基于改进Patchmatch及切片采样粒子置信度传播的立体匹配算法

doi:10.12068/j.issn.1005-3026.2016.05.001

东北大学学报:自然科学版 ›› 2016, Vol. 37 ›› Issue (5): 609-613.DOI: 10.12068/j.issn.1005-3026.2016.05.001

• 信息与控制 • 下一篇

基于改进Patchmatch及切片采样粒子置信度传播的立体匹配算法

李晶皎¹，马利^1,2，王爱侠¹，马帅²

(1. 东北大学信息科学与工程学院，辽宁沈阳110819； 2. 辽宁大学信息学院，辽宁沈阳110036)

收稿日期:2015-04-07 修回日期:2015-04-07 出版日期:2016-05-15 发布日期:2016-05-13
通讯作者: 李晶皎
作者简介:李晶皎(1964-)，女，辽宁沈阳人，东北大学教授，博士生导师.
基金资助:
辽宁省教育厅科学研究项目(L2012003); 沈阳市科技局项目(F12277181).

Stereo Matching Algorithm Based on Improved Patchmatch and Slice Sampling Particle Belief Propagation

LI Jing-jiao¹， MA Li^1,2， WANG Ai-xia¹， MA Shuai²

1.School of Information Science & Engineering， Northeastern University， Shenyang 110819， China; 2. School of Information， Liaoning University， Shenyang 110036， China.

Received:2015-04-07 Revised:2015-04-07 Online:2016-05-15 Published:2016-05-13
Contact: MA Li
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对立体匹配时视差不连续区、倾斜平面及非前向平行平面误匹配较高的问题，提出了一种基于改进Patchmatch及切片采样粒子置信度的立体匹配算法.定义了具有边缘特性的Patchmatch相似性函数，并建立基于Patchmatch的非前向平行平面视差平面估计模型.利用粒子置信度传播代替原有的最近邻搜索，使用较少的粒子近似目标分布，并采用切片采样马尔可夫链蒙特卡罗方法解决传播过程中粒子重采样更新问题.Middlebury图像数据集测试表明，该算法能够降低视差不连续区域的误匹配，有效地提高了倾斜平面及非前向平行平面图像的匹配精度.

关键词: 立体匹配, Patchmatch, 粒子置信度传播, 切片采样, 马尔可夫链蒙特卡罗

Abstract: The high erroneous results of the stereo matching occur at the following three cases where there are depth discontinuity region， the slanted surface or the non-fronto-parallel surface. A stereo matching algorithm was proposed based on the improved Patchmatch and slice sampling particle belief propagation. An edge-preserving similarity function of the Patchmatch was defined. Then， a model of the depth estimation for the non-fronto-parallel surface was introduced. The nearest neighbor search was replaced with the particle belief propagation， and the target distribution was approximated with a finite set of particles. At the same time， the sampled particles from the belief distribution was typically done by using slice sampling Markov chain Monte Carlo method to solve the particle update problem. The experiments on the Middlebury indicate that the mismatching at the depth discontinuity region can be reduced， and the match accuracy for the slanted surface and the non-fronto-parallel surface can be improved.

Key words: stereo matching, Patchmatch, particle belief propagation, slice sampling, Markov chain Monte Carlo

中图分类号:

TP391

李晶皎，马利，王爱侠，马帅. 基于改进Patchmatch及切片采样粒子置信度传播的立体匹配算法[J]. 东北大学学报:自然科学版, 2016, 37(5): 609-613.

LI Jing-jiao， MA Li， WANG Ai-xia， MA Shuai. Stereo Matching Algorithm Based on Improved Patchmatch and Slice Sampling Particle Belief Propagation[J]. Journal of Northeastern University Natural Science, 2016, 37(5): 609-613.

参考文献

[1]Scharstein D，Szeliski R.A taxonomy and evaluation of dense two-frame stereo correspondence algorithms［J］.International Journal of Computer Vision，2002，47 (1/2/3):7-42.
[2]Wang Z F，Zheng Z G.A region based stereo matching algorithm using cooperative optimization ［C］// IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Anchorage，2008:1-8.
[3]Damjanovic S，Heijden F，Spreeuwers L J.Local stereo matching using adaptive local segmentation［J］.International Scholarly Research Notices Machine Vision，2012(2012):1-15.
[4]Bleyer M，Rhemann C，Rother C.Patchmatch stereo-stereo matching with slanted support windows［J］.British Machine Vision Conference，2011，14:1-11.
[5]Lu J，Yang H，Min D，et al.Patch match filter:efficient edge-aware filtering meets randomized search for fast correspondence field estimation［J］.IEEE Computer Society Conference on Computer Vision and Pattern Recognition，2013，9(4):1854-1861.
[6]Besse F，Rother C，Fitzgibbon A，et al.PMBP:patch match belief propagation for correspondence field estimation［J］.International Journal of Computer Vision，2014，110(1):2-13.
[7]Muller O，Yang M Y，Rosenhahn B.Slice sampling particle belief propagation［C］// IEEE International Conference on Computer Vision.Sydney，2013:1129-1136.
[8]Trinh H，Mcallester D.Particle-based belief propagation for structure from motion and dense stereo vision with unknown camera constraints［M］.Berlin:Springer，2008:16-28.
[9]Kothapa R.Max-product particle belief propagation［D］.Rhode Island:Brown University，2011.
[10]Heise P，Klose S，Jensen B，et al.PM-Huber:patch match with huber regularization for stereo matching［C］// IEEE International Conference on Computer Vision.Sydney，2013:2360-2367.

基于改进Patchmatch及切片采样粒子置信度传播的立体匹配算法

Stereo Matching Algorithm Based on Improved Patchmatch and Slice Sampling Particle Belief Propagation

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 3

编辑推荐

Metrics

本文评价

[1]	庞彦伟，苏畅，龙涛. 自适应构造与聚合多尺度代价体的双目立体匹配[J]. 东北大学学报（自然科学版）, 2023, 44(4): 457-468.
[2]	原培新，蔡炟，曹文伟，陈超. 基于双目立体视觉的列车目标识别和测距技术[J]. 东北大学学报（自然科学版）, 2022, 43(3): 335-343.
[3]	张之敏，乔建忠，林树宽，王品贺. 一种基于深度网络的视图重建方法[J]. 东北大学学报:自然科学版, 2020, 41(8): 1065-1069.