Dynamic Integration of Generalized Cues for Person Tracking

Abstract. We present an approach for the dynamic combination of multiple cues in a particle filter-based tracking framework. The proposed algorithm is based on a combination of democratic integration and layered sampling. It is capable of dealing with deficiencies of single features as well as partial occlusion using the very same dynamic fusion mechanism. A set of simple but fast cues is defined, which allow us to cope with limited computational resources. The system is capable of automatic track initialization by means of a dedicated attention tracker permanently scanning the surroundings.

• Type: Conference
• Year: 2008
• Where: ECCV
• Authors: Kai Nickel, Rainer Stiefelhagen
• Keywords: Automatic Track Initialization, Computer Vision, Dedicated Attention Tracker, Dynamic Combination, Dynamic Fusion Mechanism, ECCV 2008, Particle Filter-based Tracking