Region tracking via level set PDEs without motion computation

Tracking regions in an image sequence is a challenging and difficult problem in image processing and computer vision and at the same time, one that has many important applications: automated video surveillance, video database search and retrieval, automated video editing, etc. So far, numerous approaches to region tracking have been proposed. Many of them suffer from excessive constraints imposed on the motion of the region being tracked and need an explicit motion model (e.g., affine, Euclidean). Some, which do not need a parametrized motion model, rely instead on a dense motion field. By and large, most rely on some kind or other of motion information. Those which do not use any motion information instead use a model of the region being tracked, typically by assuming strong intensity boundaries, or constraining the shape of the region to belong to a parametrized family of shapes. In this paper, we propose a novel approach to region tracking that is derived from a Bayesian formulation. The novelty of the approach is twofold: First, no motion field or motion parameters need to be computed. This removes a major burden since accurate motion computation has been and remains a challenging problem and the quality of region tracking algorithms based on motion critically depends on the computed motion fields and parameters. The second novelty of this approach, is that very little a priori information about the region being tracked is used in the algorithm. In particular, unlike numerous tracking algorithms, no assumption is made on the strength of the intensity edges of the boundary of the region being tracked, nor is its shape assumed to be of a certain parametric form. The problem of region tracking is formulated as a Bayesian estimation problem and the resulting tracking algorithm is expressed as a level set partial differential equation. We present further extensions to this partial differential equation, allowing the possibility of including additional information in the tracking process, such as priors on the region's intensity boundaries and we present the details of the numerical implementation. Very promising experimental results are provided using numerous real image sequences with natural object and camera motion.