Bitmap tracker for visual tracking under very general conditions

Abstract

System and method for visually tracking a target object silhouette in a plurality of video frames under very general conditions. The tracker does not make any assumption about the object or the scene. The tracker works by approximating, in each frame, a PDF (probability distribution function) of the target's bitmap and then estimating the maximum a posteriori bitmap. The PDF is marginalized over all possible motions per pixel, thus avoiding the stage in which optical flow is determined. This is an advantage over other general-context trackers that do not use the motion cue at all or rely on the error-prone calculation of optical flow. Using a Gibbs distribution with a first order neighborhood system yields a bitmap PDF whose maximization may be transformed into that of a quadratic pseudo-Boolean function, the maximum of which is approximated via a reduction to a maximum-flow problem.

Dependencies are inferred from the claim text.