CN207807796U - Robotic vision system - Google Patents

Abstract

The utility model provides a kind of robotic vision system, depth camera including interconnection and thermal infrared imager, the depth camera is used to obtain the depth information of object in the robot, the thermal infrared imager is used to detect the Infrared Thermogram of object in the environment, and form and the position of the object are judged in conjunction with the depth information of the object.The utility model utilizes the principle of infrared radiation of object itself, the infrared ray radiated by thermal infrared imager detection object, to detect the object；Information exchange is carried out between thermal infrared imager and depth camera simultaneously, the depth information of the object is acquired by depth camera, to judge quickly and accurately form and the position of the object.In the case that even if robot is under dark surrounds or environmental objects are in hidden, the utility model still can assist in robot and realize accurate positionin and avoidance.

Description

Robotic vision system

Technical field

The utility model is related to robotic technology fields, and in particular to a kind of robotic vision system.

Background technology

With growing, the robot technology also increasingly intelligence of robot technology.Such as most of family's machine Device people has been equipped with through functions such as visual perception ambient condition informations, i.e., obtains object in ambient enviroment by depth camera The depth information of body, then acquired object depth information is analyzed by the control device of robot interior, to realize Object positions and barrier avoiding function.

But it is such as hidden in practical applications, since object is not to be fully exposed in the visual field of the depth camera The object of position, the depth camera can not then detect the object, to be difficult to the object carry out accurately identification and Positioning.

Utility model content

The main purpose of the utility model is to provide a kind of robotic vision systems, it is intended to solve existing robot by The problem of visual field limitation is difficult to detect the object of concealed location.

In order to solve the above technical problems, the utility model provides a kind of robotic vision system, the robot vision system System includes the depth camera and thermal infrared imager being connected with each other, and the depth camera is for obtaining in the robot The depth information of object, the thermal infrared imager are used to detect the Infrared Thermogram of object in the environment, and in conjunction with the object The depth information of body judges form and the position of the object.

Preferably, the robotic vision system further includes for acquiring the depth camera and the thermal infrared imager position The IMU modules of appearance information.

Preferably, the IMU modules include gyroscope and accelerometer, and the gyroscope is for acquiring the depth camera With the rotational angle and angular velocity information of the thermal infrared imager, the accelerometer for acquire the depth camera with it is described The acceleration information of thermal infrared imager.

Preferably, the depth camera includes two cameras and the optical filter set on the camera front end, Yi Jiyong In the infrared-emitting diode of transmitting infrared ray, the optical filter is for filtering visible light, and the camera is for receiving object The infrared imaging reflected.

Preferably, the depth camera includes structured light projector and structure light depth inductor, the project structured light Device is used to project encoded light source to object, and the structure light depth inductor is used to receive the structure light figure of the object reflection Picture.

Preferably, the depth camera also includes RGB cameras, the two dimensional image for shooting the object.

Preferably, the structured light projector is infrared projector, and the structure light depth inductor is infrared inductor.

Preferably, the robotic vision system further include setting connect with the IMU modules and close to temperature sense Meter, the temperature sense meter is for acquiring environment temperature and carrying out temperature-compensating to the IMU modules.

The utility model also provides a kind of robot, and the robot includes the depth camera and infrared thermal imagery being connected with each other Instrument, the depth camera are used to obtain the depth information of object in the robot, and the thermal infrared imager is used for The Infrared Thermogram of object in the environment is detected, and judges form and the position of the object in conjunction with the depth information of the object It sets.

The utility model utilizes the principle of infrared radiation of object itself, is radiated by thermal infrared imager detection object infrared Line, to detect the object；Meanwhile information exchange is carried out between thermal infrared imager and depth camera, it is acquired by depth camera The depth information of the object, to judge quickly and accurately form and the position of the object.Even if robot is in black Under dark situation or in the case that environmental objects are in hidden, the utility model still can assist in robot and realize accurate positionin And avoidance.

Description of the drawings

Fig. 1 is the structural schematic diagram of one embodiment of the utility model robotic vision system；

Fig. 2 is the structural schematic diagram of the another embodiment of the utility model robotic vision system；

Fig. 3 is the position view of the utility model robotic vision system.

Drawing reference numeral explanation：

Specific implementation mode

The embodiments of the present invention are described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning Same or similar element or element with the same or similar functions are indicated to same or similar label eventually.Below by ginseng The embodiment for examining attached drawing description is exemplary, it is intended to for explaining the utility model, and should not be understood as to the utility model Limitation, be based on the embodiments of the present invention, those of ordinary skill in the art are without making creative work The every other embodiment obtained, shall fall within the protection scope of the present invention.

