A LOCAL METHOD FOR CONTOUR MATCHING AND ITS PARALLEL IMPLEMENTATION

This paper presents a local approach for matching contour segments in an image sequence. This study has been primarily motivated by work con cerned with the recovery of 3D structure using active vision. The meth od to recover the 3D structure of the scene requires to track in real- time contour segments in an image sequence. Here, we propose an origin al and robust approach that is ideally suited for this problem. It is also of more general interest and can be used in any context requiring matching of line boundaries over time. This method only involves loca l modeling and computation of moving edges dealing ''virtually'' with a contour segment primitive representation. Such an approach brings ro bustness to contour segmentation instability and to occlusion, and eas iness for implementation. Parallelism has also been investigated using an SIMD-based real-time image-processing system. This method has been validated with experiments on several real-image sequences. Our resul ts shown quite satisfactory performance and the algorithm runs in a fe w milliseconds.