CN117168302A - Workpiece measurement method, medium and system based on multi-view vision - Google Patents
Workpiece measurement method, medium and system based on multi-view vision Download PDFInfo
- Publication number
- CN117168302A CN117168302A CN202310935108.9A CN202310935108A CN117168302A CN 117168302 A CN117168302 A CN 117168302A CN 202310935108 A CN202310935108 A CN 202310935108A CN 117168302 A CN117168302 A CN 117168302A
- Authority
- CN
- China
- Prior art keywords
- model
- workpiece
- view
- camera
- matching
- 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.)
- Granted
Links
- 238000000691 measurement method Methods 0.000 title claims description 10
- 238000000034 method Methods 0.000 claims abstract description 46
- 238000005259 measurement Methods 0.000 claims abstract description 22
- 238000004590 computer program Methods 0.000 claims description 19
- 238000005457 optimization Methods 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 6
- 238000003384 imaging method Methods 0.000 claims description 4
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 4
- 238000001514 detection method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000004519 manufacturing process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 238000013519 translation Methods 0.000 description 3
- 230000014616 translation Effects 0.000 description 3
- 238000009826 distribution Methods 0.000 description 2
- 241000531116 Blitum bonus-henricus Species 0.000 description 1
- 241000238097 Callinectes sapidus Species 0.000 description 1
- 235000008645 Chenopodium bonus henricus Nutrition 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000725 suspension Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The application discloses a workpiece measuring method, medium and system based on multi-view, wherein the method comprises the following steps: acquiring a multi-view image of a workpiece to be measured; the multi-view image is shot by a plurality of 2D cameras in the measuring room; and (3) aligning the 3D model of the workpiece to be measured with the multi-view image, detecting and matching the characteristic points to obtain a matching result, and measuring the workpiece according to the matching result. According to the application, through the 3D technology and the condition that industrial products are provided with the 3D model, 3D model information is introduced to align the multi-objective images, so that the corresponding feature matching and the corresponding multi-objective calibration are improved to improve the measurement precision of the large-size workpiece, the measurement speed can be improved, and the corresponding measurement precision requirement can be met.
Description
Technical Field
The application mainly relates to the technical field of workpiece measurement, in particular to a workpiece measurement method, medium and system based on multi-vision.
Background
The current industrial high-precision detection modes can be divided into two main types according to methods: contact and non-contact. The contact type is a three-coordinate measuring machine, and the non-contact type is scanning and visual detection. The three-coordinate detection equipment has the advantages of simple, accurate and reliable measurement, better flexibility, high price, and inapplicability to online detection when detecting a workpiece, and can only be used for spot check, and can carry out omnibearing control on the size production quality of all goods.
In the related art, some measuring systems have the advantages of non-contact measurement, high three-dimensional measurement precision, high automation degree, strong robustness, low requirement on environment and the like. However, the detection time is long and the price is high, so that the application of the method in the aspects of aviation manufacture, transportation, production of important products and the like is limited.
Because the precision of the multi-vision measurement is critical to the usability of the system, the application of the multi-vision in measuring large-size workpieces is few at present, and the main precision still does not meet the corresponding requirement. The influence on the accuracy of the multi-vision measurement is mainly two, namely, the calibration of a multi-vision camera and the characteristic matching. Although the multi-camera calibration is a classical problem in computer vision, the existing methods cannot meet the requirements of industrial high-precision measurement in most cases although the research is many, and feature matching is also very challenging, because mechanical workpieces usually have no abundant texture information for robust feature detection and matching.
Disclosure of Invention
The technical problem to be solved by the application is as follows: aiming at the technical problems existing in the prior art, the application provides a workpiece measuring method, medium and system based on multi-vision, which can not only improve the measuring speed, but also meet the corresponding measuring precision requirement.
