A Random Field Model for Improved Feature Extraction and Tracking

This paper presents a novel method for illumination-invariant and contrast preserving feature extraction, aimed at improving performance of tracking under complex light condition. Features to be extracted are represented as a weight field. An energy function of the field is defined as an approximate variance in robust statistics. A simple non-linear iterative rule is derived to compute the optimal field. The optimal field is shown to be invariant to global illumination switching, and preserving target/background contrast. We incorporate the feature extraction method into a mean-shift tracker and this achieves reliable results on real-world sequences in complex scenes and varying illumination.