Translator Disclaimer
16 September 1994 Hierarchical image sequence model for segmentation: application to region-based sequence coding
Author Affiliations +
Proceedings Volume 2308, Visual Communications and Image Processing '94; (1994) https://doi.org/10.1117/12.185998
Event: Visual Communications and Image Processing '94, 1994, Chicago, IL, United States
Abstract
This paper studies the performance of an image sequence model based on Compound Random Fields when used for segmentation purposes. The fact of using a hierarchical model allows characterizing separately the texture and contour information within the sequence. Moreover, temporal and spatial contour behavior can also be described independently. This separated characterization allows to impose constraints on the kind of contours to be obtained and to introduce some a priori knowledge in the segmentation procedure. The way to exploit these features for an object-based sequence coding scheme is analyzed. The influence of the model parameters on the segmentation results is analyzed, in order to achieve segmentations which can be easily coded. The main sought characteristics are smooth spatial contours, slow temporal variations and homogeneous textures. Two different segmentation algorithms are used for this analysis, a recursive and a nonrecursive one.
© (1994) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ferran Marques, Victor Vera, and Antoni Gasull "Hierarchical image sequence model for segmentation: application to region-based sequence coding", Proc. SPIE 2308, Visual Communications and Image Processing '94, (16 September 1994); https://doi.org/10.1117/12.185998
PROCEEDINGS
10 PAGES


SHARE
Advertisement
Advertisement
RELATED CONTENT

Segmentation and motion estimation in image sequences
Proceedings of SPIE (January 01 1990)
Automatic modeling of 3 D moving objects from a TV...
Proceedings of SPIE (January 01 1990)
Knowleuye-Baseu Seyentation Of Road Scenes
Proceedings of SPIE (December 10 1986)

Back to Top