Window‐based approach for fast stereo correspondence. Issue 2 (1st April 2013)

• Record Type: Journal Article
• Authors: Gupta, Raj Kumar; Cho, Siu‐Yeung
• Is Part Of: IET computer vision. Volume 7:Issue 2(2013)
• Page Start: 123
• Page End: 134
• Publication Date: 2013-04-01
• Subjects: correlation methods -- image matching -- stereo image processing; window based approach -- fast stereo correspondence -- area based stereo matching -- disparity maps -- realtime vision system -- correlation based algorithms -- matching window -- disparity boundaries -- textured image areas -- Middlebury stereo datasets; correlation methods -- image matching -- stereo image processing; window based approach -- fast stereo correspondence -- area based stereo matching -- disparity maps -- realtime vision system -- correlation based algorithms -- matching window -- disparity boundaries -- textured image areas -- Middlebury stereo datasets; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2011.0077
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : In this study, the authors present a new area‐based stereo matching algorithm that computes dense disparity maps for a real‐time vision system. Although many stereo matching algorithms have been proposed in recent years, correlation‐based algorithms still have an edge because of speed and less memory requirements. The selection of appropriate shape and size of the matching window is a difficult problem for correlation‐based algorithms. In the proposed approach, two correlation windows are used to improve the performance of the algorithm while maintaining its real‐time suitability. The CPU implementation of the proposed algorithm computes more than 10 frame/s. Unlike other area‐based stereo matching algorithms, this method works very well at disparity boundaries as well as in low textured image areas and computes a dense and sharp disparity map. Evaluations on the benchmark Middlebury stereo datasets have been performed to demonstrate the qualitative and quantitative performance of the proposed algorithm.