Tracking Through Scattered Occlusion

Abstract

Scattered occlusion is an occlusion that is not localized in space or time. It occurs because of heavy smoke, rain, snow and fog, as well as tree branches and leafs, or any other thick flora for that matter. As a result, we can not assume that there is correlation in the visibility of nearby pixels. We propose a new tracker, dubbed Scatter Tracker that can efficiently deal with this type of occlusion. Our tracker is based on a new similarity measure between images that combines order statistics with a spatial prior that forces the order statistics to work on non-overlapping patches. We analyze the probability of detection, and false detection, of our tracker and show that it can be modeled as a sequence of independent Bernoulli trials on pixel similarity. In addition, to handle appearance variations of the tracked target, an appearance model update scheme based on incremental-PCA procedure is incorporated into the tracker. We show that the combination of order statistics and spatial prior greatly enhances the quality of our tracker and demonstrate its effectiveness on a number of challenging video sequences.