Motion of disturbances: detection and tracking of multi-body non-rigid motion

We present a new approach to the tracking of very non-rigid patterns of mot ion, such as water flowing down a stream. The algorithm is based on a "dist urbance map", which is obtained by linearly subtracting the temporal averag e of the previous frames from the new frame. Every local motion creates a d isturbance having the form of a wave, with a "head" at the present position of the motion and a historical "tail" that indicates the previous location s of that motion. These disturbances serve as loci of attraction for "track ing particles" that are scattered throughout the image. The algorithm is ve ry fast and can be performed in real time. We provide excellent tracking re sults on various complex sequences, using both stabilized and moving camera s, showing a busy ant column, waterfalls, rapids and flowing streams, shopp ers in a mall, and cars in a traffic intersection.