infrared light supply is closed condition, control the first camera and second camera takes to obtain the first infrared enhancing image and the second infrared enhancing image when infrared light supply is opening, it is described first image that described first infrared image and described first strengthens image, and described second infrared enhancing image is described second image.
2. coordinate acquiring device as claimed in claim 1, is characterized in that,
Described region selection module comprises: calculate selection unit, for for each pixel in the first infrared enhancing image and each pixel in the first infrared image corresponding with this pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest;
Described coordinate acquiring device also comprises: calibration module, for the calibrating parameters based on binocular camera, the second infrared enhancing image obtain described image capture module and the first infrared enhancing image of area-of-interest of being selected by described calculating selection unit are calibrated and export;
The second image in described depth calculation module is the second infrared enhancing image after calibration.
3. coordinate acquiring device as claimed in claim 1, is characterized in that,
Described coordinate acquiring device also comprises: calibration module, for the calibrating parameters based on binocular camera, calibrates the first infrared image, the first infrared enhancing image and the second infrared enhancing image and exports;
The second image in described depth calculation module is the second infrared enhancing image after calibration;
Described region selection module comprises: calculate selection unit, for for each pixel in each pixel in the first infrared enhancing image after the calibration of described calibration module and the first infrared image after the calibration corresponding with this pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest.
4. the coordinate acquiring device as described in any one of claim 1-3, is characterized in that, also comprises: Null Spot removes module, for before extraction marginal point, carries out corrosion treatment to area-of-interest.
5. coordinate acquiring device as claimed in claim 1, it is characterized in that, described depth calculation module comprises:
Search unit, for putting the scanning area of selected predetermined size in the first image centered by each marginal point extracted, the scanning area identical with pre-sizing is chosen with the pixel that the coordinate position of the central point with each marginal point is corresponding in the second image, calculate the absolute value sum of the difference of the gray-scale value of each corresponding pixel in these two scanning areas, namely the central point corresponding with sued for peace minimum value be match point corresponding with the marginal point of the first image in the second image;
Coordinate calculating unit, according to the coordinate of marginal point and the coordinate of match point, in conjunction with the focal length of binocular camera and the distance of two camera central points, is inversely proportional to fathom according to stereoscopic parallax between image and calculates, obtain the three-dimensional coordinate of match point.
6. a real-time three-dimensional Object reconstruction system, it is characterized in that, comprise the coordinate acquiring device as any one of claim 1-5, also comprise: object reconstruction module, for in the first calibration chart picture, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second calibration chart picture, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
7. a three-dimensional interactive device, is characterized in that, comprises the coordinate acquiring device as described in any one of claim 1-5 or real-time three-dimensional Object reconstruction system as claimed in claim 6.
8. a real-time three-dimensional Object reconstruction method, is characterized in that, comprising:
Image acquisition step, by the first camera of infrared binocular camera and second camera, same object is taken, obtain the first image and the second image respectively, described first image comprises the first infrared image and the first infrared enhancing image, and described second image is the second infrared enhancing image;
Region selection step, for each pixel in the first infrared enhancing image and each pixel in the first infrared image corresponding with this pixel, the ratio of the gray-scale value of both calculating or the difference of gray-scale value, ratio is greater than the pixel that the first predetermined threshold value or difference be greater than the second predetermined threshold value and forms area-of-interest;
Marginal point extraction step, carries out marginal point extraction to area-of-interest;
Depth calculation step, in the second image, search for the match point corresponding with the marginal point of the first image, according to the coordinate of marginal point and the coordinate of match point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of match point;
Object reconstruction step, in the first image, carry out interpolation according to marginal point and obtain interpolation point, the matching interpolation point that search and interpolation point is corresponding in the second image, according to the coordinate of interpolation point and the coordinate of matching interpolation point, calculate in conjunction with the focal length of binocular camera and the distance of two camera central points, obtain the three-dimensional coordinate of matching interpolation point, according to the three-dimensional reconstruction of the three-dimensional coordinate realize target thing of matching interpolation point.
