基于置信传播的立体匹配并行算法

周自维; 樊继壮; 赵杰; 刘晓丽

doi:10.3788/OPE.20111911.2774

您当前的位置：

首页 >

文章列表页 >

基于置信传播的立体匹配并行算法

信息科学 | 更新时间：2020-08-12

- 基于置信传播的立体匹配并行算法
- Parallel stereo matching algorithm base on belief propagation
- 光学精密工程 2011年19卷第11期页码：2774-2781
- 作者机构：
  
  1. 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
  2. 辽宁科技大学电信学院,辽宁鞍山,114044
- 作者简介：
- 基金信息：
  
  国家高技术研究发展计划资助项目(No.2007AA041501)();哈尔滨市科技创新人才研究专向基金资助项目(No.2008RFQXG051)();哈尔滨工业大学科研
- DOI：10.3788/OPE.20111911.2774
  中图分类号： TP391.4
- 收稿日期：2011-05-23，
  
  修回日期：2011-06-27，
  
  网络出版日期：2011-11-25，
  
  纸质出版日期：2011-11-25
- 稿件说明：
移动端阅览
周自维, 樊继壮, 赵杰, 刘晓丽. 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 Zi-wei, FAN Ji-zhuang, ZHAO Jie, LIU Xiao-li. Parallel stereo matching algorithm base on belief propagation[J]. Editorial Office of Optics and Precision Engineering, 2011,19(11): 2774-2781
周自维, 樊继壮, 赵杰, 刘晓丽. 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 DOI： 10.3788/OPE.20111911.2774.

ZHOU Zi-wei, FAN Ji-zhuang, ZHAO Jie, LIU Xiao-li. Parallel stereo matching algorithm base on belief propagation[J]. Editorial Office of Optics and Precision Engineering, 2011,19(11): 2774-2781 DOI： 10.3788/OPE.20111911.2774.

摘要

考虑在双目立体视觉匹配算法中置信传播算法虽然能获得较好的视差图但匹配速度较慢

本文提出了一种基于置信传播的并行匹配方法。该方法以置信传播为基础

采用并行机制来提高匹配速度。首先

利用最优边缘算法计算图像中的边缘信息;然后

利用边缘信息将整个待匹配视图切割成若干小的区域

使用OpenMP多核优化算法并行对各个小区域进行匹配;最后

合并出整个视差图。使用Meddlebury测试平台提供的立体图对进行了实验。结果表明

在保证匹配准确率的前提下

置信传播算法将匹配速度提高了3.51倍

为立体匹配的实际应用奠定良好的基础。该方法在具备多核处理器的嵌入系统中也有良好的应用前景。

Abstract

In this paper

a parallel stereo matching algorithm is proposed based on belief propagation algorithm to accelerate the matching speed. Firstly

the edge of the image is calculated using an optimized edge computing method

then the image to be matched is cut into several segments by the edge information

and every segment is matched based on belief propagation algorithm in parallel time. Finally

all the segment are assembled into a whole disparity image. The experimental results show that the matching speed has accelerated by 3.51 times that of traditional one in the same disparity quantity

and this method can lay the foundation for the further real-time application.

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, 2010,17(2):1172-1180.[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 VII , 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):42-72.[4] CASSISA C. Local vs global energy minimization methods: application to stereo matching[J]. PIC, 2010,21(1):4211-4221.[5] 王昕,马岩,杨剑,等. 区域立体匹配算法的实现及改进[J]. 光电精密工程,2008,16(10):2002-2007. WANG X, MA Y, YANG J, et al.. Implementation and improvement of area-based stereo matching algorithm [J].Opt.Precision Eng., 2008,16(10):2002-2007.(in Chinese)[6] 白明,庄严,王伟. 采用多级动态规划实现立体匹配[J]. 光学精密工程,2008,23(7):722-729. BAI M, ZHUANG Y, WANG W. Stereo correspondence using multi-stage dynamic programming [J].Opt.Precision Eng., 2008,23(7):722-729.(in Chinese)[7] GUPTA R, CHO S Y. Real-time stereo matching using adaptive binary window[J]. DPVT, 2010,28(2):422-432.[8] YOON K J. Adaptive support-weight approach for correspondence search[J]. IEEE Transactions On Pattern Analysis And Machine Intelligence, 2006,28(4):650-657.[9] SUN J, LI Y, KANG S. Symmetric stereo matching for occlusion handling . CVPR, 2005:399-406.[10] GEMAN S, GEMAN D. Stochastic relaxation, gibbs distribution,and the Bayesian restoration of Images[J]. IEEE Tans.Pattern Analysis and Machine Intelligence, 1984,6:721-741.[11] SWENDSON R H, WANG J. Nonuniversal critical dynamics in Monte Carlo simulation[J]. Physical Rec. Letters, 1987,58(2):86-98.[12] BOYKOV Y, VEKSLER O, ZABIN R. Fast Approximate Energy Minimization Via Graph Cuts . Proc. IEEE Int'l Conf. Computer Vision, 2001,1:532-539.[13] KOLMOGOROV V, ZABIN R. Computing visual correspondence with occlusions using graph cuts . Proc. IEEE Int'l Conf. Computer Vision, 2001,(5):327-333.[14] MIYAZAKI D, MATSUSHITA Y, IKEUCHI K. Interactive shadow removal from a single image using hierarchical graph cut[J]. ACCV, 2009,33(5):1232-1243.[15] SUN J, ZHENG N, SHUM H. Stereo matching using beliefpropagation , ECCV, 2002: 510.[16] YANG Q, WANG L, AHUJA N. et al.. A constant-space belief propagation algorithm for stereo matching[J]. CVPR, 2010,22(4):465-474.[17] 卢阿丽,唐振民. 一种基于自适应窗口和图切割的快速立体匹配算法[J]. 光学精密工程,2009,17(9):2328-2334. LUA l,TANG ZH M. Fast stereo matching algorithm based on adaptive window and graph cuts [J].Opt.Precision Eng., 2009,17(9):2328-2334.(in Chinese)[18] JUDEA P. Probabilistic reasoning in intelligent systems: networks of plausible inference[J]. Morgan Kaufmann Publishers, 1988,31(1):534-541.[19] BLACK M J, RANGARAJAN A. On the unification of line processes, outlier rejection,and robust statistics with applications in early vision[J]. IJCV, 1996,19(1):57-91.

浏览量

629

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

支撑点扩展快速立体匹配方法的设计与应用

强环境噪声下的双目视觉受电弓轨旁异常检测

空洞卷积和双边格网的立体匹配网络

基于城市遥感卫星影像对的立体匹配

利用平面约束的月球车立体匹配方法