A Fast Trilateral Filter based Adaptive Support Weight Method for Stereo Matching - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Circuits and Systems for Video Technology Année : 2014

A Fast Trilateral Filter based Adaptive Support Weight Method for Stereo Matching

Résumé

Adaptive support weight (ASW) methods represent the state-of-the-art in local stereo matching and the bilateral filter based ASW method achieves outstanding performance. However, this method fails to resolve the ambiguity induced by nearby pixels at different disparities but with similar colors. In this paper, we introduce a novel trilateral filter based ASW method that remedies such ambiguities by considering the possible disparity discontinuities through color discontinuity boundaries, i.e., the boundary strength between two pixels, which is measured by a local energy model. We also present a recursive trilateral filter based ASW method whose computational complexity is O(N) excluding the boundary detection, where N denotes the input image size. This complexity is thus independent of the support window size. The recursive trilateral filter based method is a non-local cost aggregation strategy. The experimental evaluation on the Middlebury benchmark shows that the proposed method, whose average error rate is 4.95%, outperforms other local methods in terms of accuracy and also the average runtime of the proposed trilateral filter based cost aggregation is roughly 260 milliseconds on a 3.4 GHz Inter Core i7 CPU, which is comparable to the state-of-the-art efficiency.
Fichier non déposé

Dates et versions

hal-01301109 , version 1 (11-04-2016)

Identifiants

Citer

Dongming Chen, Mohsen Ardabilian, Liming Chen. A Fast Trilateral Filter based Adaptive Support Weight Method for Stereo Matching. IEEE Transactions on Circuits and Systems for Video Technology, 2014, 99, PP, pp.1-14. ⟨10.1109/TCSVT.2014.2361422⟩. ⟨hal-01301109⟩
134 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More