Efficient region tracking with parametric models of geometry and illumination

TLDR

Object images change dramatically as the object moves, due to pose, illumination, and occlusion variations. The authors propose an efficient general framework for object tracking that addresses pose, illumination, and occlusion challenges. They implement a computationally efficient algorithm that corrects pose‑induced geometric distortions, integrates illumination handling without extra cost, and uses robust statistics to treat occluded regions as outliers. Experimental results demonstrate the effectiveness of the proposed methods.

Abstract

As an object moves through the field 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; complications arise due to the fact that the object undergoes changes in pose relative to the viewing camera, in illumination relative to light sources, and may even become partially or fully occluded. We develop an efficient general framework for object tracking, which addresses each of these complications. We first develop a computationally efficient 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. Experimental results are given to demonstrate the effectiveness of our methods.