Region-Based Tracking Using Affine Motion Models in Long Image Sequences

Abstract

This work investigates a new approach to the tracking of regions in an image sequence. The approach relies on two successive operations: detection and discrimination of moving targets and then pursuit of the targets. A motion-based segmentation algorithm, previously developed in the laboratory, provides the detection and discrimination stage. This paper emphasizes the pursuit stage. A pursuit algorithm has been designed that directly tracks the region representing the projection of a moving object in the image, rather than relying on the set of trajectories of individual points or segments. The region tracking is based on the 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 estimates 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 conducted on real images demonstrate that the approach is robust against occlusion and can handle large interframe displacements and complex motions.