Shape Models from Image Sequences

This paper describes an adaptive method for the recovery of 3-D shape models from sequences of images. A 3-D surface model, initialised to be spherical, is progressively deformed under the action of simulated external forces arising from the proole of the target object in successive images, obtained using a low-level motion segmentation scheme. Intrinsic constraints encourage the model to deform smoothly and to remain symmetrical about a plane parallel to the direction of motion. Experimental results are presented for recovery of shape models of vehicles. The resulting models may be used for several purposes, including tracking, recognition and visualisation.