An algorithm for real-time tracking of non-rigid objects
J. Woodfill, Ramin Zabih · National Conference on Artificial Intelligence · 1991
We describe an algorithm for tracking an unknown object in natural scenes. We require that the object's approximate initial location be available, and further assume that the it ean be distinguished from the background by motion or stereo. No constraint is placed on the object's shape, other than that it not change too rapidly from frame to frame. Objects are tracked and segmented cross-temporally using a massively parallel bottom-up approach. Our algorithm has been implemented on a Connection Machine, and runs in real time 15-20 frames per second).