Adaptive Scale Compressive Tracking with Feature Integration

Abstract

Abstract. Compressive tracking (CT) is utilized to cope with real-time tracking, which use a very sparse measurement matrix to compressive samples of targets and background, then a classifier is trained to distinguish foreground and background. However, this algorithm suffers from the drifting problem, and used the fixed size tracking box to detect, recognize, and update the samples and classifier. In order to solve these problems, we adopt a different way to extracted positive samples, and employ powerful features to exploit the advantages of feature fusion to describe target, a scale pyramid is used to realize adaptive scale tracking. Experimental results on various benchmark video sequences demonstrate the superior performance of our algorithm.