A hierarchical block matching algorithm in depth extraction for binocular vision

Authors:
Jiao Liangbao;Chen Jiao;Chen Rui;Cao Xuehong
Affiliations:
Nanjing Institute of Technology, Nanjing, Jiangsu, Province, China;Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, Province, China;Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, Province, China;Nanjing University of Posts and Telecommunications, Nanjing, Jiangsu, Province, China
Venue:
Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication
Year:
2011

Citing 6
Cited 0

A Taxonomy and Evaluation of Dense Two-Frame Stereo Correspondence Algorithms

International Journal of Computer Vision
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Adaptive Support-Weight Approach for Correspondence Search

IEEE Transactions on Pattern Analysis and Machine Intelligence
Hierarchical building recognition

Image and Vision Computing
Hierarchical Stereo with Thin Structures and Transparency

CRV '08 Proceedings of the 2008 Canadian Conference on Computer and Robot Vision
A new stereo matching algorithm for binocular vision

Proceedings of the 2009 International Conference on Hybrid Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

The stereo matching algorithm for binocular stereo vision is a critical and challenge issue in the field of computer vision, which may has lower matching quality or higher time complexity. To improve that, a hierarchical multi-resolution block matching algorithm for high-resolution image pair is proposed in the paper. Two windows with different size are adopted to improve the matching accuracy in the low texture region. The experimental results show that, the testing image pair at resolution 1240x1110 with the disparity range 30~45, the matching speed is improved by 7~10 times with better results compared to the traditional regional matching algorithm.