Robust object tracking in compressed image sequences

Accurate object tracking is important in defense applications where an inte rceptor missile must hone into a target and track it through the pursuit un til the strike occurs. The expense associated with an interceptor missile c an be reduced through a distributed processing arrangement where the comput ing platform on which the tracking algorithm is run resides on the ground, and the interceptor need only carry the sensor and communications equipment as part of its electronics complement. In this arrangement, the sensor ima ges are compressed, transmitted to the ground, and decompressed to facilita te real-time downloading of the data over available bandlimited channels. T he tracking algorithm is run on a groundbased computer while tracking resul ts are transmitted back to the interceptor as soon as they become available . Compression and transmission in this scenario introduce distortion. If se vere, these distortions can lead to erroneous tracking results. As a conseq uence, tracking algorithms employed for this purpose must be robust to comp ression distortions in this paper we introduced a robust object tracking al gorithm based on the continuous wavelet transform. The algorithm processes image sequence data on a frame-by-frame basis, implicitly faking advantage of temporal history and spatial frame filtering to reduce the impact of com pression artifacts. Test results show that tracking performance can be main tained at low transmission bit rates and can be used reliably in conjunctio n with many well-known image compression algorithms. (C) 1998 SPIE and IS&T . [S1017-9909(98)00804-6].