Eecient Region Tracking with Parametric Models of Geometry and Illumination

As an object moves through the eld of view of a camera, the images of the object may change dramatically. This is not simply due to the translation of the object across the image plane. Rather, complications arise due to the fact that the object undergoes changes in pose relative to viewing camera, changes in illumination relative to light sources, and may even be partially or fully occluded. Thus to successfully track an object, complications arising from varying pose, illumination, and partial occlusion must be accounted for. In this paper, we develop an eecient, general framework for object tracking { one which addresses each of these complications. We rst develop a computationally eecient method for handling the geometric distortions produced by changes in pose. We then combine geometry and illumination into an algorithm that tracks large image regions using no more computation than would be required to track with no accommodation for illumination changes. Finally, we augment these methods with techniques from robust statistics and treat occluded regions on the object as statistical outliers. Throughout, we present experimental results performed on live video sequences demonstrating the eeectiveness and eeciency of our methods.