Machine Vision and Applications

, Volume 23, Issue 6, pp 1219–1227

Real-time stereo matching based on fast belief propagation

  • Xueqin Xiang
  • Mingmin Zhang
  • Guangxia Li
  • Yuyong He
  • Zhigeng Pan
Original Paper

DOI: 10.1007/s00138-011-0405-1

Cite this article as:
Xiang, X., Zhang, M., Li, G. et al. Machine Vision and Applications (2012) 23: 1219. doi:10.1007/s00138-011-0405-1

Abstract

In this paper, a global optimum stereo matching algorithm based on improved belief propagation is presented which is demonstrated to generate high quality results while maintaining real-time performance. These results are achieved using a foundation based on the hierarchical belief propagation architecture combined with a novel asymmetric occlusion handling model, as well as parallel graphical processing. Compared to the other real-time methods, the experimental results on Middlebury data show the efficiency of our approach.

Keywords

Stereo matching Hierarchical belief propagation Occlusion handling 

Supplementary material

ESM 1 (WMV 11350 kb)

Copyright information

© Springer-Verlag 2012

Authors and Affiliations

  • Xueqin Xiang
    • 1
  • Mingmin Zhang
    • 1
  • Guangxia Li
    • 1
  • Yuyong He
    • 1
  • Zhigeng Pan
    • 2
  1. 1.State Key Lab of Computer Aided Design and Computer GraphicsHangzhouChina
  2. 2.Digital Media and HCI Research CenterHangzhou Normal UniversityHangzhouChina

Personalised recommendations