CN101930628A - Monocular-camera and multiplane mirror catadioptric device-based motion capturing method - Google Patents
Monocular-camera and multiplane mirror catadioptric device-based motion capturing method Download PDFInfo
- Publication number
- CN101930628A CN101930628A CN 201010288904 CN201010288904A CN101930628A CN 101930628 A CN101930628 A CN 101930628A CN 201010288904 CN201010288904 CN 201010288904 CN 201010288904 A CN201010288904 A CN 201010288904A CN 101930628 A CN101930628 A CN 101930628A
- Authority
- CN
- China
- Prior art keywords
- camera
- data
- point
- multiplane
- monocular
- 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
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a monocular-camera and multiplane mirror catadioptric device-based novel motion capturing method. The method comprises the following steps of: acquiring data of a travel object in a photographing area by using a multiplane mirror and a monocular camera; acquiring an index point by using a threshold method, and three-dimensionally reestablishing the index point; and finally, combining an index point motion trail obtained by treatment with a three-dimensional model and editing the motion. In the invention, by using the monocular camera and by fully using the catadioptric relation between the multiplane mirrors, the problem of multiple camera calibration caused by a camera array used in the traditional motion capturing system and the problem of synchronous control are solved, so that the aim of improving the three-dimensional recovery precision of the index point and the stability of the system is fulfilled, the system cost is greatly reduced at the same time, the system has high expandability and motion capture becomes simple and feasible.
Description
Technical field
The invention provides a kind of novel motion capture method, be specifically related to a kind of motion capture method based on monocular-camera and multiplane mirror catadioptric device.
Background technology
Movement capturing technology relates to the data that aspects such as the location of object in dimensional measurement, the physical space and direction-finding can directly be understood processing by computing machine.Key position in moving object is provided with tracker, by motion capture system acquisition tracking device position, provides the data that can use through the Computer Processing rear line in cartoon making again.After data were by computer Recognition, the animation teacher promptly can adjust in the camera lens that computing machine produces, the object of controlled motion.
The appearance of movement capturing technology can be traced back to later 1970s, this method of proposing for the quality of movement that improves cartoon role of Disney company at that time, and abandon because of effect is undesirable the back.After this, movement capturing technology has attracted more and more researchists and developer's sight, and has progressively moved towards practicability and commercialization from experimental research.Develop rapidly along with computer hardware technique, at present in developed country, motion-capturedly be widely used, successfully be applied to many aspects such as video display special efficacy, cartoon making, virtual reality, recreation, ergonomics, simulated training, biomechanics Research.
Present motion capture system, for the stability that improves system obtains to catch accurately data simultaneously, great majority all adopt motion capture system motion-captured by optical profile type and that the video camera array of taking pictures is at a high speed formed, like this, the motion-captured data that obtain for the assurance system stable and accurately, just inevitably can run into polyphaser demarcates and three-dimensional these two classic problem of coupling, also will solve the difficult problem that many camera synchronization are gathered simultaneously, this also is related to result's robustness and accuracy to a great extent.
Summary of the invention
The objective of the invention is a kind of usefulness that more is simple and easy to of proposing on the basis of conventional motion capture system, extensibility is stronger, the motion capture method based on monocular-camera and multiplane mirror catadioptric device that is easier to promote; Be intended to solve in the conventional motion capture system owing to the polyphaser demarcation of having used video camera array to cause and the difficult problem of synchro control, and then improve the precision of the monumented point coupling obtain, thereby improve the accuracy of monumented point three-dimensional reconstruction and the stability of system.
For realizing this purpose, at first utilize multiple plane mirror and monocular-camera, build data acquisition system (DAS), adjust the shooting angle and the aperture of real camera, data acquisition is carried out in the moving object of shooting area.Adopt threshold method to obtain monumented point, the application region method of filling a vacancy obtains the center of monumented point, the monumented point that obtains is carried out three-dimensional reconstruction, utilize the polar curve constraint to carry out the coupling of corresponding point, take the camera chain of ambiguousness minimum that monumented point is carried out three-dimensional reconstruction, can guarantee the stability of system to the full extent.At last, the monumented point movement locus that processing is obtained combines with three-dimensional model, carries out motion editing.
