|
Speeded-up stereo matching using geodesic support weights
O. A. Yakovlev, A. V. Gasilov Orel Branch of the Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences, 137 Moskovskoe Sh., Orel 302025, Russian Federation
Abstract:
In local stereo matching, the algorithms based on the adaptive support weights have good-quality results. This paper presents a modified version of the local matching with geodesic support. The proposed algorithm considerably reduces computation time at the cost of insignificant loss of quality that is experimentally confirmed with Middlebury Stereo Evaluation SDK. The key idea is to combine geodesic support weights and image segmentation for recoloring the reference image. This transformation makes it possible to use partial sums for matching cost computation.
Keywords:
stereo matching; segmentation; geodesic support weights.
Received: 14.07.2016
Citation:
O. A. Yakovlev, A. V. Gasilov, “Speeded-up stereo matching using geodesic support weights”, Inform. Primen., 10:3 (2016), 98–104
Linking options:
https://www.mathnet.ru/eng/ia437 https://www.mathnet.ru/eng/ia/v10/i3/p98
|
Statistics & downloads: |
Abstract page: | 202 | Full-text PDF : | 91 | References: | 30 | First page: | 1 |
|