An Improved Stereo Matching Algorithm Based on Guided Image Filter

DOI

10.2991/mic-15.2015.31How to use a DOI?

Keywords

-stereo matching; census transform; guided image filter; dynamic programming

Abstract

Stereo matching is a challenging issue in computer vision field. To address the poor accuracy behavior of local algorithms, we propose an improved stereo matching algorithm based on guided image filter. Firstly, we put forward a combined matching cost by incorporating the absolute difference and improved color census transform (ICCT). Secondly, we use the guided image filter to filter the cost volume, which can aggregate the costs fast and efficiently. Then, in the disparity computing step, we design a modified dynamic programming algorithm, which can weaken the scanning line effect. At last, the final disparity maps are gained after post-processing. The experimental results are evaluated on the Middlebury stereo dataset, showing that our approach can achieve good results both in low texture and depth discontinuity areas with an average error rate of 5.14%.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Gao Ruidong
AU  - Chen Yun
AU  - Yan Lina
PY  - 2015/08
DA  - 2015/08
TI  - An Improved Stereo Matching Algorithm Based on Guided Image Filter
BT  - Proceedings of the 2nd International Conference on Modelling, Identification and Control
PB  - Atlantis Press
SP  - 139
EP  - 144
SN  - 1951-6851
UR  - https://doi.org/10.2991/mic-15.2015.31
DO  - 10.2991/mic-15.2015.31
ID  - Ruidong2015/08
ER  -