11 May 1987 A New Segmentation Method And Its Application To Stereo Vision
Author Affiliations +
Abstract
We present a new approach to the segmentation problem by optimizing a criterion which estimates the quality of a segmentation. Our method offers a general framework for solving a large class of segmentation problem. We use a graph-based description of a partition of an image and a merging strategy based on the optimal use of a sequence of criteria. An efficient data structure enables our implementation to have a low algorithmic complexity. We show how we adapt this method to segment 2-d natural images including color images and how we use results for solving the stereo matching problem.
© (1987) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Olivier Monga, Olivier Monga, "A New Segmentation Method And Its Application To Stereo Vision", Proc. SPIE 0786, Applications of Artificial Intelligence V, (11 May 1987); doi: 10.1117/12.940669; https://doi.org/10.1117/12.940669
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT

Classification of range images
Proceedings of SPIE (December 31 1989)
Knowledge-based videotelephone sequence segmentation
Proceedings of SPIE (October 21 1993)
Image segmentation based on an adaptive 3D analysis of the...
Proceedings of SPIE (February 26 1996)

Back to Top