In order to solve the technical problems, the technical scheme provided by the application is as follows:
a workpiece measurement method based on multi-vision, comprising the steps of:
acquiring a multi-view image and a 3D model of a workpiece to be measured; the multi-view image is shot by a plurality of 2D cameras in the measuring room;
and (3) aligning the 3D model of the workpiece to be measured with the multi-view image, extracting and matching the characteristic points to obtain a matching result, and measuring the workpiece to be measured according to the matching result.
Preferably, based on the BA method integrated with the 3D model information, a two-dimensional and three-dimensional relationship between the multi-view image and the 3D model is obtained so as to realize the alignment of the 3D model of the workpiece to be measured and the multi-view image.
Preferably, the corresponding formula of the BA method incorporating 3D model information is:
wherein C represents the camera's collection, P represents all 3D points, K i And [ R ] i |t i ]Respectively represent the internal parameters and external parameters of the ith camera in the collection C, and the 3D point X j At camera C i The re-projection error of (2) is that the 3D point passes through the corresponding projection formula K i ·[R i |t i ]·X j And actually its observation point x on the camera imaging ij Euclidean distance difference between them; in a multi-view system having multiple 3D points and different cameras having different 2D points of view for the 3D points based on different internal and external parameters, using { (X) j ,x ij ) As a set of 2D-3D correspondences; wherein [ R ] m |t m ]Is the pose information of six degrees of freedom of the 3D model.
Preferably, reliable { (X) is selected using RANSAC j ,x ij ) The subsets in the set form a BA residual block, while the other residuals are constructed by using the corresponding relation under the cross view angle, and the further improved BA optimization formula is as follows:
where M is the 3D point in the 3D model and R is the point reconstructed from three dimensions.
Preferably, when feature point detection and matching are performed, after the initial calibration parameters of the multi-camera are aligned with the 3D model, three-dimensional projection is performed to directly obtain a binary image template corresponding to the three-dimensional feature, and a two-dimensional shape matching method is utilized to match the generated binary image template with the region where the corresponding feature of the image shot by the actual multi-camera is located to obtain a corresponding matching result.
Preferably, the three-dimensional feature comprises a hole or corner.
Preferably, the 3D model is a CAD model.
The embodiments of the application also disclose a computer program product comprising a computer program which, when run by a processor, performs the steps of the method as described above.
The embodiments of the present application further disclose a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above.
The embodiment of the application also discloses a workpiece measuring system based on multi-vision, which comprises a memory and a processor which are connected with each other, wherein the memory stores a computer program which executes the steps of the method when being executed by the processor.
Compared with the prior art, the application has the advantages that:
according to the application, through the 3D technology and the condition that industrial products have 3D models (such as CAD models), CAD model information is introduced to align the multi-objective images, so that the corresponding feature matching and the corresponding multi-objective calibration are improved to improve the accuracy in the measurement of the large-size workpiece, the measurement speed can be improved, and the corresponding measurement accuracy requirement can be met.
Drawings
Fig. 1 is a diagram showing a camera distribution in a measuring chamber according to the present application.
FIG. 2 is a diagram showing an embodiment of the measuring method of the present application in a specific application.
FIG. 3 is a diagram of a conventional BA process and an embodiment of the improved BA process of this application in a specific application; wherein (a) corresponds to a conventional BA process and (b) corresponds to an improved BA process.
Fig. 4 is a diagram of the result of matching a template image obtained by hole projection on different CAD models with a hole on an actual picture in the present application.
FIG. 5 is a flow chart of a workpiece measurement method according to an embodiment of the application.
Detailed Description
The application is further described below with reference to the drawings and specific examples.
As shown in fig. 5, the workpiece measurement method based on multi-view according to the embodiment of the application includes the steps of:
acquiring a multi-view image and a 3D model (such as a CAD model and the like) of a workpiece to be measured; as shown in fig. 1, a plurality of 2D cameras (different camera layouts are specific for different workpieces, so that the cameras can cover all areas to be measured) are installed in a measuring chamber, and each time a workpiece to be measured is conveyed to the measuring chamber, all the cameras are triggered to measure, and multi-view images are obtained;
and (3) aligning a 3D model of the workpiece to be measured with the multi-view image, detecting and matching characteristic points, and carrying out fine calibration through the 3D model to realize the measurement of the size, flatness and the like of the workpiece.
