Object tracking using deformable templates

We propose a novel method for object tracking using prototype-based deforma ble template models. To track an object in an image sequence, we use a crit erion which combines two terms: the frame-to-frame deviations of the object shape and the fidelity of the modeled shape to the Input image. The deform able template model utilizes the prior shape information which is extracted from the previous frames along with a systematic shape deformation scheme to model the object shape in a new frame. The following image information I s used in the tracking process: 1) edge and gradient information: the objec t boundary consists of pixels with large image gradient, 2) region consiste ncy: the same object region possesses consistent color and texture througho ut the sequence, and 3) interframe motion: the boundary of a moving object is characterized by large interframe motion. The tracking proceeds by optim izing an objective function which combines both the shape deformation and t he fidelity of the modeled shape to the current image (in terms of gradient , texture, and interframe motion). The inherent structure in the deformable template. together with region, motion, and image gradient cues. makes the proposed algorithm relatively insensitive to the adverse effects of weak i mage features and moderate amounts of occlusion.