Disparity-based segmentation of stereoscopic foreground/background image sequences
- 1 February 1994
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Communications
- Vol. 42 (2/3/4) , 673-679
- https://doi.org/10.1109/tcomm.1994.577095
Abstract
Describes a method for displacement estimation in stereoscopic images, which is closely coupled with a segmentation of the pictures into homogeneously displaced regions. The technique is driven by a statistical optimization criterion which assesses the quality of the disparity estimate and of the segmentation, thus improving both of these simultaneously. In addition, the optimization criterion explicitly takes occluded areas into consideration. With the additional help of two constraints, this enables the algorithm to locate regions corresponding to occlusions accurately.Keywords
This publication has 21 references indexed in Scilit:
- A two-stage algorithm for discontinuity-preserving surface reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992
- A new segmentation algorithm for videophone applications based on stereo image pairsIEEE Transactions on Communications, 1991
- Stereo correspondence by surface reconstructionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Direct evidence for occlusion in stereo and motionPublished by Springer Nature ,1990
- An object-background image model for predictive video codingIEEE Transactions on Communications, 1989
- Computation of stereo disparity using regularizationPattern Recognition Letters, 1988
- Ill-posed problems in early visionProceedings of the IEEE, 1988
- Early vision: From computational structure to algorithms and parallel hardwareComputer Vision, Graphics, and Image Processing, 1985
- Multilevel computational processes for visual surface reconstructionComputer Vision, Graphics, and Image Processing, 1983
- Cooperative Computation of Stereo DisparityScience, 1976