Likelihood-based dual-threshold selection for imaging target trackers
Larisa Stephan, Gillian K. Groves · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2000
Most greylevel threshold-selection algorithms find thresholds that are optimal according to specific regional or global statistics. These traditional approaches do not involve any model of the target except that it is expected to be separable from the background by a threshold suite. Thus, they fail to make use of the most important feature of imaging target trackers: the well-known location of the target in each frame. We present a technique that uses knowledge of the target location to build up a temporally- smoothed greylevel distribution map from which we extract two thresholds that separate from the background the greylevels with a high probability of belonging to the target under track.