Tracking objects in videos with texture features
Résumé
In this article, we address the problem of object tracking in videos for multimedia applications. To produce a reliable and robust tracking algorithm, several visual characteristics of the target object must be examined. The different sources of information must be carefully chosen so as to select only the most informative ones. We argue that color and texture cues can be both quickly handled by cooccurrence matrices. Yet these matrices are too sensitive to illumination changes occurring in natural scenes. By adding weights, drawn from kernels centered on representative colors of the object, the feature can cope with this matter. We provide experimental result obtained from different kinds of natural scenes.