According to the application, through the 3D technology and the condition that industrial products have 3D models (such as CAD models), CAD model information is introduced to align the multi-objective images, so that the corresponding feature matching and the corresponding multi-objective calibration are improved to improve the measurement precision of the large-size workpiece, the measurement speed can be improved, and the corresponding measurement precision requirement can be met.
The measuring method solves the problems that the existing measuring technologies such as laser 3D scanning and structured light 3D imaging are small in coverage, limited in splicing precision and the like, and is very suitable for accurate and efficient measurement of large-size workpieces.
When the 3D model of the workpiece to be measured is aligned with the multi-view image, the 6 degree of freedom poses (rotations, translations) of the camera and CAD model need to be co-optimized, since the initial camera calibration may be inaccurate. Specifically, the CAD model is incorporated into BA (Bund le Adjustment) optimization, which requires two-dimensional and three-dimensional relationships between the multi-view image and the CAD model, and according to the calculated correspondence, a BA method blended with CAD model information is provided, and the correspondence can be obtained with the existing feature detection and matching algorithm. Specifically, the formula based on the original BA therein has the following expression:
wherein C represents the camera's collection, P represents all 3D points, K i And [ R ] i |t i ]Respectively represent the internal parameters and external parameters of the ith camera in the collection C, and the 3D point X j At camera C i The re-projection error of (2) is that the 3D point passes through the corresponding projection formula K i ·[R i |t i ]·X j And actually its observation point x on the camera imaging ij Euclidean distance difference between them. In a multi-view system, there are multiple 3D points and different cameras have different 2D points of view for the 3D points based on different internal and external parameters, so { (X) j ,x ij ) As a set of such 2D-3D correspondences. While the process of minimizing this set is called BA optimization, the Levenberg-Marquardt (LM) method is often used to solve this optimization problem.
The application optimizes the existing BA formula by combining the gestures of the CAD model, and the formula is as follows:
wherein [ R ] m |t m ]Is the attitude information of the CAD model with 6 degrees of freedom, comprising rotation (rotation angle of 3 directions) and translation (translation amount of xyz), and can perfectly realize 2D-3D alignment by optimizing the CAD model under ideal condition.
In addition, slight differences in the measured workpiece and CAD model may result in two-dimensional and three-dimensional feature point mismatch due to manufacturing errors. Because manufacturing errors are unavoidable, the present application utilizes a robust BA optimization, i.e., reliable { (X) selection using RANSAC, to accommodate manufacturing errors j ,x ij ) The subsets in the set form a BA residual block (reprojection error), while the other residuals are constructed by using the corresponding relation under the cross view angle, and the BA optimization formula is further improved as follows:
where M is the 3D point in the CAD model and R is the point reconstructed from three dimensions. In this way, the CAD features are considered to provide strong constraint, which is helpful for uniformly distributing the re-projection errors in the whole camera distribution, and the problem caused by manufacturing errors of the actual workpiece is also considered, so that the two corresponding relations are beneficial to high-precision secondary calibration of the whole camera equipment, and further high-precision measurement can be carried out on the measured workpiece.
As shown in FIG. 3, where (a) in FIG. 3 is a conventional BA (beam adjustment method) that is to make a 3D point X j This optimization process may further adjust the camera's internal and external parameters based on the fact that the difference between the projection of the two cameras' internal and external parameters and the point of view (2D) of the 3D point on the two cameras is minimal (minimizing the re-projection error). In fig. 3 (b), an improved BA mode (mixed beam adjustment method, 3D feature points with large matching errors will be filtered and replaced with reconstructed points in large-size high-precision measurement, wherein blue points in the figure are well matched CAD feature points, orange points are well matched CAD feature points, green points are reconstructed points), a CAD model is introduced into BA optimization, and the 3D points are classified for optimization, so that corresponding robustness is improved, and high-precision secondary calibration of camera equipment is improved.
