REGION-BASED TRACKING USING AFFINE MOTION MODELS IN LONG IMAGE SEQUENCES

This work investigates a new approach to the tracking of regions in an image sequence. The approach relies on two successive operations: det ection and discrimination of moving targets and then pursuit of the ta rgets. A motion-based segmentation algorithm, previously developed in the laboratory, provides the detection and discrimination stage. This paper emphaizes the pursuit stage. A pursuit algorithm has been design ed that directly tracks the region representing the projection of a mo ving object in the image, rather than relying on the set of trajectori es of individual points or segments. The region tracking is based on t he dense estimation of an affine model of the motion field within each region, which makes it possible to predict the position of the target in the next frame. A multiresolution scheme provides reliable estimat es of the motion parameters, even in the case of large displacements. Two interacting linear dynamic systems describe the temporal evolution of the geometry and the motion of the tracked regions. Experiments co nducted on real images demonstrate that the approach is robust against occulusion and can handle large interframe displacements and complex motions. (C) 1994 Academic Press, Inc.