kNN-based high-dimensional Kullback-Leibler distance for tracking

This paper deals with region-of-interest (ROI) tracking in video sequences. The goal is to determine in successive frames the region which best matches, in terms of a similarity measure, a ROI defined in a reference frame. Two aspects of such a measure between the reference region and a candidate region can be distinguished: radiometry which indicates if the regions have similar colors and geometry which correlates where these colors are present in the regions. If not using geometry, the number of potential matches increases. A soft geometric constraint can be added in the form of a joint radiometric-geometric PDF. High-dimensional PDF estimation being a difficult problem, measures based on these PDF distances may lead to an incorrect match. Instead, we propose to compute the Kullback-Leibler distance between high-dimensional PDFs without explicit estimation of the PDFs, i.e., directly from the samples using the kth-nearest neighbor (kNN) framework. Results showed accurate tracking.