Real-time Dense Disparity Estimation based on Multi-Path Viterbi for Intelligent Vehicle Applications

Qian Long, Qiwei Xie, Seiichi Mita, Hossein Tehrani, Kazuhisa Ishimaru and Chunzhao Guo

In Proceedings British Machine Vision Conference 2014
http://dx.doi.org/10.5244/C.28.127

Abstract

This paper proposes a new real-time stereo matching algorithm paired with an online auto-rectification framework. The algorithm treats disparities of stereo images as hidden states and conducts Viterbi process at 4 bi-directional paths to estimate them. Structural similarity, total variation constraint, and a specific hierarchical merging strategy are combined with the Viterbi process to improve the robustness and accuracy. Based on the results of Viterbi, a convex optimization equation is derived to estimate epipolar line distortion. The estimated distortion information is used for the online compensation of Viterbi process at an auto-rectification framework. Extensive experiments were conducted to compare proposed algorithm with other practical state-of-the-art methods for intelligent vehicle applications.

Session

Poster Session

Files

Extended Abstract (PDF, 1 page, 937K)
Paper (PDF, 13 pages, 3.3M)
Supplemental Materials (ZIP, 5.2M)
Bibtex File

Citation

Qian Long, Qiwei Xie, Seiichi Mita, Hossein Tehrani, Kazuhisa Ishimaru, and Chunzhao Guo. Real-time Dense Disparity Estimation based on Multi-Path Viterbi for Intelligent Vehicle Applications. Proceedings of the British Machine Vision Conference. BMVA Press, September 2014.

BibTex

@inproceedings{BMVC.28.127
	title = {Real-time Dense Disparity Estimation based on Multi-Path Viterbi for Intelligent Vehicle Applications},
	author = {Long, Qian and Xie, Qiwei and Mita, Seiichi and Tehrani, Hossein and Ishimaru, Kazuhisa and Guo, Chunzhao},
	year = {2014},
	booktitle = {Proceedings of the British Machine Vision Conference},
	publisher = {BMVA Press},
	editors = {Valstar, Michel and French, Andrew and Pridmore, Tony}
	doi = { http://dx.doi.org/10.5244/C.28.127 }
}