Disparity-selective stereo matching using correlation confidence measure
- Authors
- Kim, Sijung; Jang, Jinbeum; Lim, Jaeseung; Paik, Joonki; Lee, Sangkeun
- Issue Date
- Sep-2018
- Publisher
- OPTICAL SOC AMER
- Citation
- JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION, v.35, no.9, pp 1653 - 1662
- Pages
- 10
- Journal Title
- JOURNAL OF THE OPTICAL SOCIETY OF AMERICA A-OPTICS IMAGE SCIENCE AND VISION
- Volume
- 35
- Number
- 9
- Start Page
- 1653
- End Page
- 1662
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/805
- DOI
- 10.1364/JOSAA.35.001653
- ISSN
- 1084-7529
1520-8532
- Abstract
- Recently, the cost-volume filtering (CVF) methods for local stereo matching have provided fast and accurate results compared to those of the other method. However, CVF still causes incorrect results in the occlusion and texture-free regions. In particular, cost aggregation by pixel units involves complex computation because of its dependence on the image resolution and search range. This paper presents a robust stereo matching method for occluded regions. First, we generate cost volumes using the CENSUS transform and the scale-invariant feature transform (SIFT). Then, label-based cost volumes are aggregated using adaptive support weight and the simple linear iterative clustering (SLIC) scheme from two generated cost volumes. In order to obtain optimal disparity by two label-based cost volumes, we select the disparity corresponding to high confidence similarity of CENSUS or SIFT with minimum cost point. Experimental results show that our method estimates the optimal disparity in occlusion information, which exists only in the scene of one of the stereo pairs. (C) 2018 Optical Society of America
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.