CN111768449A - Object grabbing method combining binocular vision with deep learning - Google Patents
Object grabbing method combining binocular vision with deep learning Download PDFInfo
- Publication number
- CN111768449A CN111768449A CN201910254109.0A CN201910254109A CN111768449A CN 111768449 A CN111768449 A CN 111768449A CN 201910254109 A CN201910254109 A CN 201910254109A CN 111768449 A CN111768449 A CN 111768449A
- Authority
- CN
- China
- Prior art keywords
- target
- information
- matching
- image
- deep learning
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013135 deep learning Methods 0.000 title claims abstract description 23
- 238000004364 calculation method Methods 0.000 claims abstract description 6
- 239000013598 vector Substances 0.000 claims description 20
- 238000001514 detection method Methods 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 description 9
- 238000013519 translation Methods 0.000 description 7
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/757—Matching configurations of points or features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Abstract
The invention discloses an object grabbing method combining binocular vision and deep learning, which comprises the following steps: acquiring binocular images; respectively carrying out target identification on the left image and the right image to obtain target area information; calculating a region characteristic value according to the region information of each target, and matching left and right targets; calculating the target pose by using the target area information and the matching relation of the left image and the right image; and the mechanical actuator performs grabbing. The invention combines the binocular vision of the self-adaptive deep learning algorithm model, utilizes the self-adaptive deep learning algorithm model to carry out feature matching, obtains more accurate matching features and matching relations, and further leads the calculation result of the binocular vision to be more accurate and stable, thereby improving the application efficiency and the reliability of the mechanical arm for positioning and grabbing the object.
Description
Technical Field
The invention belongs to the technical field of mechanical arm positioning and grabbing application, and particularly relates to an object grabbing method combining binocular vision and deep learning.
Background
The mechanical arm determines the application efficiency and reliability of the mechanical arm for positioning and grabbing the object, and based on the identification and positioning of the object by binocular stereo vision, the position information of the object can be quickly obtained, and the positioning and grabbing of the object by the mechanical arm are realized. Binocular stereoscopic vision is an important branch of computer vision, two cameras are used for shooting the same object from different positions to obtain two images, corresponding points in the two images are found out through a matching algorithm, parallax is obtained through calculation, and distance information of the object in the real world is recovered based on a triangulation principle. In actual use, each matching algorithm has poor extracted matching characteristics due to self defects, and the difficulty in extracting the matching characteristics is increased when the texture missing object is processed, so that the matching effect is not perfect.
The deep learning can utilize the useful characteristics extracted by the supervised training automatic learning, so that the characteristics can be more abstractly and highly expressed, and the distributed and parallel computing capability is the greatest advantage. The deep learning is applied to the matching process of binocular vision, the defects of common binocular vision are overcome, and the method has high practical value.
Disclosure of Invention
Aiming at the problems, the invention provides an object grabbing method combining binocular vision and deep learning. The technical scheme adopted by the invention is as follows:
an object grabbing method combining binocular vision and deep learning comprises the following steps: acquiring binocular images; respectively carrying out target identification on the left image and the right image to obtain target area information; calculating a region characteristic value according to the region information of each target, and matching left and right targets; calculating the target pose by using the target area information and the matching relation of the left image and the right image; and the mechanical actuator performs grabbing.
Further, the acquiring binocular images comprises: carrying out three-dimensional calibration on the binocular camera; respectively acquiring a left image and a right image of a target object through a left camera and a right camera of a binocular camera; and performing epipolar line correction on the left image and the right image to align the corrected left image and right image.
Further, the performing target identification on the left image and the right image respectively to obtain target area information includes: cutting the image size to a specified size; inputting the data into a self-adaptive deep learning algorithm for processing; and outputting the detection result as the basis of subsequent matching.
Further, the adaptive deep learning algorithm is based on a classic target detection algorithm SSD, and on an original algorithm CONV4_3 layer, a FPN algorithm idea is utilized to perform up-sampling on multi-level Feature Maps so as to improve the small target detection precision.
Further, the calculating a region feature value according to the information of each target region and performing matching of the left target and the right target includes: calculating a reference anchor point according to the regional information of the left image and the right image; calculating the characteristic information P of each block of regional information according to the anchor points; and matching the left target and the right target.
Further, the calculating the reference anchor point according to the region information of the left and right images includes: the calculation of the anchor point is completed by the size and the center point of each area, and the specific method is as follows:
where Qi is the target region size and Ki is the target region center.
