Object Tracking Based on Multiple Features Adaptive Fusion

Abstract

Multiple features fusion based tracking is one of the most active research in tracking literature, In this paper, a novel adaptive fusion strategy is proposed for multiple features fusion, based on two common used fusion rules: product rule and weighted sum rule. This strategy employs particle filtering technique; product rule and weighted sum rule are unified into an adaptive framework through defined features distance. In practice, the new fusion strategy shows more robustness than product fusion and weighted sun rule.