Efficiently tracking a moving object in two-dimensional image space

A tracking algorithm has been developed to efficiently track a moving objec t in two-dimensional image space. The algorithm employs a limited exhaustiv e template matching scheme that combines the accuracy of an exhaustive sear ch with the computational efficiency of a coarse-fine template matching sch eme, The overall result is an accurate, time-efficient tracking algorithm. After providing a theoretical discussion of the algorithm, three separate b iomedical applications of the algorithm are described. (1) stabilizing an i rradiating laser on the retinal surface for photocoagulation treatment, (2) measuring target fixation eye movement to construct pattern densities at t he retina, and (3) tracking a rat swimming in a Morris Water Maze for psych ophysiological studies. Results for each application is provided, The paper concludes Vith a discussion of the relative merits of the tracking algorit hm and recommendations for methods to improve the performance of the algori thm. (C) 2001 SPIE and IS&T.