Fast color-texture discrimination: Application to car tracking

Visual tracking methods have been intensively contributed in the past decade. Promising results have been brought, leading to partial solution of the problem. However it is still utmost difficult to maintain track of an object for a long time, because some events can strongly disrupt the tracking procedures. Such events are occlusions, clutters, illumination changes, particular movements or pose changes. To overcome these challenging events and produce more reliable tracking algorithms, image data must be exploited through several aspects, that is to say through several cues : texture, color, shape or movement. But before being able to use these sources, one must make sure that each of these sources is reliable and non-redundant. In this article, we reckon that texture and color must be jointly processed, and we propose a new color-texture feature called weighted cooccurrence matrices. Using this feature within a particle filter, successful car tracking examples are proposed.