Disparity and occlusion estimation in multiocular systems and their coding for the communication of multiview image sequences
- 1 June 1998
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 8 (3), 328-344
- https://doi.org/10.1109/76.678630
Abstract
An efficient disparity estimation and occlusion detection algorithm for multiocular systems is presented. A dynamic programming algorithm, using a multiview matching cost as well as pure geometrical constraints, is used to estimate disparity and to identify the occluded areas in the extreme left and right views. A significant advantage of the proposed approach is that the exact number of views in which each point appears (is not occluded) can be determined. The disparity and occlusion information obtained may then be used to create virtual images from intermediate viewpoints. Furthermore, techniques are developed for the coding of occlusion and disparity information, which is needed at the receiver for the reproduction of a multiview sequence using the two encoded extreme views. Experimental results illustrate the performance of the proposed techniquesKeywords
This publication has 14 references indexed in Scilit:
- Disparity and occlusion estimation for multiview image sequences using dynamic programmingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Incorporating intensity edges in the recovery of occlusion regionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Fractal coding of a multi-view 3-D imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Object-based coding of stereo image sequences using joint 3-D motion/disparity compensationIEEE Transactions on Circuits and Systems for Video Technology, 1997
- A Maximum Likelihood Stereo AlgorithmComputer Vision and Image Understanding, 1996
- Disparity-space images and large occlusion stereoPublished by Springer Science and Business Media LLC ,1994
- A maximum likelihood N-camera stereo algorithmPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1994
- Stereo Without Disparity Gradient Smoothing: a Bayesian Sensor Fusion SolutionPublished by Springer Science and Business Media LLC ,1992
- A dynamic programming algorithm for elastic registration of distorted pictures based on autoregressive modelIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- Stereo by Intra- and Inter-Scanline Search Using Dynamic ProgrammingIeee Transactions On Pattern Analysis and Machine Intelligence, 1985