Technical scheme of the present invention following (flow process is referring to Fig. 1):
A kind of motion capture method is characterized in that,
-this method utilizes a monocular-camera and one to carry out picture catching by multiplane mirror catadioptric device;
-method for catching is as follows:
A. data pretreatment stage comprises three steps:
1) image data acquiring calculates the minute surface angle.Take pictures with 30 °～100 ° the angle of depression with video camera, in same photo, obtain the scene of different points of view simultaneously, choose the corresponding point in the different scenes, calculate the angle of scene midplane mirror;
2) demarcate real camera.Choose point corresponding in the different scenes, real video camera is carried out the demarcation of inside and outside parameter;
3) demarcate virtual video camera.Following geometric relationship is arranged between real video camera and the virtual video camera:
X
2+Y
2+Z
2＝R
2
Wherein, (X, Y are the world coordinatess of true camera and virtual camera photocentre Z), and R is a positive number, are the distance of photocentre to the minute surface intersection, that is the global proportionality factor.Owing to have only a unique true camera in all scenes, so the intrinsic parameter of every camera is all identical, that is the intrinsic parameter of true camera, utilize the true camera of above formula embodiment and the relation between the virtual camera simultaneously, just can obtain the outer parameter of every camera easily, write down the inside and outside parameter of every camera;
B. the tracking of identification point and obtaining the stage comprises a step:
4) gather moving scene data and processing.Utilize the optical profile type movement capturing technology that the data acquisition of movement locus is carried out in moving object, extract the corresponding point data in each viewpoint scene, obtain the centre coordinate of identification point;
C. three-dimensional reconstruction and exercise data edit phase comprise two steps:
5) three-dimensional coordinate of recovery identification point.Each pilot scene is carried out the registration of corresponding point data, according to the camera parameters of demarcating, the three-dimensional coordinate of restore data point and record;
6) exercise data editor.Because the human skeleton structure is structurized in itself, so, the tree structure of corresponding skeleton, selecting the position of basin bone is tree root, with the movement capturing data structuring.Set up after the tree structure, the description of whole movement capturing data is just fairly simple, and some basic constraints can lie in the structure expression that need not be explicit.Extract the key frame of movement capturing data, drive three-dimensional model.
Wherein, described multiplane mirror catadioptric device is made up of the two sides level crossing; Two level crossing minute surfaces are relative, overlook " V " word to put.
Beneficial effect of the present invention: the present invention adopts monocular-camera, make full use of the catadioptric relation between multiple plane mirror simultaneously, thoroughly solve the difficult problem of the polyphaser demarcation that faces owing to the use video camera array in traditional motion capture system and the problem of synchro control, thereby reached the purpose that improves monumented point 3-d recovery precision and system stability; Greatly reduce the cost of system simultaneously, system possesses good extensibility, makes motion-capturedly to become simple.
Description of drawings
Fig. 1 is a system flowchart of the present invention;
Fig. 2 is an apparatus structure synoptic diagram of the present invention;
Fig. 3 is the data master drawing among the embodiment.
Specific embodiments
Technical scheme for a better understanding of the present invention is described in further detail below in conjunction with accompanying drawing.
By the system flowchart of Fig. 1 as can be seen the entire process process of system form by three phases: the tracking of data pre-service, identification point and obtain, three-dimensional reconstruction and exercise data editor.
1, data pre-service
This stage comprises: the step 1) image data acquiring, calculating minute surface angle---Fig. 3 is the data master drawing, step 2) demarcation real camera and step 3) demarcation virtual video camera, the background modeling that carries out for the real-time that guarantees system in addition.
