Object tracking with dynamic feature graph

Abstract

Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the model to accommodate the object appearance and structure changes. Traditional appearance based representations (like color histogram) fails when the object has rich texture. In this paper, we present a novel feature based object representation attributed relational graph (ARG) for reliable object tracking. The object is modeled with invariant features (SIFT) and their relationship is encoded in the form of an ARG that can effectively distinguish itself from background and other objects. We adopt a competitive and efficient dynamic model to adoptively update the object model by adding new stable features as well as deleting inactive features. A relaxation labeling method is used to match the model graph with the observation to gel the best object position. Experiments show that our method can get reliable track even under dramatic appearance changes, occlusions, etc.