Design and application of fast matching method based on support points expansion

ZHOU Zi-wei; FAN Ji-zhuang; LI Ge; ZHAO Jie; ZHANG He

doi:10.3788/OPE.20132101.0207

您当前的位置：

首页 >

文章列表页 >

Design and application of fast matching method based on support points expansion

Article | 更新时间：2020-08-12

- Design and application of fast matching method based on support points expansion
- Optics and Precision Engineering Vol. 21, Issue 1, Pages: 207-216(2013)
- 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2.辽宁科技大学电子与信息工程学院
- 作者简介：
- 基金信息：
- DOI：10.3788/OPE.20132101.0207
  CLC： TP391.4
- Received：02 July 2012，
  
  Revised：12 September 2012，
  
  Published Online：24 January 2013，
  
  Published：15 January 2013
- 稿件说明：
移动端阅览
周自维樊继壮李戈赵杰张赫. 支撑点扩展快速立体匹配方法的设计与应用[J]. 光学精密工程, 2013,21(1): 207-216

ZHOU Zi-wei FAN Ji-zhuang LI Ge ZHAO Jie ZHANG He. Design and application of fast matching method based on support points expansion[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 207-216
周自维樊继壮李戈赵杰张赫. 支撑点扩展快速立体匹配方法的设计与应用[J]. 光学精密工程, 2013,21(1): 207-216 DOI： 10.3788/OPE.20132101.0207.

ZHOU Zi-wei FAN Ji-zhuang LI Ge ZHAO Jie ZHANG He. Design and application of fast matching method based on support points expansion[J]. Editorial Office of Optics and Precision Engineering, 2013,21(1): 207-216 DOI： 10.3788/OPE.20132101.0207.

摘要

为精确构建计算机立体视觉中的视差图，提出了一种快速全局优化匹配算法。该算法采用吉布斯随机场模型描述空间点与其邻域之间的关系，由改进的Graph Cuts方法对空间点的邻域进行匹配来获取场景的致密视差图。首先，计算出一组具有明确匹配关系的稀疏匹配点，将这些匹配点命名为支撑点；然后，对每一个支撑点的邻域进行扩展，采用改进的Graph Cuts全局优化算法计算扩展后的邻域空间的匹配关系，并将满足一定匹配度的邻域点设置为新的支撑点。最后，重复上述步骤并逐级扩展，直至扩展出的匹配空间覆盖整个视图，进而获取待匹配图对的致密视差图。实验结果表明，该方法不仅对不同场景视差图的质量具有良好的一致性，而且匹配速度较快(匹配时间约为0.8~1.2 s)，大大高于其他传统的全局匹配算法。为体现本文算法的实际应用价值，以Smart Eye Ⅱ立体视觉试验台为测试平台，对真实场景进行了视差图构建，取得了良好的试验效果。

Abstract

To construct a high qualitative disparity space image in stereo vision

a fast global optimal matching algorithm based on Gibbs Random Field(GRF) model was proposed. In this algorithm

the relationship between a space point and its neighborhood was described by using the GRF

and an improved Graph Cut method was used to calculate the matching relationship of the neighborhoods and to obtain the density disparity space image of a scene. Firstly

a set of matching points with distinct matching relationship was calculated

and named them as support points. Then

these support points were taken for the center and their neighborhood spaces were expanded. The improved Graph Cuts algorithm was used to match the expanded neighborhood spaces

and then set the neighborhood points that meet matching degree as new support points. Repeating the above steps and extending progressively

until the expansion of the neighborhood covered the entire the scene image and the density disparity map of the image pair was obtain finally. Experimental results show that this method has good speed consistency on the disparity map of the different scenes

and the matching time is about 0.8-1.2 s. For reflecting the practical value of the algorithm

the proposed algorithm was adopted to construct the disparity map of a real scene on the binocular vision test bed Smart Eye Ⅱ

and good reconstruction results were obtained.

关键词

Keywords

references

NALPANTIDIS L, GASTERATOS A. Stereo vision for robotic applications in the presence of non-ideal lighting conditions[J]. Image and Vision Computing, 2010, 28(5)： 940-951.[2]CRANE C D. Development of an integrated sensor system for obstacle detection and terrain evaluation for application to unmanned ground vehicles[J]. Unmanned Ground Vehicle Technology, 2005, 5084(10): 156-165.[3]SCHARSTEIN D, SZELISKI R. A taxonomy and evaluation of dense two frame stereo correspondence algorithms [J ]. Int J of Computer Vision, 2002, 47 (1) :72-42.[4]CASSISA C. Local vs global energy minimization methods: application to stereo matching[J]. PIC, 2010,14 (1) :172-180.[5]薛婷, 曹兆峰, 金俞鑫. 基于虚拟立体视觉的气液两相流三维测量系统的标定[J]. 光学精密工程, 2012, 20(1):124-130.XUE T, CAO ZH F, JIN Y X. Calibration of three-dimensional measurement system for gas-liquid two phase flow based on virtual stereo vision[J]. Opt. Precision Eng., 2012, 20(1):124-130. (in Chinese)[6]杨勇, 徐于萍, 赵星,等. 基于同名点间距变换的三维显示参数匹配[J]. 光学精密工程， 2012,20(5):1084-1089.YANG Y ,XU Y P,ZHAO X, et al.. Parameter matching of three dimensional display based on space of corresponding image point transformation[J]. Opt. Precision Eng., 2012,20(5):1084-1089. (in Chinese)[7]SUN J, LI Y, KANG S. Symmetric stereo matching for occlusion handling[C]. In CVPR, 2005, pages Ⅱ: 399-406.[8]DE-MAEZTU L, VILLANUEVA A. Stereo matching using gradient similarity and locally adaptive support-weight[J]. Pattern Recognition Letters, 2011, 32(13): 1643-1651.[9]GEMAN S, GEMAN D. Stochastic relaxation, Gibbs distribution and the bayesian restoration of Images[J]. IEEE Tans.Pattern Analysis and Machine Intelligen, 1984, 6(11):21-741.[10]NALPANTIDIS L, GASTERATOS A. Biologically and psychophysically inspired adaptive support weights algorithm for stereo correspondence[J]. Robotics and Autonomous Systems, 2010, 2(13): 62-69.[11]BOYKOV Y, VEKSLER O, ZABIH. Fast approximate energy minimization via graph cuts[C]. IEEE Intl Conf. Computer Vision, 2011, 2(21): 532-539.[12]MIYAZAKI D, MASTUSHITA Y, IKEUCHI K. Interactive shadow removal from a single image using hierarchical graph cut[C]. ACCV, 2009, VI(1),2239-2247.[13]KINDERMANN, SNELL R J. Markov Random Fields and Their Applications[M], R.I.: American Mathematical Society, 1980.[14]MANAP N, SORAHAN J. Disparity refinement based on depth image layers separation for stereo matching algorithms[J]. Telecom., Elec. Comp. Eng, 2012, 4(1)： 223-231.[15]DAHLHAUS E, JOHNSON D S. The complexity of multi way cuts[C]. ACM Symp 1992, Theory of Computing, 1992: 241-251.[16]周自维，赵杰，樊继壮,等. 基于置信传播的立体匹配并行算法研究[J]. 光学精密工程, 2011, 19(11): 2774-2781.ZHOU Z W, ZHAO J, FAN J Z, et al.. Research on fast stereo matching algorithm base on Belief Propagation[J].Opt. Precision Eng., 2011, 19(11): 2774-2781. (in Chinese)

Views

200

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Parallel stereo matching algorithm base on belief propagation

Object-level dynamic simultaneous localization and mapping method fusing object detection and optical flow

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

RGB-D SLAM method of dynamic scene based on instance segmentation and optical flow

Atrous convolution and Bilateral grid network

Related Author

ZHOU Zi-wei

FAN Ji-zhuang

ZHAO Jie

LIU Xiao-li

ZHUO Xin

LI Shuguang

WANG Chenggen

BAI Suqin

Related Institution

School of Electronics Information, Liaoning University of Science and Technology

State Key Laboratory of Robotics and System, Harbin Institute of Technology

Key Laboratory of Smart Airport Theory and System， Civil Aviation University of China

Nanjing Marine Radar Research Institute

School of Computer Science， Jiangsu University of Science and Technology

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