Stereo matching based on support points

ZHANG Xue-he; ZHAO Jie; LI Ge; HOU Zhen-xiu

doi:10.3788/OPE.20152313.0546

您当前的位置：

首页 >

文章列表页 >

Stereo matching based on support points

更新时间：2020-08-13

- Stereo matching based on support points
- Optics and Precision Engineering Vol. 23, Issue 10z, Pages: 545-552(2015)
- 作者机构：
  
  哈尔滨工业大学机器人技术与系统国家重点实验室,黑龙江哈尔滨,150080
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20152313.0546
  CLC： TP391.4
- Received：17 April 2015，
  
  Revised：19 May 2015，
  
  Published：14 November 2015
- 稿件说明：
移动端阅览
张学贺, 赵杰, 李戈等. 基于支撑点的立体匹配[J]. 光学精密工程, 2015,23(10z): 545-552

ZHANG Xue-he, ZHAO Jie, LI Ge etc. Stereo matching based on support points[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 545-552
张学贺, 赵杰, 李戈等. 基于支撑点的立体匹配[J]. 光学精密工程, 2015,23(10z): 545-552 DOI： 10.3788/OPE.20152313.0546.

ZHANG Xue-he, ZHAO Jie, LI Ge etc. Stereo matching based on support points[J]. Editorial Office of Optics and Precision Engineering, 2015,23(10z): 545-552 DOI： 10.3788/OPE.20152313.0546.

摘要

为了使立体匹配算法能够兼具较高运算效率和良好的视差匹配精度

提出一种基于稳定支撑点的立体匹配算法。该算法利用Canny最优边缘算子检测图像的边缘点作为"支撑点"

应用Delaunay三角剖分算法将整个待匹配视图划分成一系列相连的二维三角面片;然后以三角形作为匹配基元构建视差模型进行初始视差估计;最后根据三角形共用顶点的特性修正视差值

进而得到最终的视差图。使用Middlebury算法测试平台提供的立体图对算法进行了实验验证。结果表明:本文算法的定位精度高

误匹配率低

匹配时间约为1 s

视差图的匹配精度约为93%

在获取高精度视差图的同时具备良好的匹配速度

为立体匹配算法的实际应用奠定了良好的基础

在基于双目视觉的路径导航系统中也有着良好的应用前景。

Abstract

A stereo matching method based on stable support points was proposed to improve its computing speed and disparity accuracy. With the method

a canny edge operator was used to detect the edge points of the image and act them as 'supporting points. Then those points were processed by a Delaunay triangulation algorithm to divide the whole image into a series of linked triangular facets. These facets were used as matching elements to compose the basic modules to perform a rude estimation of image disparity. Finally

according to the triangular property of shared vertices

the estimated disparity was refined and the disparity map was obtained. The method was tested by Middlebury stereo pairs on the platform

Experimental results show that the time cost of the method is about 1 s and the matching accuracy is 93% as compared with ground truth map. The proposed method has higher positioning accuracy and lower error mathing rate

and improves both the computing speed and computing accuracy. It forms a steady foundation and good application prospect for robot's path planning system with stereo camera devices.

关键词

Keywords

references

SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1-3):7-42.

YOON K J, KWEON I S. Adaptive support-weight approach for correspondence search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):650-656.

MURPHY K P, WEISS Y, JORDAN M I. Loopy belief propagation for approximate inference:An empirical study[C]. Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence, Morgan Kaufmann Publishers Inc., 1999:467-475.

ROTHER C, KOLMOGOROV V, BLAKE A. Grabcut:Interactive foreground extraction using iterated graph cuts[C]. ACM Transactions on Graphics(TOG). ACM, 2004, 23(3):309-314.

周自维,樊继壮,赵杰,等.基于置信传播的立体匹配并行算法[J].光学精密工程,2011,19(11):2774-2781. ZHOU Z W, FAN J Z, ZHAO J, et al.. Parallel stereo matching algorithm base on belief propagation[J]. Opt. Precision Eng., 2011, 19(11):2774-2781.(in Chinese)

MEI X, SUN X, ZHOU M, et al.. On building an accurate stereo matching system on graphics hardware[C]. 2011 IEEE International Conference on Computer Vision Workshops(ICCV Workshops), IEEE, 2011:467-474.

GEIGER A, ROSER M, URTASUN R. Efficient Large-Scale Stereo Matching[M]. Computer Vision-ACCV 2010. Springer Berlin Heidelberg, 2011:25-38.

XIA C, YANG Y, JU R, et al.. Effective local stereo matching by extended triangular interpolation[C]. 2013 IEEE International Conference on Multimedia and Expo(ICME), 2013:1-6.

FICKEL G P, JUNG C R, MALZBENDER T, et al.. Stereo matching and view interpolation based on image domain triangulation[J]. IEEE Trans on Image Processing, 2013, 22(9):3353-3365.

FICKEL G P, JUNG C R, SAMADANI R, et al.. Stereo matching based on image triangulation for view synthesis[C]. 19th IEEE International Conference on Image Processing(ICIP), 2012:2733-2736.

MAINI R, AGGARWAL H. Study and comparison of various image edge detection techniques[J]. International Journal of Image Processing(IJIP), 2009, 3(1):1-11.

李牧,闫继红,李戈,等.自适应Canny算子边缘检测技术[J].哈尔滨工程大学学报,2007,28(9):1002-1007. LI M, YAN J H, LI G, et al.. Self-adaptive Canny operator edge detection technique[J]. Journal of Harbin Engineering University, 2007, 28(9):1002-1007.(in Chinese)

MAUR P. Delaunay triangulation in 3D[R]. Technical Report, Department of Computer Science and Engineering, University of West Bohemia, Pilsen, Czech Republic, 2002.

YOON K J, KWEON I S. Adaptive support-weight approach for correspondence search[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(4):650-656.

Views

335

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Fast stereo matching based on seed pixel propagation

Stereo matching method based on the plane constraint for lunar rover

Stereo matching method for lunar rover using the plane constraint

A Fast Stereo Matching Algorithm Based on Adaptive Window and Graph cuts

Binocular vision-based trackside pantograph anomaly detection under strong environmental noise

Related Author

HU Han-ping

ZHU Ming

LI Haichao

LI Ying

GU Zheng

Hai-chao LI

Ying LI

Zheng GU

Related Institution

Changchun University of Science and Technology

Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences

University of Chinese Academy of Sciences

Qian Xuesen Laboratory of Space Technology

2.Beijing Institute of Spacecraft System Engineering

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176855 Email：gxjmgc@ciomp.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