Further, the calculating the feature information P of each block of region information according to the anchor point includes: from anchor point information (x)0，y0) And region information (x, y, w, h, t), calculating coordinate offset information (x-x)0，y-y0) And region information (w x h, t) which together form feature information P (x-x)0，y-y0，w*h，t)。
Further, the left and right target matching comprises: and (3) regarding the feature information P as four-dimensional vectors, respectively multiplying the four-dimensional vectors by corresponding weights, then calculating the Euclidean distance between the two vectors to be regarded as the final difference degree of the vectors, and obtaining a matching combination by using a WTA (winner Take ALL) algorithm according to the difference degree.
The invention has the beneficial effects that: the binocular vision of the self-adaptive deep learning algorithm model is combined, the self-adaptive deep learning algorithm model is used for feature matching, more accurate matching features and matching relations are obtained, the binocular vision calculation result is more accurate and stable, and therefore the application efficiency and reliability of the mechanical arm in positioning and grabbing the object are improved.
Drawings
Fig. 1 is a schematic flow chart of an object grabbing method combining binocular vision and deep learning according to the invention.
Detailed Description
The following detailed description of the preferred embodiments of the present invention, taken in conjunction with the accompanying drawings, will make the advantages and features of the invention easier to understand by those skilled in the art, and thus will clearly and clearly define the scope of the invention.
Referring to fig. 1, the embodiment of the present invention specifically includes the following steps:
(1) and carrying out three-dimensional calibration on the binocular camera.
The method specifically comprises the following steps: respectively calibrating a left camera and a right camera of a binocular camera to obtain an internal reference matrix A of the binocular camera and a rotation matrix R of the left camera1And a rotation matrix R of the right camera2And the translation vector T of the left camera1And a translation vector T of the right camera2(ii) a Calculating a rotation matrix R and a translation vector T between the left camera and the right camera according to the following formula:
(2) and respectively acquiring a left image and a right image of the target object through a left camera and a right camera of the binocular camera.
(3) And performing epipolar line correction on the left image and the right image to align the corrected left image and right image.
The method specifically comprises the following steps: decomposing the rotation matrix R into two rotation matrices R1And r2Wherein r is1And r2The method comprises the steps that the left camera and the right camera are rotated by half respectively to enable the optical axes of the left camera and the right camera to be parallel;
aligning the left image and the right image is achieved by:
wherein R isrectRotation matrix to align rows:
rotation matrix RrectBy pole e1Starting the direction, mainly using the original point of the left image, and taking the direction from the left camera to the translation vector of the right camera as a main point direction:
e1and e2Is orthogonal to e1Normalized to unit vector:
wherein, TxIs the component of the translation vector T in the horizontal direction in the plane of the binocular camera, TyThe component of the translation vector T in the vertical direction in the plane where the binocular camera is located is taken as the translation vector T;
e3and e1And e2Orthogonal, e3Calculated by the following formula:
e3＝e2×e1
according to the physical significance of the rotation matrix, the method comprises the following steps:
wherein α represents the angle of rotation of the left and right cameras in the plane of the left and right cameras, 0- α -180 DEG, and the left camera is aligned around e3Direction rotation α', for the right camera, around e3The direction is rotated α ".
(4) And respectively carrying out target identification on the left image and the right image to obtain target area information.
The method specifically comprises the following steps: cutting the image size to 300 multiplied by 300 mm; inputting the cut image into a self-adaptive deep learning algorithm for processing; and outputting the detection result as the basis of subsequent matching.
(5) And calculating the reference anchor point according to the information of each target area.
The calculation of the anchor point is completed by the size and the center point of each area, and the specific method is as follows:
where Qi is the target region size and Ki is the target region center.
(6) And calculating the characteristic information P of each block of region information according to the anchor point.
The method specifically comprises the following steps: from anchor point information (x)0，y0) And region information (x, y, w, h, t), calculating coordinate offset information (x-x)0，y-y0) And region information (w x h, t) which together form feature information P (x-x)0，y-y0，w*h，t)。
(7) And performing left-right matching according to the obtained characteristic information P.
The method specifically comprises the following steps: and (3) regarding the feature information P as four-dimensional vectors, respectively multiplying the four-dimensional vectors by corresponding weights, then calculating the Euclidean distance between the two vectors to be regarded as the final difference degree of the vectors, and obtaining a matching combination by using a WTA (winner Take ALL) algorithm according to the difference degree.
(8) And calculating the three-dimensional coordinates of the characteristic points according to the binocular stereoscopic vision principle by using the obtained matching relationship. The method specifically comprises the following steps:
let the left camera O-xyz be located at the origin of the world coordinate system and no rotation occurs, and the image coordinate system is Ol-X1Y1Effective focal length of fl(ii) a Coordinate system of right camera OrXyz, image coordinate system Or-XrYrEffective focal length of fr. Then we can get the following relation from the projection model of the camera:
because of the O-xyz coordinate system and Or-xryrzrThe positional relationship between the coordinate systems may be transformed by a spatial transformation matrix MLrExpressed as:
similarly, for spatial points in the O-xyz coordinate system, the correspondence between two camera face points can be expressed as:
the spatial point three-dimensional coordinates can then be expressed as:
therefore, the left and right computer internal parameters/focal length f can be obtained by the computer calibration technologyr,flAnd the image coordinates of the space points in the left camera and the right camera can reconstruct the three-dimensional space coordinates of the measured point.
(9) And the mechanical executing mechanism determines the position of the object according to the acquired three-dimensional coordinates and captures the object.
Claims (8)
1. An object grabbing method combining binocular vision and deep learning is characterized by comprising the following steps: acquiring binocular images; respectively carrying out target identification on the left image and the right image to obtain target area information; calculating a region characteristic value according to the region information of each target, and matching left and right targets; calculating the target pose by using the target area information and the matching relation of the left image and the right image; and the mechanical actuator performs grabbing.
2. The binocular vision combined deep learning object grabbing method according to claim 1, wherein the acquiring of binocular images comprises: carrying out three-dimensional calibration on the binocular camera; respectively acquiring a left image and a right image of a target object through a left camera and a right camera of a binocular camera; and performing epipolar line correction on the left image and the right image to align the corrected left image and right image.
3. The binocular vision combined with deep learning object capture method according to claim 1, wherein the performing of the target recognition on the left and right images respectively to obtain the target area information comprises: cutting the image size to a specified size; inputting the data into a self-adaptive deep learning algorithm for processing; and outputting the detection result as the basis of subsequent matching.
4. The adaptive deep learning algorithm according to claim 3, wherein the adaptive deep learning algorithm is based on a classic target detection algorithm SSD, and at the original algorithm CONV4_3 level, a multi-level Feature Maps is up-sampled by using an FPN algorithm idea to improve the small target detection accuracy.
5. The binocular vision combined with deep learning object capturing method according to claim 1, wherein the calculating of the region feature values according to the region information of each object and the matching of the left and right objects comprises: calculating a reference anchor point according to the regional information of the left image and the right image; calculating the characteristic information P of each block of regional information according to the anchor points; and matching the left target and the right target.
6. The method of claim 5, wherein the anchor point is calculated according to the area information of the left and right images, and the calculation is performed according to the size of each area and the center point thereof, as follows:
where Qi is the target region size and Ki is the target region center.
7. The method of claim 5, wherein the computing of the feature information P of each block of region information according to the anchor point comprises: from anchor point information (x)0，y0) And regional informationInformation (x, y, w, h, t), coordinate offset information (x-x) is calculated0，y-y0) And region information (w x h, t) which together form feature information P (x-x)0，y-y0，w*h，t)。
8. The left-right object matching according to claim 5, comprising: and (3) regarding the feature information P as four-dimensional vectors, respectively multiplying the four-dimensional vectors by corresponding weights, then calculating the Euclidean distance between the two vectors to be regarded as the final difference degree of the vectors, and obtaining a matching combination by using a WTA (winner Take ALL) algorithm according to the difference degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254109.0A CN111768449A (en) | 2019-03-30 | 2019-03-30 | Object grabbing method combining binocular vision with deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910254109.0A CN111768449A (en) | 2019-03-30 | 2019-03-30 | Object grabbing method combining binocular vision with deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111768449A true CN111768449A (en) | 2020-10-13 |
Family
ID=72718687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910254109.0A Pending CN111768449A (en) | 2019-03-30 | 2019-03-30 | Object grabbing method combining binocular vision with deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111768449A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393524A (en) * | 2021-06-18 | 2021-09-14 | 常州大学 | Target pose estimation method combining deep learning and contour point cloud reconstruction |
| CN113689422A (en) * | 2021-09-08 | 2021-11-23 | 理光软件研究所（北京）有限公司 | Image processing method and device and electronic equipment |
| CN113689326A (en) * | 2021-08-06 | 2021-11-23 | 西南科技大学 | Three-dimensional positioning method based on two-dimensional image segmentation guidance |
| CN113808197A (en) * | 2021-09-17 | 2021-12-17 | 山西大学 | Automatic workpiece grabbing system and method based on machine learning |
| CN117409340A (en) * | 2023-12-14 | 2024-01-16 | 上海海事大学 | Unmanned aerial vehicle cluster multi-view fusion aerial photography port monitoring method, system and medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015042460A1 (en) * | 2013-09-20 | 2015-03-26 | Camplex, Inc. | Surgical visualization systems and displays |
| CN107192331A (en) * | 2017-06-20 | 2017-09-22 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of workpiece grabbing method based on binocular vision |
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN108076338A (en) * | 2016-11-14 | 2018-05-25 | 北京三星通信技术研究有限公司 | Image vision processing method, device and equipment |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108229456A (en) * | 2017-11-22 | 2018-06-29 | 深圳市商汤科技有限公司 | Method for tracking target and device, electronic equipment, computer storage media |
| CN108381549A (en) * | 2018-01-26 | 2018-08-10 | 广东三三智能科技有限公司 | A kind of quick grasping means of binocular vision guided robot, device and storage medium |
| CN108647573A (en) * | 2018-04-04 | 2018-10-12 | 杭州电子科技大学 | A kind of military target recognition methods based on deep learning |
| CN108656107A (en) * | 2018-04-04 | 2018-10-16 | 北京航空航天大学 | A kind of mechanical arm grasping system and method based on image procossing |
| CN108876855A (en) * | 2018-05-28 | 2018-11-23 | 哈尔滨工程大学 | A kind of sea cucumber detection and binocular visual positioning method based on deep learning |
| CN109034018A (en) * | 2018-07-12 | 2018-12-18 | 北京航空航天大学 | A kind of low latitude small drone method for barrier perception based on binocular vision |
| CN109102547A (en) * | 2018-07-20 | 2018-12-28 | 上海节卡机器人科技有限公司 | Robot based on object identification deep learning model grabs position and orientation estimation method |
-
2019
- 2019-03-30 CN CN201910254109.0A patent/CN111768449A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015042460A1 (en) * | 2013-09-20 | 2015-03-26 | Camplex, Inc. | Surgical visualization systems and displays |
| CN108076338A (en) * | 2016-11-14 | 2018-05-25 | 北京三星通信技术研究有限公司 | Image vision processing method, device and equipment |
| CN107192331A (en) * | 2017-06-20 | 2017-09-22 | 佛山市南海区广工大数控装备协同创新研究院 | A kind of workpiece grabbing method based on binocular vision |
| CN107767423A (en) * | 2017-10-10 | 2018-03-06 | 大连理工大学 | A kind of mechanical arm target positioning grasping means based on binocular vision |
| CN108229456A (en) * | 2017-11-22 | 2018-06-29 | 深圳市商汤科技有限公司 | Method for tracking target and device, electronic equipment, computer storage media |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| CN108381549A (en) * | 2018-01-26 | 2018-08-10 | 广东三三智能科技有限公司 | A kind of quick grasping means of binocular vision guided robot, device and storage medium |
| CN108647573A (en) * | 2018-04-04 | 2018-10-12 | 杭州电子科技大学 | A kind of military target recognition methods based on deep learning |
| CN108656107A (en) * | 2018-04-04 | 2018-10-16 | 北京航空航天大学 | A kind of mechanical arm grasping system and method based on image procossing |
| CN108876855A (en) * | 2018-05-28 | 2018-11-23 | 哈尔滨工程大学 | A kind of sea cucumber detection and binocular visual positioning method based on deep learning |
| CN109034018A (en) * | 2018-07-12 | 2018-12-18 | 北京航空航天大学 | A kind of low latitude small drone method for barrier perception based on binocular vision |
| CN109102547A (en) * | 2018-07-20 | 2018-12-28 | 上海节卡机器人科技有限公司 | Robot based on object identification deep learning model grabs position and orientation estimation method |
Non-Patent Citations (5)
| Title |
|---|
| SHUXIN LI 等: "Multiscale Rotated Bounding Box-Based Deep Learning Method for Detecting Ship Targets in Remote Sensing Images", 《SENSORS》, vol. 18, no. 08, 17 August 2018 (2018-08-17), pages 1 - 14 * |
| 原彬理: "基于双目立体视觉的普通工件图像匹配与定位", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2019, 15 March 2019 (2019-03-15), pages 138 - 805 * |
| 徐凯: "基于双目视觉的机械手定位抓取技术的研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 2018, 15 June 2018 (2018-06-15), pages 138 - 1247 * |
| 李传朋: "基于机器视觉和深度学习的目标识别与抓取定位研究", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 2017, pages 138 - 356 * |
| 马利 等: "适于硬件实现的自适应权重立体匹配算法", 《系统仿真学报》, vol. 26, no. 09, pages 2079 - 2084 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113393524A (en) * | 2021-06-18 | 2021-09-14 | 常州大学 | Target pose estimation method combining deep learning and contour point cloud reconstruction |
| CN113393524B (en) * | 2021-06-18 | 2023-09-26 | 常州大学 | Target pose estimation method combining deep learning and contour point cloud reconstruction |
| CN113689326A (en) * | 2021-08-06 | 2021-11-23 | 西南科技大学 | Three-dimensional positioning method based on two-dimensional image segmentation guidance |
| CN113689326B (en) * | 2021-08-06 | 2023-08-04 | 西南科技大学 | Three-dimensional positioning method based on two-dimensional image segmentation guidance |
| CN113689422A (en) * | 2021-09-08 | 2021-11-23 | 理光软件研究所（北京）有限公司 | Image processing method and device and electronic equipment |
| CN113808197A (en) * | 2021-09-17 | 2021-12-17 | 山西大学 | Automatic workpiece grabbing system and method based on machine learning |
| CN117409340A (en) * | 2023-12-14 | 2024-01-16 | 上海海事大学 | Unmanned aerial vehicle cluster multi-view fusion aerial photography port monitoring method, system and medium |
| CN117409340B (en) * | 2023-12-14 | 2024-03-22 | 上海海事大学 | Unmanned aerial vehicle cluster multi-view fusion aerial photography port monitoring method, system and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110728715B (en) | Intelligent inspection robot camera angle self-adaptive adjustment method | |
| CN111768449A (en) | Object grabbing method combining binocular vision with deep learning | |
| CN109272570B (en) | Space point three-dimensional coordinate solving method based on stereoscopic vision mathematical model | |
| CN105894499B (en) | A kind of space object three-dimensional information rapid detection method based on binocular vision | |
| CN104463108B (en) | A kind of monocular real time target recognitio and pose measuring method | |
| CN106570913B (en) | monocular SLAM rapid initialization method based on characteristics | |
| CN109767474B (en) | Multi-view camera calibration method and device and storage medium | |
| TWI555379B (en) | An image calibrating, composing and depth rebuilding method of a panoramic fish-eye camera and a system thereof | |
| CN111897349B (en) | Autonomous obstacle avoidance method for underwater robot based on binocular vision | |
| CN107843251B (en) | Pose estimation method of mobile robot | |
| CN111127524A (en) | Method, system and device for tracking trajectory and reconstructing three-dimensional image | |
| CN110555878B (en) | Method and device for determining object space position form, storage medium and robot | |
| TWI709062B (en) | Virtuality reality overlapping method and system | |
| CN112184811B (en) | Monocular space structured light system structure calibration method and device | |
| WO2020063058A1 (en) | Calibration method for multi-degree-of-freedom movable vision system | |
| CN112734863A (en) | Crossed binocular camera calibration method based on automatic positioning | |
| WO2022040983A1 (en) | Real-time registration method based on projection marking of cad model and machine vision | |
| CN110490943A (en) | Quick method for precisely marking, system and the storage medium of 4D holography capture system | |
| CN111213159A (en) | Image processing method, device and system | |
| CN110827321A (en) | Multi-camera cooperative active target tracking method based on three-dimensional information | |
| CN104346614A (en) | Watermelon image processing and positioning method under real scene | |
| CN113240749B (en) | Remote binocular calibration and ranging method for recovery of unmanned aerial vehicle facing offshore ship platform | |
| CN115345942A (en) | Space calibration method and device, computer equipment and storage medium | |
| Wang et al. | Automatic measurement based on stereo vision system using a single PTZ camera | |
| KR102107465B1 (en) | System and method for generating epipolar images by using direction cosine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |