CN107123156A - A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision - Google Patents
A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision Download PDFInfo
- Publication number
- CN107123156A CN107123156A CN201710140955.0A CN201710140955A CN107123156A CN 107123156 A CN107123156 A CN 107123156A CN 201710140955 A CN201710140955 A CN 201710140955A CN 107123156 A CN107123156 A CN 107123156A
- Authority
- CN
- China
- Prior art keywords
- camera
- binocular
- light source
- active light
- target
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/04—Texture mapping
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T15/00—3D [Three Dimensional] image rendering
- G06T15/50—Lighting effects
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Graphics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention discloses a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision, active light source projection arrangement is placed in the middle of binocular camera, obtain the target surface image with projected fringe respectively by binocular, the stripe information provided according to active light source projection arrangement obtains the complete disparity map of reconstruct target surface by Stereo matching, and then obtains the complete three-dimensional structure in reconstruct target 4 table surface by basic principle of triangulation.Solve conventional three-dimensional reconstructing method for reflective, the low texture of height, there are large area data void holes with complex surface object reconstruction surface the problem of.
Description
【Technical field】
The invention belongs to technical field of computer vision, and in particular to a kind of active light being combined with binocular stereo vision
Source projection three-dimensional reconstructing method.
【Background technology】
The three-dimensional reconstruction of target is the critically important research contents that computer vision imitates human vision.For texture and knot
The informative target of structure, binocular stereo vision method can obtain good quality reconstruction, but single or even tight for texture
The target lacked again, can cause to reconstruct the large area data void holes of target surface due to that can not extract effective characteristic point.And
Traditional structured-light system is on the contrary, especially for surface district flat, without obvious gray scale, texture and change in shape
Domain, obvious striations can be formed with structure light, be easy to make graphical analysis and processing, this point is entered for the target of flatter table
Row three-dimensionalreconstruction is adaptable.However, the mesh of the complex surface such as high reflective target and indent for being enriched for surface texture
Mark, the three-dimensionalreconstruction based on structure light is difficult to obtain gratifying effect.
【The content of the invention】
It is an object of the invention to provide a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision,
There is large area number for reflective, the low texture of height, with complex surface object reconstruction surface to solve conventional three-dimensional reconstructing method
The problem of according to cavity.
The present invention uses following technical scheme:A kind of active light source projection three-dimensional reconstruct being combined with binocular stereo vision
Method, active light source projection arrangement is placed in the middle of binocular camera, the object table with projected fringe is obtained respectively by binocular
Face image, the stripe information provided according to active light source projection arrangement obtains reconstruct target surface regarding completely by Stereo matching
Difference figure, and then the complete three-dimensional structure in reconstruct target 4 table surface is obtained by basic principle of triangulation.
Further, implement according to following steps:
Step 1, according to reconstruct target to left camera and right camera distance, and target to be reconstructed itself profile chi
It is very little, select suitable binocular camera parallax range to build binocular three-dimensional reconstruction system so that left camera and right camera can be same
When obtain target image;Binocular three-dimensional reconstruction system includes the left camera and right camera being set up in parallel, and is arranged on left camera
With the active light source projection arrangement in the middle of right camera;Then adjusting the focal length of left camera and right camera respectively can observe to them
To the image for clearly reconstructing target;
Step 2, the binocular three-dimensional reconstruction system progress stereo calibration to being put up in step 1, and left camera is obtained respectively
With the location parameter between the distortion parameter of right camera, and left camera and right camera;
Step 3, opening active light source projection arrangement, bar code are projected the surface of reconstruct target, and form clearly bar
Line;
Step 4, pass through left camera and right camera, obtain containing clear striped reconstruct target left images, to left and right
Two images are carried out after going to distort and correcting, and carrying out Stereo matching using SGM algorithms obtains complete disparity map, and then obtains
Take the three dimensional point cloud of reconstruct target surface.
Further, the specific method of step 2 is:Binocular camera is demarcated using Zhang Zhengyou standardizations, and obtained
The inner parameter and external parameter of left camera and right camera, and then obtain the distortion parameter of left camera and right camera, and left phase
Location parameter between machine and right camera.
Further, in step 3, bar code is that black-and-white two color contrast is high, texture variations are obvious, change frequency is high, random
The bar code of rule.
Further, the specific method of step 4 is:Stereo Matching Algorithm uses Semi-Global Block
The global algorithm of Matching half.
The beneficial effects of the invention are as follows:The active light source projection three-dimensional reconstructing method and biography being combined with binocular stereo vision
The binocular stereo vision of system compares, and traditional technique of binocular stereoscopic vision is single or even missing for the smooth texture in surface
The restoration result of target can not match due to lacking obvious characteristic point and cause the data void holes of large area, and this method is to surface light
Sliding texture is single or even target of missing can recover target surface complete three-dimensional information relatively;Compared to traditional structure
Light technology, this method to for gray scale, texture, surface configuration changes obvious target can more accurately recover its three-dimensional information,
The relative position of strict labeling projection device and camera is not needed, and only needs to once carry out one to the projection of target region
Secondary IMAQ, it is simple to operate real-time.
【Brief description of the drawings】
Fig. 1 is that binocular stereo vision is combined three-dimensional reconfiguration system hardware structure diagram with active textured light source;
Fig. 2 is that binocular stereo vision is combined three-dimensional reconfiguration system workflow diagram with active textured light source;
Fig. 3 is the binaryzation of projection without the clear structure bar code for repeating texture high-contrast;
Fig. 4 is binocular camera image-forming principle schematic diagram;
Fig. 5 is scaling board schematic diagram needed for binocular camera calibration process;
Fig. 6 a are the disparity map that embodiment is obtained;
Fig. 6 b are the disparity map obtained using traditional binocular Stereo Vision;
The three-dimensional reconstruction result that Fig. 7 a embodiments are obtained;
Fig. 7 b are the three-dimensional reconstruction result obtained using traditional binocular Stereo Vision.
Wherein, 1. left camera, 2. right cameras, 3. active light source projection arrangements, 4. reconstruct targets.
【Embodiment】
Below by drawings and examples, technical scheme is described in further detail.
The invention provides a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision, such as Fig. 1
It is shown, active light source projection arrangement is placed in the middle of binocular camera, binocular camera is the left camera 1 and right camera 2 placed side by side,
The target surface image with projected fringe is obtained respectively by left camera 1 and right camera 2, according to active light source projection arrangement 3
The stripe information of offer obtains the complete disparity map in reconstruct target 4 surface by Stereo matching, and then is surveyed by basic triangle
Measure principle and obtain the complete three-dimensional structure in reconstruct target 4 table surface.
A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision of the present invention is specifically according to following
Step is implemented:
Step 1, the distance according to reconstruct target 4 to left camera 1 and right camera 2, and target to be reconstructed 4 profile of itself
Size, selects suitable binocular camera parallax range to build binocular three-dimensional reconstruction system so that left camera 1 and right camera 2 can
To obtain target image simultaneously;The binocular three-dimensional reconstruction system includes the left camera and right camera being set up in parallel, and sets
Active light source projection arrangement in the middle of left camera 1 and right camera 2;Then adjust respectively the focal length of left camera 1 and right camera 2 to
They can observe the image for clearly reconstructing target;
So-called suitable binocular camera parallax range is exactly to allow left and right camera to increase baseline while obtain target image
Distance can improve the precision of three-dimensional reconstruction, still, and parallax range increase can cause the reduction of public view field, excessive parallax range
It may cause left and right camera can not be while obtaining target image.
Step 2, the binocular three-dimensional reconstruction system progress stereo calibration to being put up in step 1, and left camera 1 is obtained respectively
With the distortion parameter of right camera 2, and the location parameter between left camera 1 and right camera 2;Location parameter refer to left and right camera it
Between relative position, final three-dimensional reconstruction result is under using left camera lens photocentre as the coordinate system of origin.
Wherein it is possible to demarcated using Zhang Zhengyou standardizations to binocular camera, and obtain left camera 1 and right camera 2
Inner parameter and external parameter, inner parameter include principle point location, distortion factor, and external parameter includes rotation parameter, translation ginseng
Number, and then obtain the distortion parameter of left camera 1 and right camera 2, and the location parameter between left camera 1 and right camera 2.
Step 3, opening active light source projection arrangement 2, bar code are projected the surface of reconstruct target 4, and formed clearly
Striped;The bar code is that black-and-white two color contrast is high, texture variations are obvious, change frequency is high, irregular bar code.
Step 4, pass through left camera 1 and right camera 2, obtain containing clear striped reconstruct target left images, to a left side
Right two images are carried out after going to distort and correcting, and carrying out Stereo matching using SGM algorithms obtains complete disparity map, and then
Obtain the three dimensional point cloud of reconstruct target surface.Wherein, Stereo Matching Algorithm can use Semi-Global Block
The global algorithm of Matching half, can further improve the accuracy of left and right camera image Stereo matching, it is accurate and complete to obtain
Whole disparity map, and then recover the three dimensional point cloud of target surface.
In the inventive solutions, three-dimensionalreconstruction is mainly big by binocular solid camera model and fringe projection module two
Module is constituted.The three-dimensionalreconstruction principle of binocular stereo vision is as shown in figure 4, wherein baseline distance B is the projection centre of two video cameras
The distance of line;Camera focus is f.If two video cameras watch the same characteristic point P (x of space object in synchronizationc,yc,
zc), point P image is obtained on " left camera image " and " right camera image " respectively, their image coordinate is respectively pleft
=(Xleft,Yleft), pright=(Xright,Yright)。
The image of existing two video cameras is in approximately the same plane, then characteristic point P image coordinate Y-coordinate is identical, i.e. Yleft=
Yright=Y, then obtained by triangle geometrical relationship:
Then parallax is:Disparity=Xleft-Xright.Thus three-dimensionals of the characteristic point P under camera coordinates system can be calculated
Coordinate is:
Therefore, as long as any point in left camera image planes can find corresponding match point in right camera image planes, so that it may
To determine the three-dimensional coordinate of the point.This method be in complete point-to-point computing, image planes institute a little simply by the presence of corresponding
Match point, it is possible to participate in above-mentioned computing, so as to obtain its corresponding three-dimensional coordinate.
The present invention is first turned on DC light source projection arrangement in specific operating process, by binaryzation without repetition texture
The clear structure bar pattern of high-contrast projects to target object, the camera exposure time is adjusted, if still there is large area
Credit light, then clearly stripe pattern can extremely be collected by adjusting the brightness of light source;When occurring clearly projecting bar on target object
After line, triggering binocular camera makes left and right camera synchronize collection to target image;Obtain the left and right camera figure of synchronization
As after, carry out denoising successively to left and right camera image according to basic procedure as shown in Figure 2, go to distort, correct and ask for
Disparity map, is finally completed the three-dimensional reconstruction of target surface.
Embodiment:
The light source that this embodiment is used is the adjustable light source of direct current brightness, and the computer used includes IMAQ
Software, the model of computer is Lenovo Qitian M7300, and CCD camera regards MV-1300 using dimension, and the parallax range of binocular camera is
To being placed in parallel before 10cm, the optical axis of binocular camera.
The Binocular Stereo Vision System put up is demarcated using gridiron pattern scaling board as shown in Figure 5.Obtain mark
Fixed number carries out three-dimensional reconstruction according to flow as shown in Figure 2 after to reconstruct target 4.To cover the satellite mould of heat control material
Experimentation analysis is carried out exemplified by type.Active light source projection arrangement 2 is opened, result striped as shown in Figure 3 is transmitted to target
Surface.First the pretreatment such as image denoising is carried out to the left and right camera image collected, then obtaining according to camera calibration
Distortion factor, left camera 1 and the location parameter of right camera 2 carry out image and remove distortion and image rectification, are obtained finally by Stereo matching
To disparity map.As shown in Figure 6 a, left figure is the disparity map that the inventive method is obtained, and surface parallax information is complete, is reflected continuous
The depth information of change;Fig. 6 b are the disparity map that traditional binocular Stereo Vision is obtained, and occur in that large area parallax data
Lose, the loss of data will necessarily influence the integrality of final reconstructed results, and then pass through principle of triangulation as shown in Figure 4
The three-dimensional coordinate information of target surface is obtained, reconstructed results are that three-dimensional rebuilding method proposed by the present invention is rebuild as shown in Figure 7a
As a result, it is possible to obtain the complete three-dimensional information of target surface;Fig. 7 b are traditional binocular Stereo Vision three-dimensional reconstruction result,
The part of parallax data missing occurs in that the data void holes of large area, has had a strong impact on the integrality of restoration result.
Three-dimensionalreconstruction basic procedure based on binocular stereo vision is followed successively by camera calibration, IMAQ, image preprocessing
With feature extraction, Stereo matching, depth calculation etc..Wherein, common feature mainly has point-like character, wire in characteristic extraction procedure
Feature and provincial characteristics etc..Extraction is supplied without obvious feature in addition to edge for the smooth low texture object in surface, left and right is caused
There was only a small amount of characteristic point successful match in image so that substantial amounts of data void holes occurs in reconstruction result.It is traditional based on structure
The intensity of the target three-dimensional reconstruction heavy dependence target surface reflected light of light, can not obtain for high reflective target and clearly project
Stripe pattern, and then influence the integrality of reconstructed results.
For traditional Three Dimensional Reconfiguration based on structure light and binocular stereo vision is smooth to surface, texture is single very
To the deficiency of the high reflective target restoration result of serious loss, a kind of active textured light source and binocular stereo vision phase are devised
With reference to three-dimensional reconstruction method, be related to the hardware modules such as binocular camera, active projection light source, can realize to reflective, the low line of height
Reason, the recovery with complex surface shape objects Complete three-dimensional surface information.Black-and-white two color contrast height, texture variations are bright
The aobvious, surface that change frequency is high, irregular striped active light source projects the smooth target of texture-free can be binocular solid
With substantial amounts of characteristic point is provided, the information of complete target surface can be obtained by intensive Feature Points Matching.Based on binocular
The extraction process of the target three-dimensional reconstruction characteristic point of stereoscopic vision is carried out on gray level image, selects black and white two-value
Striped can effectively improve the contrast for obtaining image, obtain clearly stripe pattern.The stripe information conversion of high frequency can be with
More characteristic points are provided, intensive characteristic point helps to rebuild the integrality of target surface.Select irregular striped can
The characteristic point error hiding probability that effectively reduction is caused due to texture repetition, obtains more accurate depth information at characteristic point.Use direct current
Light source is as projection light source, and the texture that can shorten the camera exposure time and adjust the brilliance control target image of light source is bright
Degree, so as to obtain the characteristic information on surface, will not cause the frequency acquisition and projecting apparatus of camera because of the shortening of CCD time for exposure
Brush frequency produce interference, so as to influence the quality of IMAQ.In addition, for the larger target of surface undulation, based on binocular
The three-dimensional reconstruction method of stereoscopic vision, which is different from traditional method of structured light, can still obtain good effect.
Claims (5)
1. a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision, it is characterised in that in binocular phase
Active light source projection arrangement (3) is placed in the middle of machine, the target surface image with projected fringe is obtained respectively by binocular, according to
The stripe information that active light source projection arrangement (3) is provided obtains the complete disparity map in reconstruct target (4) surface by Stereo matching,
And then the complete three-dimensional structure in reconstruct target 4 table surface is obtained by basic principle of triangulation.
2. a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision as claimed in claim 1, its
It is characterised by, implements according to following steps:
Step 1, the distance according to reconstruct target (4) to left camera (1) and right camera (2), and target to be reconstructed (4) itself
Appearance and size, selects suitable binocular camera parallax range to build binocular three-dimensional reconstruction system so that left camera (1) and right phase
Machine (2) can obtain target image simultaneously;The binocular three-dimensional reconstruction system includes the left camera and right camera being set up in parallel, with
And it is arranged on the active light source projection arrangement in the middle of left camera (1) and right camera (2);Then left camera (1) and the right side are adjusted respectively
The focal length of camera (2) can observe the image for clearly reconstructing target to them;
Step 2, carry out stereo calibration to the binocular three-dimensional reconstruction system put up in step 1, and obtain respectively left camera (1) and
The distortion parameter of right camera (2), and the location parameter between left camera (1) and right camera (2);
Step 3, opening active light source projection arrangement (3), bar code are projected the surface of reconstruct target (4), and formed clearly
Striped;
Step 4, pass through left camera (1) and right camera (2), obtain containing clear striped reconstruct target left images, to a left side
Right two images are carried out after going to distort and correcting, and carrying out Stereo matching using SGM algorithms obtains complete disparity map, and then
Obtain the three dimensional point cloud of reconstruct target surface.
3. its spy of a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision as claimed in claim 2
Levy and be, the specific method of described step two is:Binocular camera is demarcated using Zhang Zhengyou standardizations, and obtains left phase
The inner parameter and external parameter of machine (1) and right camera (2), and then obtain the distortion parameter of left camera (1) and right camera (2),
And the location parameter between left camera (1) and right camera (2).
4. its spy of a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision as claimed in claim 2
Levy and be, in the step 3, the bar code is that black-and-white two color contrast is high, texture variations are obvious, change frequency is high, irregular
Bar code.
5. its spy of a kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision as claimed in claim 2
Levy and be, the specific method of described step four is:Stereo Matching Algorithm is using Semi-Global Block Matching half
A global algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710140955.0A CN107123156A (en) | 2017-03-10 | 2017-03-10 | A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710140955.0A CN107123156A (en) | 2017-03-10 | 2017-03-10 | A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107123156A true CN107123156A (en) | 2017-09-01 |
Family
ID=59717980
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710140955.0A Pending CN107123156A (en) | 2017-03-10 | 2017-03-10 | A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107123156A (en) |
Cited By (21)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992868A (en) * | 2017-11-15 | 2018-05-04 | 辽宁警察学院 | A kind of High Precision Stereo footprint Quick Acquisition method |
CN108288292A (en) * | 2017-12-26 | 2018-07-17 | 中国科学院深圳先进技术研究院 | A kind of three-dimensional rebuilding method, device and equipment |
CN109146837A (en) * | 2018-06-13 | 2019-01-04 | 中车青岛四方机车车辆股份有限公司 | A kind of image capture device, defect detecting system and the method for wheel contact surface |
CN109373904A (en) * | 2018-12-17 | 2019-02-22 | 石家庄爱赛科技有限公司 | 3D vision detection device and 3D vision detection method |
CN109584183A (en) * | 2018-12-05 | 2019-04-05 | 吉林大学 | A kind of laser radar point cloud goes distortion method and system |
CN110012195A (en) * | 2019-03-18 | 2019-07-12 | 深圳奥比中光科技有限公司 | It is a kind of to reduce the method, apparatus and terminal device that depth camera is interfered |
CN110907457A (en) * | 2019-12-19 | 2020-03-24 | 长安大学 | Aggregate morphological feature detection system and method based on 3D point cloud data |
CN110930323A (en) * | 2019-11-07 | 2020-03-27 | 华为技术有限公司 | Method and device for removing light reflection of image |
CN111121722A (en) * | 2019-12-13 | 2020-05-08 | 南京理工大学 | Binocular three-dimensional imaging method combining laser dot matrix and polarization vision |
CN111508012A (en) * | 2019-01-31 | 2020-08-07 | 先临三维科技股份有限公司 | Method and device for line stripe mismatching detection and three-dimensional reconstruction |
CN111640156A (en) * | 2020-05-26 | 2020-09-08 | 中国地质大学(武汉) | Three-dimensional reconstruction method, equipment and storage equipment for outdoor weak texture target |
CN112033283A (en) * | 2020-08-07 | 2020-12-04 | 苏州天麓智能科技有限责任公司 | Turnout measuring method and device based on binocular vision imaging system |
CN112365585A (en) * | 2020-11-24 | 2021-02-12 | 革点科技(深圳)有限公司 | Binocular structured light three-dimensional imaging method based on event camera |
CN112508999A (en) * | 2020-11-20 | 2021-03-16 | 西北工业大学深圳研究院 | Space target motion state identification method based on cooperative observation image sequence |
CN112837411A (en) * | 2021-02-26 | 2021-05-25 | 由利(深圳)科技有限公司 | Method and system for realizing three-dimensional reconstruction of movement of binocular camera of sweeper |
CN113052898A (en) * | 2021-04-08 | 2021-06-29 | 四川大学华西医院 | Point cloud and strong-reflection target real-time positioning method based on active binocular camera |
CN113655064A (en) * | 2021-08-11 | 2021-11-16 | 合肥工业大学 | Appearance defect multi-mode visual detection sensor |
CN114252024A (en) * | 2020-09-20 | 2022-03-29 | 浙江四点灵机器人股份有限公司 | Single-measurement-module multi-working-mode workpiece three-dimensional measurement device and method |
CN114295516A (en) * | 2021-11-18 | 2022-04-08 | 煤炭科学研究总院 | Material density measuring method and device |
CN114404084A (en) * | 2022-01-21 | 2022-04-29 | 北京大学口腔医学院 | Scanning device and scanning method |
CN115451866A (en) * | 2022-08-12 | 2022-12-09 | 湖北工业大学 | High-light-reflection surface three-dimensional measurement method based on light field equivalent camera array model |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102062588A (en) * | 2009-11-11 | 2011-05-18 | 中国科学院沈阳自动化研究所 | Computer binocular vision denture scanning device and three-dimensional reconstruction method thereof |
CN104240294A (en) * | 2014-09-28 | 2014-12-24 | 华南理工大学 | Three-dimensional reconstruction method on basis of binocular single vision field |
US20160328601A1 (en) * | 2014-04-25 | 2016-11-10 | Tencent Technology (Shenzhen) Company Limited | Three-dimensional facial recognition method and system |
-
2017
- 2017-03-10 CN CN201710140955.0A patent/CN107123156A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102062588A (en) * | 2009-11-11 | 2011-05-18 | 中国科学院沈阳自动化研究所 | Computer binocular vision denture scanning device and three-dimensional reconstruction method thereof |
US20160328601A1 (en) * | 2014-04-25 | 2016-11-10 | Tencent Technology (Shenzhen) Company Limited | Three-dimensional facial recognition method and system |
CN104240294A (en) * | 2014-09-28 | 2014-12-24 | 华南理工大学 | Three-dimensional reconstruction method on basis of binocular single vision field |
Non-Patent Citations (5)
Title |
---|
(意)法比奥•雷蒙蒂诺等: "《飞行时间测距成像相机》", 31 August 2016, 《国防工业出版社》 * |
刘江等: "光栅投影双目立体视觉测量方法的研究", 《组合机床与自动化加工技术》 * |
刘芳芳: "基于伪随机编码结构光的三维重建技术研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
徐进军: "《工业测量技术与数据处理》", 28 February 2014, 武汉大学出版社 * |
汪懋华等: "《现代精细农业理论与实践》", 31 October 2012, 中国农业大学出版社 * |
Cited By (29)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107992868A (en) * | 2017-11-15 | 2018-05-04 | 辽宁警察学院 | A kind of High Precision Stereo footprint Quick Acquisition method |
CN108288292A (en) * | 2017-12-26 | 2018-07-17 | 中国科学院深圳先进技术研究院 | A kind of three-dimensional rebuilding method, device and equipment |
CN109146837A (en) * | 2018-06-13 | 2019-01-04 | 中车青岛四方机车车辆股份有限公司 | A kind of image capture device, defect detecting system and the method for wheel contact surface |
CN109584183A (en) * | 2018-12-05 | 2019-04-05 | 吉林大学 | A kind of laser radar point cloud goes distortion method and system |
CN109373904A (en) * | 2018-12-17 | 2019-02-22 | 石家庄爱赛科技有限公司 | 3D vision detection device and 3D vision detection method |
CN111508012A (en) * | 2019-01-31 | 2020-08-07 | 先临三维科技股份有限公司 | Method and device for line stripe mismatching detection and three-dimensional reconstruction |
CN111508012B (en) * | 2019-01-31 | 2024-04-19 | 先临三维科技股份有限公司 | Method and device for line stripe mismatching detection and three-dimensional reconstruction |
CN110012195A (en) * | 2019-03-18 | 2019-07-12 | 深圳奥比中光科技有限公司 | It is a kind of to reduce the method, apparatus and terminal device that depth camera is interfered |
CN110012195B (en) * | 2019-03-18 | 2021-07-06 | 奥比中光科技集团股份有限公司 | Method and device for reducing interference on depth camera, terminal equipment and storage medium |
CN110930323A (en) * | 2019-11-07 | 2020-03-27 | 华为技术有限公司 | Method and device for removing light reflection of image |
CN110930323B (en) * | 2019-11-07 | 2023-09-12 | 华为技术有限公司 | Method and device for removing reflection of image |
CN111121722A (en) * | 2019-12-13 | 2020-05-08 | 南京理工大学 | Binocular three-dimensional imaging method combining laser dot matrix and polarization vision |
CN110907457A (en) * | 2019-12-19 | 2020-03-24 | 长安大学 | Aggregate morphological feature detection system and method based on 3D point cloud data |
CN111640156A (en) * | 2020-05-26 | 2020-09-08 | 中国地质大学(武汉) | Three-dimensional reconstruction method, equipment and storage equipment for outdoor weak texture target |
CN112033283A (en) * | 2020-08-07 | 2020-12-04 | 苏州天麓智能科技有限责任公司 | Turnout measuring method and device based on binocular vision imaging system |
CN114252024B (en) * | 2020-09-20 | 2023-09-01 | 浙江四点灵机器人股份有限公司 | Single-measurement-module multi-working-mode workpiece three-dimensional measurement device and method |
CN114252024A (en) * | 2020-09-20 | 2022-03-29 | 浙江四点灵机器人股份有限公司 | Single-measurement-module multi-working-mode workpiece three-dimensional measurement device and method |
CN112508999A (en) * | 2020-11-20 | 2021-03-16 | 西北工业大学深圳研究院 | Space target motion state identification method based on cooperative observation image sequence |
CN112508999B (en) * | 2020-11-20 | 2024-02-13 | 西北工业大学深圳研究院 | Space target motion state identification method based on collaborative observation image sequence |
CN112365585A (en) * | 2020-11-24 | 2021-02-12 | 革点科技(深圳)有限公司 | Binocular structured light three-dimensional imaging method based on event camera |
CN112365585B (en) * | 2020-11-24 | 2023-09-12 | 革点科技(深圳)有限公司 | Binocular structured light three-dimensional imaging method based on event camera |
CN112837411A (en) * | 2021-02-26 | 2021-05-25 | 由利(深圳)科技有限公司 | Method and system for realizing three-dimensional reconstruction of movement of binocular camera of sweeper |
CN113052898B (en) * | 2021-04-08 | 2022-07-12 | 四川大学华西医院 | Point cloud and strong-reflection target real-time positioning method based on active binocular camera |
CN113052898A (en) * | 2021-04-08 | 2021-06-29 | 四川大学华西医院 | Point cloud and strong-reflection target real-time positioning method based on active binocular camera |
CN113655064B (en) * | 2021-08-11 | 2023-08-08 | 合肥工业大学 | Appearance defect multimode visual detection sensor |
CN113655064A (en) * | 2021-08-11 | 2021-11-16 | 合肥工业大学 | Appearance defect multi-mode visual detection sensor |
CN114295516A (en) * | 2021-11-18 | 2022-04-08 | 煤炭科学研究总院 | Material density measuring method and device |
CN114404084A (en) * | 2022-01-21 | 2022-04-29 | 北京大学口腔医学院 | Scanning device and scanning method |
CN115451866A (en) * | 2022-08-12 | 2022-12-09 | 湖北工业大学 | High-light-reflection surface three-dimensional measurement method based on light field equivalent camera array model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107123156A (en) | A kind of active light source projection three-dimensional reconstructing method being combined with binocular stereo vision | |
CN110288642B (en) | Three-dimensional object rapid reconstruction method based on camera array | |
US11354840B2 (en) | Three dimensional acquisition and rendering | |
CN107945268B (en) | A kind of high-precision three-dimensional method for reconstructing and system based on binary area-structure light | |
WO2016188068A1 (en) | Method and system for stereoscopic vision three-dimensional measurement taking computing laser speckles as texture | |
CN103971408B (en) | Three-dimensional facial model generating system and method | |
Luo et al. | Multi-view hair capture using orientation fields | |
CN107167093B (en) | A kind of the combined type measuring system and measurement method of laser line scanning and shadow Moire | |
CN110264567A (en) | A kind of real-time three-dimensional modeling method based on mark point | |
CN111028295A (en) | 3D imaging method based on coded structured light and dual purposes | |
CN109919876A (en) | A kind of true face model building of three-dimensional and three-dimensional true face photographic system | |
CN108592824A (en) | A kind of frequency conversion fringe projection structural light measurement method based on depth of field feedback | |
CN106920263B (en) | Undistorted integration imaging 3 D displaying method based on Kinect | |
CN108151671A (en) | A kind of 3 D digital imaging sensor, 3 D scanning system and its scan method | |
CN110230998A (en) | A kind of fast precise method for three-dimensional measurement and device based on line laser and binocular camera | |
CN103971409A (en) | Measuring method for foot three-dimensional foot-type information and three-dimensional reconstruction model by means of RGB-D camera | |
CN109242954A (en) | Multi-view angle three-dimensional human body reconstruction method based on template deformation | |
Cao et al. | Sparse photometric 3D face reconstruction guided by morphable models | |
CN104408762A (en) | Method for obtaining object image information and three-dimensional model by using monocular unit and two-dimensional platform | |
CN108182722B (en) | Real projective image generation method for three-dimensional object edge optimization | |
CN105029691B (en) | A kind of cigarette void-end detection method based on three-dimensional reconstruction | |
CN106170086B (en) | Method and device thereof, the system of drawing three-dimensional image | |
CN112595263A (en) | Binocular vision three-dimensional point cloud reconstruction measuring method for sinusoidal grating and speckle mixed pattern projection | |
CN106203429A (en) | Based on the shelter target detection method under binocular stereo vision complex background | |
CN110910431A (en) | Monocular camera-based multi-view three-dimensional point set recovery method |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170901 |
|
RJ01 | Rejection of invention patent application after publication |