The above-mentioned optimized formula can show that the 2D viewpoint matching accuracy of the same 3D point under different camera angles also affects the corresponding reconstruction point, and the general workpiece has no abundant texture, so that the feature extraction and matching also become a difficulty. The main difficulty in using the template matching method is to generate the template, the original method is to manually sketch the template (binary image), and the method is time-consuming and easy to introduce human errors. Therefore, three-dimensional features (such as holes, corners and the like) are pre-existing and marked on the CAD model, three-dimensional projection is carried out after the initial calibration parameters of the multiple cameras are aligned with the CAD model to directly obtain a binary image template of the corresponding hole, and a two-dimensional shape matching method is utilized to match the generated binary image template with the Region (ROI) of the corresponding hole of the actual multi-view shooting image to obtain a corresponding matching result. The method utilizes the holes on the CAD model and the camera internal and external parameters corresponding to the initial calibration to project to generate the corresponding binary image, and because the precision of the digital model is very high, the obtained error is far smaller than that of a binary image template manually sketched.
As shown in fig. 4, the result of matching the template image obtained by the hole projection on different CAD models with the hole on the actual picture is that the corresponding 3D position can be reconstructed by matching the hole center 2D coordinates of the same hole under different cameras.
The application realizes the detection of large-size workpieces (such as battery boxes, vehicle suspensions and the like) based on a multi-view system, because the cameras are large in multi-scale, the high-precision calibration of the cameras is critical to the detection precision, and the existing BA algorithm is optimized based on prior information of CAD digital and analog of each workpiece, so that the robustness can be effectively improved. According to the application, the CAD model and the corresponding calibrated camera internal and external parameters are introduced to generate a high-precision template, so that the detection precision of the 2D characteristic points is improved, and the reconstructed 3D point precision is further improved.
The embodiments of the application also disclose a computer program product comprising a computer program which, when run by a processor, performs the steps of the method as described above. The embodiments of the present application further disclose a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the method as described above. The embodiment of the application also discloses a computer device comprising a memory and a processor, wherein the memory stores a computer program which, when being executed by the processor, performs the steps of the method as described above. The program product, medium and measuring system of the application correspond to the measuring method described above, as well as have the advantages described above for the measuring method.
It will be appreciated by those skilled in the art that the above-described embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein. The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above is only a preferred embodiment of the present application, and the protection scope of the present application is not limited to the above examples, and all technical solutions belonging to the concept of the present application belong to the protection scope of the present application. It should be noted that modifications and adaptations to the application without departing from the principles thereof are intended to be within the scope of the application as set forth in the following claims.
Claims (10)
1. A method for measuring a workpiece based on multi-vision, comprising the steps of:
acquiring a multi-view image and a 3D model of a workpiece to be measured; the multi-view image is shot by a plurality of 2D cameras in the measuring room;
and (3) aligning the 3D model of the workpiece to be measured with the multi-view image, extracting and matching the characteristic points to obtain a matching result, and measuring the workpiece to be measured according to the matching result.
2. The multi-view vision-based workpiece measurement method according to claim 1, wherein a two-dimensional and three-dimensional relationship between the multi-view image and the 3D model is acquired based on a BA method incorporated into the 3D model information to achieve alignment of the 3D model and the multi-view image of the workpiece to be measured.
3. The multi-vision based workpiece measurement method of claim 2, wherein the corresponding formula of the BA method incorporating 3D model information is:
wherein C represents the camera's collection, P represents all 3D points, K i And [ R ] i |t i ]Respectively represent the internal parameters and external parameters of the ith camera in the collection C, and the 3D point X j At camera C i The re-projection error of (2) is that the 3D point passes through the corresponding projection formula K i ·[R i |t i ]·X j And actually its observation point x on the camera imaging ij Euclidean distance difference between them; in a multi-view system having multiple 3D points and different cameras having different 2D points of view for the 3D points based on different internal and external parameters, using { (X) j ,x ij ) As a set of 2D-3D correspondences; wherein [ R ] m |t m ]Is the pose information of six degrees of freedom of the 3D model.
4. A method of multi-vision based workpiece measurement as defined in claim 3, wherein reliable { (X) is selected using RANSAC j ,x ij ) The subsets in the set form a BA residual block, while the other residuals are constructed by using the corresponding relation under the cross view angle, and the further improved BA optimization formula is as follows:
where M is the 3D point in the 3D model and R is the point reconstructed from three dimensions.
5. The method for measuring workpieces based on multi-view according to any one of claims 1 to 4, wherein when feature points are detected and matched, after the parameters initially calibrated by the multi-view camera are aligned with the 3D model, a binary image template corresponding to the three-dimensional features is directly obtained by three-dimensional projection, and a two-dimensional shape matching method is used for matching the generated binary image template with the region where the corresponding features of the images shot by the actual multi-view camera are located to obtain a corresponding matching result.
6. The multi-vision based workpiece measurement method of claim 5, wherein the three-dimensional features comprise holes or corners.
7. The multi-vision based workpiece measurement method of any one of claims 1-4, wherein the 3D model is a CAD model.
8. A computer program product comprising a computer program which, when run by a processor, performs the steps of the method according to any one of claims 1 to 7.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the method according to any one of claims 1-7.
10. A multi-vision based workpiece measurement system comprising a memory and a processor connected to each other, the memory having stored thereon a computer program which, when executed by the processor, performs the steps of the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310935108.9A CN117168302B (en) | 2023-07-27 | 2023-07-27 | Workpiece measurement method, medium and system based on multi-view vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310935108.9A CN117168302B (en) | 2023-07-27 | 2023-07-27 | Workpiece measurement method, medium and system based on multi-view vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117168302A true CN117168302A (en) | 2023-12-05 |
| CN117168302B CN117168302B (en) | 2024-08-16 |
Family
ID=88930816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310935108.9A Active CN117168302B (en) | 2023-07-27 | 2023-07-27 | Workpiece measurement method, medium and system based on multi-view vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117168302B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130083990A1 (en) * | 2011-10-04 | 2013-04-04 | Metalforming, Inc. | Using Videogrammetry to Fabricate Parts |
| WO2016065063A1 (en) * | 2014-10-22 | 2016-04-28 | Pointivo, Inc. | Photogrammetric methods and devices related thereto |
| CN110955958A (en) * | 2019-11-09 | 2020-04-03 | 江苏跃格智能装备有限公司 | Working method of workpiece positioning device based on CAD model |
| CN113658270A (en) * | 2021-08-10 | 2021-11-16 | 湖南视比特机器人有限公司 | Multi-view visual calibration method, device, medium and system based on workpiece hole center |
| WO2022037285A1 (en) * | 2020-08-20 | 2022-02-24 | 北京达佳互联信息技术有限公司 | Camera extrinsic calibration method and apparatus |
| CN114332247A (en) * | 2022-01-07 | 2022-04-12 | 湖南视比特机器人有限公司 | Calibration method and device for multi-view vision measurement, storage medium and camera equipment |
| CN115272569A (en) * | 2022-07-25 | 2022-11-01 | 武汉中观自动化科技有限公司 | Generation method and generation device of deviation and color difference graph of three-dimensional data and electronic equipment |
-
2023
- 2023-07-27 CN CN202310935108.9A patent/CN117168302B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130083990A1 (en) * | 2011-10-04 | 2013-04-04 | Metalforming, Inc. | Using Videogrammetry to Fabricate Parts |
| WO2016065063A1 (en) * | 2014-10-22 | 2016-04-28 | Pointivo, Inc. | Photogrammetric methods and devices related thereto |
| CN110955958A (en) * | 2019-11-09 | 2020-04-03 | 江苏跃格智能装备有限公司 | Working method of workpiece positioning device based on CAD model |
| WO2022037285A1 (en) * | 2020-08-20 | 2022-02-24 | 北京达佳互联信息技术有限公司 | Camera extrinsic calibration method and apparatus |
| CN113658270A (en) * | 2021-08-10 | 2021-11-16 | 湖南视比特机器人有限公司 | Multi-view visual calibration method, device, medium and system based on workpiece hole center |
| CN114332247A (en) * | 2022-01-07 | 2022-04-12 | 湖南视比特机器人有限公司 | Calibration method and device for multi-view vision measurement, storage medium and camera equipment |
| CN115272569A (en) * | 2022-07-25 | 2022-11-01 | 武汉中观自动化科技有限公司 | Generation method and generation device of deviation and color difference graph of three-dimensional data and electronic equipment |
Non-Patent Citations (4)
| Title |
|---|
| 吴毅红: "基于图像的相机定位技术综述", 人工智能, no. 2, 10 April 2019 (2019-04-10), pages 50 - 64 * |
| 宛ER: "视觉SLAM—BA模型的理解", Retrieved from the Internet <URL:https://blog.csdn.net/xranmail/article/details/86486759> * |
| 左正康等人: "三维摄影条件下视差角光束法平差模型的适用性研究", 北京大学学报(自然科学版), vol. 59, no. 3, 31 May 2023 (2023-05-31), pages 445 - 455 * |
| 李洁: "基于点云的空间非合作目标位姿估计关键技术研究", 工程科技I辑, no. 7, 15 July 2023 (2023-07-15), pages 140 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117168302B (en) | 2024-08-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2236980B1 (en) | A method for determining the relative position of a first and a second imaging device and devices therefore | |
| Furukawa et al. | Accurate camera calibration from multi-view stereo and bundle adjustment | |
| CN115345822A (en) | Automatic three-dimensional detection method for surface structure light of aviation complex part | |
| CN103196370B (en) | Measuring method and measuring device of conduit connector space pose parameters | |
| CN103366360B (en) | Information processing apparatus and information processing method | |
| CN105066962B (en) | A kind of high-precision photogrammetric apparatus of the big angle of visual field of multiresolution | |
| EP2932191A2 (en) | Apparatus and method for three dimensional surface measurement | |
| CN111609801A (en) | Multi-size workpiece thickness measuring method and system based on machine vision | |
| Mohr et al. | Relative positioning from geometric invariants. | |
| US10252417B2 (en) | Information processing apparatus, method of controlling information processing apparatus, and storage medium | |
| Resch et al. | On-site semi-automatic calibration and registration of a projector-camera system using arbitrary objects with known geometry | |
| Bergström et al. | Virtual projective shape matching in targetless CAD-based close-range photogrammetry for efficient estimation of specific deviations | |
| CN110044266B (en) | Photogrammetry system based on speckle projection | |
| Jiang et al. | A ball-shaped target development and pose estimation strategy for a tracking-based scanning system | |
| Yamauchi et al. | Calibration of a structured light system by observing planar object from unknown viewpoints | |
| Bergström et al. | Automatic in-line inspection of shape based on photogrammetry | |
| CN110458951B (en) | Modeling data acquisition method and related device for power grid pole tower | |
| CN117168302B (en) | Workpiece measurement method, medium and system based on multi-view vision | |
| Yang et al. | Improved calibration method of binocular vision measurement system for large hot forging | |
| JP4429135B2 (en) | Three-dimensional shape measurement system and measurement method | |
| Yu et al. | Multi-view 2D–3D alignment with hybrid bundle adjustment for visual metrology | |
| Sheng et al. | Image segmentation and object measurement based on stereo vision | |
| Percoco et al. | 3D image based modelling for inspection of objects with micro-features, using inaccurate calibration patterns: an experimental contribution | |
| Ping et al. | Verification of turning insert specifications through three-dimensional vision system | |
| Uyanik et al. | A method for determining 3D surface points of objects by a single camera and rotary stage |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |