The Community for Technology Leaders
3D Data Processing Visualization and Transmission, International Symposium on (2004)
Thessaloniki, Greece
Sept. 6, 2004 to Sept. 9, 2004
ISBN: 0-7695-2223-8
pp: 147-154
Konstantinos Moustakas , Aristotle University of Thessaloniki, Greece; Informatics and Telematics Institute, Greece
Dimitrios Tzovaras , Informatics and Telematics Institute, Greece
Michael G. Strintzis , Aristotle University of Thessaloniki, Greece; Informatics and Telematics Institute, Greece
ABSTRACT
This paper presents a framework for the synthesis of stereoscopic video using as input only a monoscopic image sequence. Initially, bi-directional 2D motion estimation is performed, which is followed by an efficient method for the reliable tracking of object contours. Rigid 3D motion and structure is recovered utilizing extended Kalman filtering. Finally, occlusions are dealt with a novel Bayesian framework, which exploits future information to correctly reconstruct occluded areas. Experimental evaluation shows that the layered object scene representation, combined with the proposed methods for object tracking throughout the sequence and occlusion handling, yields very accurate results.
INDEX TERMS
null
CITATION

D. Tzovaras, M. G. Strintzis and K. Moustakas, "A Non Causal Bayesian Framework for Object Tracking and Occlusion Handling for the Synthesis of Stereoscopic Video," 3D Data Processing Visualization and Transmission, International Symposium on(3DPVT), Thessaloniki, Greece, 2004, pp. 147-154.
doi:10.1109/TDPVT.2004.1335188
85 ms
(Ver 3.3 (11022016))