Title :
A compound Bayes test for detection of occlusion and visible background and foreground areas in stereo
Author :
Triantafyllidis, G.A. ; Tzovaras, D. ; Strintzis, M.G.
Author_Institution :
Dept. of Electr. & Comput. Eng., Aristotelian Univ. of Thessaloniki, Greece
Abstract :
An efficient technique based on the Bayes test is introduced in this paper, for the identification of the occlusion and visible background and foreground areas in a noisy stereoscopic image pair. Four hypotheses are used for the formulation of compound Bayes decision rules. Experimental results illustrating the performance of the proposed techniques are presented and evaluated
Keywords :
Bayes methods; feature extraction; stereo image processing; Bayes decision rules; compound Bayes test; noisy stereoscopic image pair; occlusion detection; visible background detection; visible foreground detection; Additive white noise; Background noise; Cameras; Data compression; Gaussian noise; Information processing; Laboratories; Pixel; Stereo vision; Testing;
Conference_Titel :
Digital and Computational Video, 2001. Proceedings. Second International Workshop on
Conference_Location :
Tampa, FL
Print_ISBN :
0-7695-1110-4
DOI :
10.1109/DCV.2001.929948
