Compressive perceptual hashing tracking with online foreground learning

This paper proposes a novel compressive sensing based perceptual hashing algorithm for visual tracking. Tracking object is represented by compressive perceptual hashing feature combined with patch-based appearance model. Besides, an updating foreground weight map is assigned for each object representation and the weight map is updated according to the accumulation of foreground pixel and distance between the foreground pixel and the center of the weight map. Based on the compressive perceptual hashing template and the weight map, our tracker searches the local region with the maximum response in an coarse-to-fine way. In addition, we introduce a visual attention knowledge that the object, namely foreground, should be always located in the center of the weight map, to handle the model drift problem. Extensive experiments demonstrate that the proposed tracking method achieves the state-of-the-art performance in challenging scenarios.