9. real-time three-dimensional Object reconstruction method as claimed in claim 8, is characterized in that, also comprise:
Null Spot removal step, carried out corrosion treatment to area-of-interest before extraction marginal point;
Calibration steps, before or after being executed in region selection step, based on the calibrating parameters of binocular camera, calibrates the first infrared image, the first infrared enhancing image and the second infrared enhancing image and exports.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210353512.7A CN102999939B (en) | 2012-09-21 | 2012-09-21 | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device |
| PCT/CN2013/083092 WO2014044126A1 (en) | 2012-09-21 | 2013-09-09 | Coordinate acquisition device, system and method for real-time 3d reconstruction, and stereoscopic interactive device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210353512.7A CN102999939B (en) | 2012-09-21 | 2012-09-21 | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102999939A CN102999939A (en) | 2013-03-27 |
| CN102999939B true CN102999939B (en) | 2016-02-17 |
Family
ID=47928467
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210353512.7A Expired - Fee Related CN102999939B (en) | 2012-09-21 | 2012-09-21 | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102999939B (en) |
| WO (1) | WO2014044126A1 (en) |
Families Citing this family (76)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102999939B (en) * | 2012-09-21 | 2016-02-17 | 魏益群 | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device |
| CN103236083B (en) * | 2013-05-06 | 2016-06-22 | 北京建筑工程学院 | Real-time three-dimensional measuring method based on stereo image library |
| CN104424630A (en) * | 2013-08-20 | 2015-03-18 | 华为技术有限公司 | Three-dimension reconstruction method and device, and mobile terminal |
| CN104714840B (en) * | 2013-12-13 | 2019-01-15 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN108924428A (en) | 2014-09-30 | 2018-11-30 | 华为技术有限公司 | A kind of Atomatic focusing method, device and electronic equipment |
| CN105528599B (en) * | 2014-09-30 | 2019-07-26 | 联想(北京)有限公司 | Handle the method and terminal device of image |
| CN105528060B (en) * | 2014-09-30 | 2018-11-09 | 联想(北京)有限公司 | terminal device and control method |
| CN105491307B (en) * | 2014-10-13 | 2019-06-25 | 联想(北京)有限公司 | Depth sensing system |
| CN104709696B (en) * | 2014-12-31 | 2018-03-16 | 深圳市中智科创机器人有限公司 | The method, apparatus and system of pallet stacking car placement/discharging of goods |
| US10430982B2 (en) * | 2015-03-20 | 2019-10-01 | Intel Corporation | Sensor data visualization apparatus and method |
| CN106293012A (en) * | 2015-05-28 | 2017-01-04 | 深圳柔石科技有限公司 | A kind of three-dimensional body-sensing bi-direction interactive system and method |
| CN105082860A (en) * | 2015-07-10 | 2015-11-25 | 青岛亿辰电子科技有限公司 | Rapid manufacturing method for 3D mini-portrait |
| CN105277169B (en) * | 2015-09-25 | 2017-12-22 | 安霸半导体技术（上海）有限公司 | Binocular distance-finding method based on image segmentation |
| CN105430501B (en) * | 2015-12-03 | 2019-06-04 | 青岛海信电器股份有限公司 | A kind of volume adjusting method and system |
| CN105592367A (en) * | 2015-12-23 | 2016-05-18 | 青岛海信电器股份有限公司 | Image display parameter adjusting method and system |
| CN105872516A (en) * | 2015-12-28 | 2016-08-17 | 乐视致新电子科技（天津）有限公司 | Method and device for obtaining parallax parameters of three-dimensional film source |
| CN105704472A (en) * | 2016-01-13 | 2016-06-22 | 青岛海信电器股份有限公司 | Television control method capable of identifying child user and system thereof |
| CN105681861A (en) * | 2016-03-04 | 2016-06-15 | 青岛海信电器股份有限公司 | Adjusting method and system for display subtitle of terminal |
| CN105946718B (en) * | 2016-06-08 | 2019-04-05 | 深圳芯智汇科技有限公司 | The method of car-mounted terminal and its switching display reverse image |
| CN106170086B (en) * | 2016-08-19 | 2019-03-15 | 深圳奥比中光科技有限公司 | Method and device thereof, the system of drawing three-dimensional image |
| CN106384382A (en) * | 2016-09-05 | 2017-02-08 | 山东省科学院海洋仪器仪表研究所 | Three-dimensional reconstruction system and method based on binocular stereoscopic vision |
