Optimized Region Competition Algorithm Applied to the Segmentation of Artificial Muscles in Stereoscopic Images

Abstract

This paper addresses the implementation of the Region Competition algorithm for segmenting stereoscopic video sequences. The segmentation performed by this algorithm is an essential stage for the 3D characterization of artificial muscles. Image sequences are acquired by a two-cam computer vision system. The aim of this work is to come up with optimal and efficient segmentation of these images; the information obtained from the first segmented frame of the video sequence is used for segmenting the next frame and so on. Redundancy between stereoscopic pairs of images is also used to optimize the segmentation. In this paper, the Region Competition algorithm is described and a specific implementation is detailed. It also shows how to solve particular problems of stereoscopic video segmentation. Finally, results yielded from experiments are presented and discussed.