Design of a real-time tracking system for fast-moving objects

This paper describes the design of a real-time raster-scan TV/FLIR camera based tracking system for fast moving objects using image processing techniques. A tracking-window is placed over the approximate location of the target, either automatically or by a human operator. The target image is segmented from the background using a new adaptive cooperative segmentation technique that utilizes background histogram in the immediate vicinity of the target-image and edge strengths of the pixels within the tracking window, The segmented target-image is then processed to estimate tracking-errors and compute a confidence measure. Tracking errors are filtered using a stable implementation of the Kalman filter to get accurate estimates of the target's motion-states. The target state is predicted over the next few image frames for generating orientation commands for the tracking-mount. The tracking-system successfully tracks targets even under low-contrast and noisy imaging conditions.