Motion Segmentation and Tracking

This paper presents a noveltracking based motion segmentation algorithm. The tracking is done by fitting successively more elaborate models of optical flowonthe tracked region and the segmentation is done by extracting the regions of the image that are consistent with the computed model of flow. The method can track objects in image sequences with moving background, taken by a hand-held camera, tolerate up to 30 pixels interframe motion and takes 0.3 seconds per frame pair of size 320 x 240 pixels on a 500 Mhz Sun Blade 100 workstation