| CN106530389B (en) * | 2016-09-23 | 2019-04-05 | 西安电子科技大学 | Stereo reconstruction method based on medium-wave infrared facial image |
| CN106650542A (en) * | 2016-12-29 | 2017-05-10 | 浙江理工大学 | Multifunctional hand-held object scanner |
| CN107041729A (en) * | 2016-12-30 | 2017-08-15 | 西安中科微光影像技术有限公司 | Binocular near infrared imaging system and blood vessel recognition methods |
| CN106931906A (en) * | 2017-03-03 | 2017-07-07 | 浙江理工大学 | A Simple Method for Measuring 3D Dimensions of Objects Based on Binocular Stereo Vision |
| CN106773509B (en) * | 2017-03-28 | 2019-07-09 | 成都通甲优博科技有限责任公司 | A kind of photometric stereo three-dimensional rebuilding method and beam splitting type photometric stereo camera |
| CN108269279B (en) * | 2017-07-17 | 2019-11-08 | 先临三维科技股份有限公司 | Three-dimensional reconstruction method and device based on monocular 3 D scanning system |
| CN107424149A (en) * | 2017-07-20 | 2017-12-01 | 晓视自动化科技（上海）有限公司 | The module measurement method of planeness and equipment of view-based access control model technology |
| CN107657245A (en) * | 2017-10-16 | 2018-02-02 | 维沃移动通信有限公司 | A kind of face identification method and terminal device |
| CN107527367A (en) * | 2017-10-19 | 2017-12-29 | 新疆秦域工业设备制造安装有限公司 | A kind of cotton identification and localization method based on binocular camera |
| CN108480239B (en) * | 2018-02-10 | 2019-10-18 | 浙江工业大学 | Method and device for fast sorting of workpieces based on stereo vision |
| CN110231832B (en) * | 2018-03-05 | 2022-09-06 | 北京京东乾石科技有限公司 | Obstacle avoidance method and obstacle avoidance device for unmanned aerial vehicle |
| CN110555874B (en) * | 2018-05-31 | 2023-03-10 | 华为技术有限公司 | Image processing method and device |
| CN110858902A (en) * | 2018-08-22 | 2020-03-03 | 晨星半导体股份有限公司 | Synchronization method of decoded tile and display position based on input geographic location and related video decoding device |
| CN109598738A (en) * | 2018-11-12 | 2019-04-09 | 长安大学 | A kind of line-structured light center line extraction method |
| CN109538208A (en) * | 2018-12-21 | 2019-03-29 | 冀中能源峰峰集团有限公司 | A kind of compound positioning system of cutting head of roadheader and method |
| CN111383274B (en) * | 2018-12-27 | 2024-03-22 | 浙江舜宇智能光学技术有限公司 | Calibration method of camera module and target for camera module calibration |
| CN111429194B (en) * | 2019-01-09 | 2023-04-07 | 阿里巴巴集团控股有限公司 | User track determination system, method, device and server |
| CN109949358A (en) * | 2019-03-29 | 2019-06-28 | 三一海洋重工有限公司 | A kind of detection method and detection device of container truck lifting state |
| CN111932565B (en) * | 2019-05-13 | 2023-09-19 | 中国科学院沈阳自动化研究所 | Multi-target recognition tracking calculation method |
| CN111986246B (en) * | 2019-05-24 | 2024-04-30 | 北京四维图新科技股份有限公司 | Three-dimensional model reconstruction method, device and storage medium based on image processing |
| CN110533708A (en) * | 2019-08-28 | 2019-12-03 | 维沃移动通信有限公司 | A kind of electronic equipment and depth information acquisition method |
| CN111027405B (en) * | 2019-11-15 | 2023-09-01 | 浙江大华技术股份有限公司 | Method and device for estimating space occupancy of article, terminal and storage device |
| CN110866949A (en) * | 2019-11-15 | 2020-03-06 | 广东利元亨智能装备股份有限公司 | Center point positioning method, device, electronic device and storage medium |
| CN110824278A (en) * | 2019-11-15 | 2020-02-21 | 中国工程物理研究院计算机应用研究所 | Stereo map construction equipment for on-line analysis of electronic equipment performance and application method |
| CN112907643A (en) * | 2019-12-04 | 2021-06-04 | 上海图漾信息科技有限公司 | Target detection method and device |
| CN110956640B (en) * | 2019-12-04 | 2023-05-05 | 国网上海市电力公司 | A Method of Edge Point Detection and Registration in Heterogeneous Images |
| CN111277811B (en) * | 2020-01-22 | 2021-11-09 | 上海爱德赞医疗科技有限公司 | Three-dimensional space camera and photographing method thereof |
| CN112771575A (en) * | 2020-03-30 | 2021-05-07 | 深圳市大疆创新科技有限公司 | Distance determination method, movable platform and computer readable storage medium |
| CN111508068B (en) * | 2020-04-20 | 2023-05-30 | 华中科技大学 | Three-dimensional reconstruction method and system applied to binocular endoscopic image |
| CN113643225B (en) * | 2020-04-26 | 2025-02-14 | 北京配天技术有限公司 | A circular arc detection method and circular arc detection device |
