A Model and Tracking Algorithm for a Class of Video Targets

Abstract

Algorithms are developed for a real-time, automatic system capable of tracking two-dimensional (2-D) targets in complex scenes. A mathematical model of 2-D image spatial and temporal evolution applicable to certain classes of targets and target perturbations is developed. It is shown that for small target perturbations the 2-D tracking problem may be approximated as a 1-D time-varying parameter estimation problem. A CCD-implementable solution is developed which is particularly useful when considering target rotation and dilation and target/background separation. Results of system simulation and suggestions for future research are presented.