We introduce a stochastic model to characterize the online computational process of an object recognition system based on a hierarchy of classifiers. The model is a graphical network for the conditional distribution, under both object and background hypotheses, of the classifiers which are executed during a coarse-to-fine search. A likelihood is then assigned to each history or “trace” of processing. In this way, likelihood ratios provide a measure of confidence for each candidate detection, which markedly improves the selectivity of hierarchical search, as illustrated by pruning many false positives in a face detection experiment. This also leads to a united framework for object detection and tracking. Experiments in tracking faces in image sequences demonstrate invariance to large face movements, partial occlusions, changes in illumination and varying numbers of faces.
CITATION STYLE
Gangaputra, S., & Geman, D. (2006). The Trace Model for Object Detection and Tracking (pp. 401–420). https://doi.org/10.1007/11957959_21
Mendeley helps you to discover research relevant for your work.