The utility model proposes a kind of robotic vision systems, and as shown in Figure 1 and Figure 2, the robotic vision system includes The depth camera 1 and thermal infrared imager 2 of interconnection, the depth camera 1 is for obtaining object in the robot The depth information of body, the thermal infrared imager 2 are used to detect the Infrared Thermogram of object in the environment, and in conjunction with the object Depth information judge form and the position of the object.

In the utility model embodiment, as shown in figure 3, the depth camera 1 is respectively positioned on the machine with thermal infrared imager 2 Head part, preferably " face " are equivalent to " eyes " of the robot.Wherein, thermal infrared imager 2 be using infrared detector and Optical imagery object lens receive in the infrared energy distribution pattern reflection to the light-sensitive element of infrared detector of measured target, from And Infrared Thermogram is obtained, this thermography is corresponding with the heat distribution field of body surface.That is, the thermal infrared imager 2 is by object The invisible infrared energy that body is sent out is changed into visible thermal image.Different colours above thermal image represent testee not It is synthermal.

The core component of thermal infrared imager 2 is infrared detector, mainly there is detector vanadium oxide and polysilicon detection at present Two kinds of device, the main advantage of vanadium oxide detector are the photoelectric conversion efficiency highers for infrared light, possess higher noise Than with strong light protective capability.The temperature stability of vanadium oxide detector is good, long lifespan, and temperature drift is small.The utility model is preferred The temperature sensing sensitivity of thermal infrared imager 2 with vanadium oxide detector, vanadium oxide can reach 0.03 DEG C.

Wherein, the information interaction of thermal infrared imager 2 and depth camera 1, depth camera 1 acquire the depth information of object, The depth information that the thermal imagery distribution map and depth camera 1 that robot is provided according to thermal infrared imager 2 provide, can be quickly smart Form and the position of the object are judged accurately.Even if robot is under dark surrounds or environmental objects are hidden In the case of, the utility model still can assist in robot and realize accurate positionin and avoidance.

Further, since thermal infrared imager 2 has very high sensitivity to the heat radiation of object, therefore, for burning things which may cause a fire disaster etc. The object of high-temperature, the utility model can realize quickly identifying and positioning for dangerous objects, to prevent safety accident.

In a preferred embodiment, as shown in Figure 1 and Figure 2, the robotic vision system further includes for acquiring the depth Spend the IMU modules 3 of camera 1 and 2 posture information of the thermal infrared imager.The posture information includes rotational angle, angular speed, angle Acceleration etc., the acquisition of the posture information, it is therefore intended that robot control system Real-time Feedback depth camera 1 with it is infrared The position and posture of thermal imaging system 2 is convenient for real-time control.

In a preferred embodiment, as shown in Figure 1 and Figure 2, the IMU modules 3 include gyroscope 31 and accelerometer 32, The gyroscope 31 is used to acquire the rotational angle and angular velocity information of the depth camera 1 and the thermal infrared imager 2, described Accelerometer 32 is used to acquire the acceleration information of the depth camera 1 and the thermal infrared imager 2.

In a preferred embodiment, as shown in Figure 1, the depth camera 1 includes two cameras 11 and taken the photograph set on described As the optical filter 12 of first 11 front end, and the infrared-emitting diode 13 for emitting infrared ray, the optical filter 12 were used for Filter visible light, the camera 11, preferably CCD B/W cameras, the infrared imaging reflected for receiving object.

Wherein, the infrared-emitting diode 13 is worn for emitting infrared ray, infrared ray outward after body surface reflects It crosses the optical filter 12 to be received by video camera, two cameras 11 position object coordinates using visual difference.Due to visible Under the conditions of light, object and the actual object of shot by camera have different, and can then be solved under the conditions of pure infrared ray The problem, therefore optical filter 12 is it will be seen that after light filtering, the depth camera 1 is more smart to the depth information acquisition of object Really.Similarly, under dark surrounds, which can equally acquire object depth information.

In a preferred embodiment, as shown in Fig. 2, the depth camera 1 includes structured light projector 14 and structure optical depth Inductor 15 is spent, the structured light projector 14 is used to project encoded light source to object, and the structure light depth inductor 15 is used In the structure light image for receiving the object reflection.

The utility model is used as by projecting a pre-designed pattern with reference to image, i.e. encoded light source, by structure Light projection reuses the structured light patterns that structure light depth inductor 15 receives body surface reflection, then obtains to body surface Two images were obtained, a width is the reference picture being pre-designed, and in addition a width is the structure for the body surface reflection that camera obtains Light image must deform due to receiving pattern because of the solid type shape of object, therefore can be by the pattern on video camera Position and deformation degree calculate the spatial information of body surface.To quickly accurately match two images, and then complete Object identification.

In a preferred embodiment, as shown in Fig. 2, the depth camera 1 includes also RGB cameras 16, for shooting State the two dimensional image of object.

Since the resolution ratio of depth pattern is relatively low, typically VGA (640x480) is below.And RGB cameras 16 are clapped The image resolution ratio taken the photograph is ten million pixel or more, therefore will be captured by the depth map of low resolution and the RGB cameras 16 Color Image Fusion can be formed with high-resolution three-dimensional color image, convenient for accurately identifying object.To improve fusion essence Degree, the RGB cameras 16 and 15 installation site of structure light depth inductor close to and be located at same level.

In a preferred embodiment, the structured light projector 14 is infrared projector, the structure light depth inductor 15 be infrared inductor, i.e., the described encoded light source is infrared ray.

In a preferred embodiment, as shown in Figure 1 and Figure 2, the robotic vision system further includes setting and the IMU Module 3 connect and close to temperature sense meter 4, the temperature sense meter 4 is for acquiring environment temperature and to the IMU modules 3 Carry out temperature-compensating.

Since the component in IMU modules 3 is easy to be affected by temperature, such as the zero-bit of gyroscope 31 and calibration factor etc..Cause Temperature sense meter 4 is being arranged close to the position of the IMU modules 3 in this utility model, for perceiving around the IMU modules 3 The temperature of environment, for robot control system according to the temperature characterisitic of each component in the temperature and IMU modules 3 into trip temperature Compensation, to reduce harmful effect of the environment temperature to each component in IMU modules 3.

The utility model also provides a kind of robot, as shown in figure 3, the robot includes to be set to the robot head The robotic vision system in (or body portion, limb portion), the vision system include the depth camera 1 and thermal infrared imager 2 of interconnection, The depth camera 1 is used to obtain the depth information of object in the robot, and the thermal infrared imager 2 is for examining The Infrared Thermogram of object in the environment is surveyed, and judges form and the position of the object in conjunction with the depth information of the object It sets.

Robot is correspondingly additionally provided with control system, which connect and carry out with the robotic vision system Information exchange, each item data acquired using the vision system, to realize the functions such as positioning, navigation and avoidance, together When, the depth camera 1 also has recognition of face and safety precaution function, is very suitable for household, safety monitoring and intricately Shape environment work.

It is to be appreciated that the technical solution between each embodiment of the utility model can be combined with each other, but must be with Those of ordinary skill in the art can be implemented as basis, should when the combination of technical solution appearance is conflicting or cannot achieve Think that the combination of this technical solution is not present, also not within the scope of the requires of the utility model is protected.

Above-described is only the part of the utility model or preferred embodiment, and either word or attached drawing all cannot be because The range of this limitation the utility model protection utilizes the utility model under every design with one entirety of the utility model Equivalent structure transformation made by specification and accompanying drawing content, or directly/be used in other related technical areas indirectly and include In the range of the utility model is protected.

Claims (9)

1. a kind of robotic vision system, which is characterized in that the depth camera including interconnection and thermal infrared imager, the depth Degree camera is used to obtain the depth information of object in the robot, and the thermal infrared imager is for detecting the ring The Infrared Thermogram of object in border, and judge in conjunction with the depth information of the object form and the position of the object.

2. robotic vision system as described in claim 1, which is characterized in that further include for acquire the depth camera with The IMU modules of the thermal infrared imager posture information.

3. robotic vision system as claimed in claim 2, which is characterized in that the IMU modules include gyroscope and acceleration Degree meter, the gyroscope are used to acquire the rotational angle and angular velocity information of the depth camera and the thermal infrared imager, institute State acceleration information of the accelerometer for acquiring the depth camera and the thermal infrared imager.

4. robotic vision system as claimed in claim 3, which is characterized in that the depth camera include two cameras and Optical filter set on the camera front end, and the infrared-emitting diode for emitting infrared ray, the optical filter are used for Visible light is filtered, the camera is for receiving the infrared imaging that object is reflected.

5. robotic vision system as claimed in claim 3, which is characterized in that the depth camera includes structured light projector With structure light depth inductor, the structured light projector is used to project encoded light source to object, and the structure light sense of depth is answered Device is used to receive the structure light image of the object reflection.

6. robotic vision system as claimed in claim 5, which is characterized in that the depth camera also includes RGB cameras, Two dimensional image for shooting the object.

7. robotic vision system as claimed in claim 6, which is characterized in that the structured light projector is infrared projection Device, the structure light depth inductor are infrared inductor.

8. the robotic vision system as described in claim 2-7 any one, which is characterized in that further include setting with it is described IMU modules connect and close to temperature sense meter, the temperature sense meter for acquire environment temperature and to the IMU modules into Trip temperature compensates.

9. a kind of robot, which is characterized in that include the robotic vision system described in claim 1-8 any one.