| CN111882077B (en) * | 2020-06-24 | 2022-06-10 | 国网宁夏电力有限公司检修公司 | A method and system for establishing an arming space for a substation |
| CN112101379B (en) * | 2020-08-24 | 2024-06-11 | 北京配天技术有限公司 | Shape matching method, computer equipment and storage device |
| CN112330747B (en) * | 2020-09-25 | 2022-11-11 | 中国人民解放军军事科学院国防科技创新研究院 | Multi-sensor combined detection and display method based on unmanned aerial vehicle platform |
| CN112308886B (en) * | 2020-09-27 | 2025-03-25 | 合肥疆程技术有限公司 | A method, device and system for determining HUD image size |
| CN112634376B (en) * | 2020-12-25 | 2024-06-04 | 深圳中科飞测科技股份有限公司 | Calibration method and device, calibration equipment and storage medium |
| CN113158765B (en) * | 2021-02-23 | 2024-11-19 | 合肥英睿系统技术有限公司 | Method, device and electronic equipment for identifying target objects in infrared images |
| CN113063361A (en) * | 2021-03-29 | 2021-07-02 | 长安大学 | Symmetrical rail contact net detection device and detection method |
| CN113284188B (en) * | 2021-05-10 | 2024-02-02 | 西安理工大学 | Thermal infrared target reporting system and calibration method thereof |
| CN113237896B (en) * | 2021-06-08 | 2024-02-20 | 诚丰家具有限公司 | Furniture board dynamic monitoring system and method based on light source scanning |
| CN113343917B (en) * | 2021-06-30 | 2024-05-31 | 上海申瑞继保电气有限公司 | Substation equipment identification method based on histogram |
| CN113567451A (en) * | 2021-07-23 | 2021-10-29 | 江苏电力信息技术有限公司 | Cable defect detection and diameter measurement method |
| CN113610881B (en) * | 2021-08-25 | 2024-03-01 | 浙江华感科技有限公司 | Target object determination method and device, storage medium and electronic device |
| CN113807201A (en) * | 2021-08-26 | 2021-12-17 | 深圳证券通信有限公司 | Intelligent machine room equipment abnormal state inspection method based on computer vision |
| CN114332349B (en) * | 2021-11-17 | 2023-11-03 | 浙江视觉智能创新中心有限公司 | Binocular structured light edge reconstruction method, system and storage medium |
| CN114419148B (en) * | 2021-12-08 | 2024-12-17 | 科大讯飞股份有限公司 | Touch detection method, device, equipment and computer readable storage medium |
| CN114205575B (en) * | 2021-12-23 | 2025-04-01 | 桑瑞思医疗科技有限公司 | Method, device, equipment and storage medium for three-dimensional reconstruction of surgical video |
| CN114708422B (en) * | 2022-02-14 | 2024-06-28 | 清华大学 | A method and device for calculating cabin door coordinates based on binocular images |
| CN115556657B (en) * | 2022-09-29 | 2023-11-03 | 广东精益专用汽车有限公司 | Intelligent refrigerator car and refrigerator car monitoring system |
| CN116665034B (en) * | 2022-11-11 | 2023-10-31 | 中国消防救援学院 | Three-dimensional matching and flame space positioning method based on edge characteristics |
| CN116129037B (en) * | 2022-12-13 | 2023-10-31 | 珠海视熙科技有限公司 | Visual touch sensor, three-dimensional reconstruction method, system, equipment and storage medium thereof |
| CN116090094B (en) * | 2022-12-27 | 2024-06-04 | 武汉理工大学 | Hull thermal model building method, device and equipment based on infrared thermal imaging |
| CN115861603B (en) * | 2022-12-29 | 2023-09-26 | 宁波星巡智能科技有限公司 | Method, device, equipment and medium for locking region of interest in infant care scene |
| CN116778183B (en) * | 2023-07-07 | 2024-02-02 | 广州工程技术职业学院 | Glass gauge graduation line identification method, device and equipment |
| CN117726750A (en) * | 2023-11-24 | 2024-03-19 | 山西辰涵数字科技股份有限公司 | Museum cultural relics intelligent display method and system based on artificial intelligence |
| CN118781569B (en) * | 2024-09-10 | 2024-12-24 | 先导原创(上海)新技术研究有限公司 | Preview aiming method, binocular camera, preview aiming system, automobile, controller and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1484628A1 (en) * | 2003-06-07 | 2004-12-08 | Zeiss Optronik GmbH | System and method for generating three-dimensional images |
| CN1946195A (en) * | 2006-10-26 | 2007-04-11 | 上海交通大学 | Scene depth restoring and three dimension re-setting method for stereo visual system |
| CN101924953A (en) * | 2010-09-03 | 2010-12-22 | 南京农业大学 | An easy matching method based on fiducial points |
| KR101012691B1 (en) * | 2010-07-05 | 2011-02-09 | 주훈 | 3D stereo camera system |
| CN102074005A (en) * | 2010-12-30 | 2011-05-25 | 杭州电子科技大学 | Interest-region-oriented stereo matching method |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120098971A1 (en) * | 2010-10-22 | 2012-04-26 | Flir Systems, Inc. | Infrared binocular system with dual diopter adjustment |
| CN102999939B (en) * | 2012-09-21 | 2016-02-17 | 魏益群 | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device |
-
2012
- 2012-09-21 CN CN201210353512.7A patent/CN102999939B/en not_active Expired - Fee Related
-
2013
- 2013-09-09 WO PCT/CN2013/083092 patent/WO2014044126A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1484628A1 (en) * | 2003-06-07 | 2004-12-08 | Zeiss Optronik GmbH | System and method for generating three-dimensional images |
| CN1946195A (en) * | 2006-10-26 | 2007-04-11 | 上海交通大学 | Scene depth restoring and three dimension re-setting method for stereo visual system |
| KR101012691B1 (en) * | 2010-07-05 | 2011-02-09 | 주훈 | 3D stereo camera system |
| CN101924953A (en) * | 2010-09-03 | 2010-12-22 | 南京农业大学 | An easy matching method based on fiducial points |
| CN102074005A (en) * | 2010-12-30 | 2011-05-25 | 杭州电子科技大学 | Interest-region-oriented stereo matching method |
Non-Patent Citations (1)
| Title |
|---|
| 基于双目立体视觉的立体匹配算法研究;刘小群;《中国优秀硕士学位论文全文数据库》;20120115;第9-10页，第20-22页，第40-47页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2014044126A1 (en) | 2014-03-27 |
| CN102999939A (en) | 2013-03-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102999939B (en) | Coordinate acquiring device, real-time three-dimensional reconstructing system and method, three-dimensional interactive device | |
| CN103868460B (en) | Binocular stereo vision method for automatic measurement based on parallax optimized algorithm | |
| CN109997170B (en) | Apparatus and method for obtaining distance information from a view | |
| US20190164257A1 (en) | Image processing method, apparatus and device | |
| CN107635129B (en) | Three-dimensional trinocular camera device and depth fusion method | |
| CN101527046B (en) | Motion detection method, device and system | |
| CN107729893B (en) | Visual positioning method and system of die spotting machine and storage medium | |
| EP2194725B1 (en) | Method and apparatus for correcting a depth image | |
| CN110264416A (en) | Sparse point cloud segmentation method and device | |
| CN101516040B (en) | Video matching method, device and system | |
| Correal et al. | Automatic expert system for 3D terrain reconstruction based on stereo vision and histogram matching | |
| CN103679707A (en) | Binocular camera disparity map based road obstacle detection system and method | |
| CN111027415B (en) | Vehicle detection method based on polarization image | |
| CN109064505A (en) | A kind of depth estimation method extracted based on sliding window tensor | |
| CN114463303B (en) | Road target detection method based on fusion of binocular camera and laser radar | |
| CN109559353A (en) | Camera module scaling method, device, electronic equipment and computer readable storage medium | |
| CN112364793A (en) | Target detection and fusion method based on long-focus and short-focus multi-camera vehicle environment | |
| CN111951339A (en) | Image processing method for performing parallax calculation by using heterogeneous binocular cameras | |
| CN113723432B (en) | Intelligent identification and positioning tracking method and system based on deep learning | |
| US11699303B2 (en) | System and method of acquiring coordinates of pupil center point | |
| CN113345035B (en) | A method, system and computer-readable storage medium for instant slope prediction based on binocular camera | |
| CN117670969A (en) | Depth estimation method, device, terminal equipment and storage medium | |
| CN117058183A (en) | Image processing method and device based on double cameras, electronic equipment and storage medium | |
| CN110766740B (en) | Real-time high-precision binocular range finding system and method based on pedestrian tracking | |
| CN117422750B (en) | A method, device, electronic device and storage medium for real-time scene distance perception |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160217 Termination date: 20160921 |