Because hardware acquisition system of the present invention is made up of monocular-camera and multiple plane mirror---as Fig. 2, so needn't consider the problem of the synchro control images acquired that relates in the camera array, the data that can directly gather moving scene.Utilize X.Ying then, K.Peng, R.Ren, H.Zha, " Geometric Properties of Multiple Reflections in Catadioptric Camera with TwoPlanar Mirrors ", to appearin I Proc.EEE Int.Conf. on Computer Vision and Pattern Recognition (CVPR ' 10), San Francisco, CA, USA, June 13-18,2010 methods, video camera is carried out inside and outside parameter demarcate, background is carried out modeling, so that the real-time of the system of assurance.
2, the tracking of identification point and obtaining
This stage comprises step 4) collection moving scene data and handles.The tracking of monumented point and the method for obtaining are: at first subtract each other with the image sequence and the background image that obtain, obtain prospect; Utilize the method for threshold value to obtain identification point again, the method for filling a vacancy with the zone obtains the center of identification point again.Many Gausses or single Gaussian distribution that utilization of the present invention is popular are in the world carried out modeling to each pixel, simultaneously with the image sequence that obtains background image updating in real time.Consider the real-time of system, background modeling is finished at the data pretreatment stage.
Specific practice is as follows:
Light-source system of the present invention adopts the LED lamp of active illuminating, and the LED lamp of the brightness that will meet the requirements pastes on subject's the clothes, carries out suitable layout to testing real photoenvironment, makes it to satisfy the illumination condition of requirement of experiment.Certain brightness range (low-light level) is adjusted in camera brightness, a show label point in the scene image that camera photographs.This will reduce the detection difficulty of monumented point greatly.The number of pixels that needs in the image to detect is directly proportional with the number of monumented point.In view of above reason, the zone that the present invention adopts simple threshold method and region growing algorithm to ask for monumented point.
Simple, effective, quick, practical through this method of experimental verification, less to the frame per second influence of camera.
Program circuit:
1) threshold value of setting monumented point.
2) will carry out region growing above the point of threshold value, generate different zones.
3) ask for (x, y) average of the coordinate center of as a token of putting in each zone.
3, three-dimensional reconstruction and exercise data editor
This stage comprises the three-dimensional coordinate and the step 6) exercise data editor of step 5) recovery identification point.When a monumented point is photographed simultaneously by at least two video cameras, the three-dimensional position of this monumented point will be well-determined.At present, the optimization method of binding in the world is based on two video cameras.The method that the present invention adopts is: when a monumented point only occurs in two viewpoint scenes, will rebuild it with traditional method; When a monumented point appears at least three viewpoint scenes, select for use three ambiguousness minimums, viewpoint scene that reliability is the highest to rebuild it.The ambiguousness minimum here is meant that this monumented point is the probability maximum of same monumented point in three viewpoint scenes.This method has effectively solved the problem that ambiguousness influences system stability.
On the other hand, images match is the classic problem in vision field always, among the present invention, because the picture material of obtaining is fairly simple, and owing to use the relation of level crossing, geometric relationship between the scene of different points of view is easy to determine according to the relation of the position between the level crossing, so the method that the present invention has only adopted polar curve to retrain is carried out coupling a little.
Exercise data and skeleton after handling are mapped, because the human skeleton structure is structurized in itself, so, the tree structure of corresponding skeleton, selecting the position of basin bone is tree root, with the movement capturing data structuring.Set up after the tree structure, the description of whole movement capturing data is just fairly simple, and some basic constraints can lie in the structure expression that need not be explicit.Use the clustering method of optimizing to extract the key frame of movement capturing data, drive three-dimensional model.
The motion capture system of using the present invention to propose, can utilize the automatic calibrating camera of feature of data itself, owing to do not use video camera array, the great difficult problem of polyphaser demarcation and the problem of synchro control have fundamentally been solved, improved the matching precision of data corresponding point greatly, made the movement locus of extraction more accurate.This method has solved movement human to a great extent from the problem of blocking in addition, utilizes the information of wherein several points to estimate and to recover in the information of blocking this point of position.The proposition of native system makes and motion-capturedly becomes more reliable and more stable, is simple and easy to use.
It should be noted that the purpose of publicizing and implementing example is to help further to understand the present invention, but it will be appreciated by those skilled in the art that: in the spirit and scope that do not break away from the present invention and claims, various substitutions and modifications all are possible.Therefore, the present invention should not be limited to the disclosed content of embodiment, and the scope of protection of present invention is as the criterion with the scope that claims define.
Claims (10)
1. a motion capture method is characterized in that,
-this method utilizes a monocular-camera and one to carry out picture catching by multiplane mirror catadioptric device;
-method for catching is as follows:
A. data pretreatment stage comprises three steps:
1) image data acquiring calculates the minute surface angle;
2) demarcate real camera;
3) demarcate virtual video camera;
B. the tracking of identification point and obtaining the stage comprises a step:
4) gather moving scene data and processing;
C. three-dimensional reconstruction and exercise data edit phase comprise two steps:
5) three-dimensional coordinate of recovery identification point;
6) exercise data editor.
2. the method for claim 1 is characterized in that, described multiplane mirror catadioptric device is made up of the two sides level crossing; Two level crossing minute surfaces are relative, overlook " V " word to put.
3. the method for claim 1, it is characterized in that the implementation method of described step 1) is: take pictures with 30 °～100 ° the angle of depression with video camera, in same photo, obtain the scene of different points of view simultaneously, choose the corresponding point in the different scenes, calculate the angle of scene midplane mirror.
4. method as claimed in claim 3 is characterized in that, described step 2) implementation method be: choose in the different scenes corresponding point, real video camera carried out the demarcation of inside and outside parameter.
5. method as claimed in claim 4 is characterized in that, the implementation method of described step 3) is:
Following geometric relationship is arranged between real video camera and the virtual video camera:
X
2+Y
2+Z
2＝R
2
Wherein, (X, Y Z) are the world coordinates of true camera and virtual camera photocentre; R is a positive number, is the distance of photocentre to the minute surface intersection; The intrinsic parameter of every camera all equals the intrinsic parameter of true camera, and formula is obtained the outer parameter of every camera above utilizing; Write down the inside and outside parameter of every camera.
6. method as claimed in claim 5, it is characterized in that, the implementation method of described step 4) is: utilize the optical profile type movement capturing technology that the data acquisition of movement locus is carried out in moving object, extract the corresponding point data in each viewpoint scene, obtain the centre coordinate of identification point.
7. method as claimed in claim 6 is characterized in that, the implementation method of described step 5) is: each pilot scene is carried out the registration of corresponding point data, according to the camera parameters of demarcating, the three-dimensional coordinate of restore data point and record.
8. method as claimed in claim 7 is characterized in that, the implementation method of described step 6) is: the tree structure of corresponding skeleton, and selecting the position of basin bone is tree root, with the movement capturing data structuring; Extract the key frame of movement capturing data, drive three-dimensional model.
9. the method for claim 1 is characterized in that, also comprises the background modeling step of carrying out for the real-time that guarantees system at the data pretreatment stage.
10. the method for claim 1 is characterized in that, the zone that utilizes threshold method and region growing algorithm to ask for monumented point, and method is as follows:
A) threshold value of setting monumented point;
B) will carry out region growing above the point of threshold value, generate different zones;
C) ask for (x, y) average of the coordinate center of as a token of putting in each zone.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010288904 CN101930628A (en) | 2010-09-21 | 2010-09-21 | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010288904 CN101930628A (en) | 2010-09-21 | 2010-09-21 | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101930628A true CN101930628A (en) | 2010-12-29 |
Family
ID=43369783
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010288904 Pending CN101930628A (en) | 2010-09-21 | 2010-09-21 | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101930628A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102184545A (en) * | 2011-06-02 | 2011-09-14 | 浙江大学 | Single-chart self-calibration method of catadioptric omnibearing camera mirror plane pose |
| CN102226691A (en) * | 2011-04-01 | 2011-10-26 | 北京大学 | Measurement method of plane mirror included angle in multiplane-mirror catadioptric system |
| CN102256061A (en) * | 2011-07-29 | 2011-11-23 | 武汉大学 | Two-dimensional and three-dimensional hybrid video stabilizing method |
| CN102261907A (en) * | 2011-04-20 | 2011-11-30 | 北京大学 | Multiple viewpoint polar geometric measuring method used in multiple flat mirror catadioptric imaging system |
| CN102750687A (en) * | 2011-09-23 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Method and device for camera parameter calibration and three-dimensional point cloud generating |
| CN103065470A (en) * | 2012-12-18 | 2013-04-24 | 浙江工业大学 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
| CN103337094A (en) * | 2013-06-14 | 2013-10-02 | 西安工业大学 | Method for realizing three-dimensional reconstruction of movement by using binocular camera |
| CN103561829A (en) * | 2011-05-31 | 2014-02-05 | 微软公司 | Action trigger gesturing |
| CN105205799A (en) * | 2014-06-10 | 2015-12-30 | 北京七鑫易维信息技术有限公司 | Device with omnibearing feature face and augmented reality three-dimensional registration system |
| CN105242689A (en) * | 2015-09-23 | 2016-01-13 | 浙江大学 | Holder tracking visual system based on optical reflection |
| CN105832342A (en) * | 2016-03-14 | 2016-08-10 | 深圳清华大学研究院 | Kinematics parameter capturing method based on visible spatial expansion of optical motion capturing system |
| CN109285213A (en) * | 2018-07-18 | 2019-01-29 | 西安电子科技大学 | Comprehensive polarization three-dimensional rebuilding method |
| CN109785364A (en) * | 2019-01-15 | 2019-05-21 | 中国第一汽车股份有限公司 | Motor vehicles user's motion profile method for catching |
| CN110514143A (en) * | 2019-08-09 | 2019-11-29 | 南京理工大学 | A kind of fringe projection system scaling method based on reflecting mirror |
| CN111602177A (en) * | 2018-12-20 | 2020-08-28 | 卡尔蔡司光学国际有限公司 | Method and apparatus for generating a 3D reconstruction of an object |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764931A (en) * | 2003-02-11 | 2006-04-26 | 索尼电脑娱乐公司 | Method and apparatus for real time motion capture |
| CN1766831A (en) * | 2004-10-29 | 2006-05-03 | 中国科学院计算技术研究所 | A kind of skeleton motion extraction method of the motion capture data based on optics |
| US20080024505A1 (en) * | 2006-07-28 | 2008-01-31 | Demian Gordon | Facs solving in motion capture |
| US20080100622A1 (en) * | 2006-11-01 | 2008-05-01 | Demian Gordon | Capturing surface in motion picture |
| JP2008522324A (en) * | 2004-12-03 | 2008-06-26 | ソニー株式会社 | System and method for capturing facial and physical movements |
| CN101228555A (en) * | 2005-07-07 | 2008-07-23 | 独创目标实验室公司 | System for 3D monitoring and analysis of motion behavior of targets |
-
2010
- 2010-09-21 CN CN 201010288904 patent/CN101930628A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1764931A (en) * | 2003-02-11 | 2006-04-26 | 索尼电脑娱乐公司 | Method and apparatus for real time motion capture |
| CN1766831A (en) * | 2004-10-29 | 2006-05-03 | 中国科学院计算技术研究所 | A kind of skeleton motion extraction method of the motion capture data based on optics |
| JP2008522324A (en) * | 2004-12-03 | 2008-06-26 | ソニー株式会社 | System and method for capturing facial and physical movements |
| CN101228555A (en) * | 2005-07-07 | 2008-07-23 | 独创目标实验室公司 | System for 3D monitoring and analysis of motion behavior of targets |
| US20080024505A1 (en) * | 2006-07-28 | 2008-01-31 | Demian Gordon | Facs solving in motion capture |
| US20080100622A1 (en) * | 2006-11-01 | 2008-05-01 | Demian Gordon | Capturing surface in motion picture |
Non-Patent Citations (9)
| Title |
|---|
| 《2010 IEEE Conference on Computer Vision and Pattern Recognition》 20100618 Xianghua Ying 等 Geometric properties of multiple reflections in catadioptric camera with two planar mirrors , * |
| 《COMPUTER VISION－ECCV 2006》 20061231 Keith Forbes 等 Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera , * |
| 《COMPUTER VISION－ECCV 2006》 20061231 Keith Forbes 等 Shape-from-Silhouette with Two Mirrors and an Uncalibrated Camera , 2 * |
| 《IEEE Computer Graphics and Applications》 20021231 I-Chen Lin等 Extracting 3D Facial Animation Parameters from Multiview Video Clips , * |
| 《IEEE Computer Graphics and Applications》 20021231 I-Chen Lin等 Extracting 3D Facial Animation Parameters from Multiview Video Clips , 2 * |
| 《中国优秀博硕士学位论文全文数据库》 20061115 叶翔宇 航天员舱内活动地面模拟实验研究 , 2 * |
| 《中国优秀硕士学位论文全文数据库（信息科技辑）》 20081215 吴玥 基于单目视频运动跟踪的三维人体动画研究 , * |
| 《中国优秀硕士学位论文全文数据库》 20090515 胡琴 基于标记点的三维人体步态捕获技术研究 , * |
| 《中国优秀硕士学位论文全文数据库》 20090515 胡琴 基于标记点的三维人体步态捕获技术研究 , 2 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102226691A (en) * | 2011-04-01 | 2011-10-26 | 北京大学 | Measurement method of plane mirror included angle in multiplane-mirror catadioptric system |
| CN102261907A (en) * | 2011-04-20 | 2011-11-30 | 北京大学 | Multiple viewpoint polar geometric measuring method used in multiple flat mirror catadioptric imaging system |
| CN103561829A (en) * | 2011-05-31 | 2014-02-05 | 微软公司 | Action trigger gesturing |
| CN102184545B (en) * | 2011-06-02 | 2012-11-07 | 浙江大学 | Single-chart self-calibration method of catadioptric omnibearing camera mirror plane pose |
| CN102184545A (en) * | 2011-06-02 | 2011-09-14 | 浙江大学 | Single-chart self-calibration method of catadioptric omnibearing camera mirror plane pose |
| CN102256061A (en) * | 2011-07-29 | 2011-11-23 | 武汉大学 | Two-dimensional and three-dimensional hybrid video stabilizing method |
| CN102256061B (en) * | 2011-07-29 | 2013-06-05 | 武汉大学 | Two-dimensional and three-dimensional hybrid video stabilizing method |
| CN102750687A (en) * | 2011-09-23 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Method and device for camera parameter calibration and three-dimensional point cloud generating |
| CN103065470A (en) * | 2012-12-18 | 2013-04-24 | 浙江工业大学 | Detection device for behaviors of running red light of vehicle based on machine vision with single eye and multiple detection faces |
| CN103337094B (en) * | 2013-06-14 | 2016-05-18 | 西安工业大学 | A kind of method of applying binocular camera and realizing motion three-dimensional reconstruction |
| CN103337094A (en) * | 2013-06-14 | 2013-10-02 | 西安工业大学 | Method for realizing three-dimensional reconstruction of movement by using binocular camera |
| CN105205799A (en) * | 2014-06-10 | 2015-12-30 | 北京七鑫易维信息技术有限公司 | Device with omnibearing feature face and augmented reality three-dimensional registration system |
| CN105205799B (en) * | 2014-06-10 | 2019-04-02 | 北京七鑫易维信息技术有限公司 | A kind of device and augmented reality three-dimensional Accreditation System with comprehensive characteristic face |
| CN105242689B (en) * | 2015-09-23 | 2019-03-26 | 浙江大学 | A kind of holder tracking vision system based on optical reflection |
| CN105242689A (en) * | 2015-09-23 | 2016-01-13 | 浙江大学 | Holder tracking visual system based on optical reflection |
| CN105832342A (en) * | 2016-03-14 | 2016-08-10 | 深圳清华大学研究院 | Kinematics parameter capturing method based on visible spatial expansion of optical motion capturing system |
| CN105832342B (en) * | 2016-03-14 | 2018-08-21 | 深圳市第二人民医院 | Kinematics parameters method for catching based on the extension of automatic Optic Motion Capture System visible space |
| CN109285213A (en) * | 2018-07-18 | 2019-01-29 | 西安电子科技大学 | Comprehensive polarization three-dimensional rebuilding method |
| CN111602177A (en) * | 2018-12-20 | 2020-08-28 | 卡尔蔡司光学国际有限公司 | Method and apparatus for generating a 3D reconstruction of an object |
| CN111602177B (en) * | 2018-12-20 | 2023-05-09 | 卡尔蔡司光学国际有限公司 | Method and apparatus for generating a 3D reconstruction of an object |
| CN109785364A (en) * | 2019-01-15 | 2019-05-21 | 中国第一汽车股份有限公司 | Motor vehicles user's motion profile method for catching |
| CN109785364B (en) * | 2019-01-15 | 2023-08-25 | 中国第一汽车股份有限公司 | Method for capturing motion track of motor vehicle user |
| CN110514143A (en) * | 2019-08-09 | 2019-11-29 | 南京理工大学 | A kind of fringe projection system scaling method based on reflecting mirror |
| US11808564B2 (en) | 2019-08-09 | 2023-11-07 | Nanjing University Of Science And Technology | Calibration method for fringe projection systems based on plane mirrors |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101930628A (en) | Monocular-camera and multiplane mirror catadioptric device-based motion capturing method | |
| CN111968129B (en) | Instant positioning and map construction system and method with semantic perception | |
| CN109166149B (en) | Positioning and three-dimensional line frame structure reconstruction method and system integrating binocular camera and IMU | |
| CN109816703B (en) | Point cloud registration method based on camera calibration and ICP algorithm | |
| CN106648103B (en) | A kind of the gesture tracking method and VR helmet of VR helmet | |
| Younes et al. | Keyframe-based monocular SLAM: design, survey, and future directions | |
| CN109636831B (en) | Method for estimating three-dimensional human body posture and hand information | |
| CN108369643B (en) | Method and system for 3D hand skeleton tracking | |
| CN104680582B (en) | A kind of three-dimensional (3 D) manikin creation method of object-oriented customization | |
| CN104463108B (en) | A kind of monocular real time target recognitio and pose measuring method | |
| CN103839277B (en) | A kind of mobile augmented reality register method of outdoor largescale natural scene | |
| CN110223383A (en) | A kind of plant three-dimensional reconstruction method and system based on depth map repairing | |
| CN109544636A (en) | A kind of quick monocular vision odometer navigation locating method of fusion feature point method and direct method | |
| CN106600627A (en) | Rigid body motion capturing method and system based on mark point | |
| CN105528082A (en) | Three-dimensional space and hand gesture recognition tracing interactive method, device and system | |
| CN105551086A (en) | Customized foot modeling and shoe pad customization method on the basis of computer vision | |
| Tung et al. | Complete multi-view reconstruction of dynamic scenes from probabilistic fusion of narrow and wide baseline stereo | |
| CN110555412A (en) | End-to-end human body posture identification method based on combination of RGB and point cloud | |
| CN114119739A (en) | Binocular vision-based hand key point space coordinate acquisition method | |
| CN103443826A (en) | Mesh animation | |
| CN110941996A (en) | Target and track augmented reality method and system based on generation of countermeasure network | |
| CN106203429A (en) | Based on the shelter target detection method under binocular stereo vision complex background | |
| TWI684956B (en) | Object recognition and tracking system and method thereof | |
| CN107038758A (en) | A kind of augmented reality three-dimensional registration method based on ORB operators | |
| CN110516639A (en) | A kind of personage's three-dimensional position real-time computing technique based on video flowing natural scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20101229 |