Segment-based adaptive window and multi-feature fusion for stereo matching
Journal of Algorithms & Computational Technology · 2016
DOI: 10.1177/1748301815618299 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Algorithms & Computational Technology, 2016. Verfasst von Hua Shi und 4 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 34 Literaturangaben.
Abstract (Originalsprache)
As to the problems of local stereo matching methods, such as matching window selection difficulty, fuzzy disparity edges and low accuracy in weak texture regions, this paper proposes an efficient stereo matching algorithm to improve the stereo matching accuracy in these regions. First of all, we segment the stereo images and calculate the adaptive support window according to the area of each segmentation region. Second, the matching cost is computed based on the feature fusion of color and gradient, and then the initial disparity can be achieved. Finally, the ultimate matching disparity can be obtained through a series post-processing, including consistency checking, mismatch correcting, disparity refinement and so on. Test results of Middlebury Stereo Datasets show that the proposed algorithm is effective with high matching precision, and especially can tackle well with the weak texture and slope surfaces regions.
Zitieren
APA
Shi, H., Zhu, H., Wang, J., Yu, S., & Fu, Z. (2016). Segment-based adaptive window and multi-feature fusion for stereo matching. Journal of Algorithms & Computational Technology. https://doi.org/10.1177/1748301815618299
Vancouver
Shi H, Zhu H, Wang J, Yu S, Fu Z. Segment-based adaptive window and multi-feature fusion for stereo matching. Journal of Algorithms & Computational Technology. 2016. doi:10.1177/1748301815618299
BibTeX
@article{Shi2016,
author = {Shi, Hua and Zhu, Hong and Wang, Jing and Yu, Shun-Yuan and Fu, Zheng-Fang},
title = {Segment-based adaptive window and multi-feature fusion for stereo matching},
journal = {Journal of Algorithms & Computational Technology},
year = {2016},
doi = {10.1177/1748301815618299}
}
EUVIMED