Adaptive Compressive Tracking Based on Perceptual Hash Algorithm

Abstract

As the compressive tracking algorithm is easily failed to track target due to the classifier learning rate is fixed when appearances and lightings of target get seriously changed and completely loses the target after heavy occlusion, we propose adaptive compressive tracking algorithm based on perceptual hash algorithm. It makes the compressive tracking algorithm more adaptive to the change of target appearances by adjusting the learning rate of classifier in real time according to the Hamming distance between the hash fingerprints of current target and the original one. Experimental results show that the method can quickly and accurately track the target in the case of the object appearances change and the object is occluded. Our tracker accuracy and robustness have been improved and real-time performance.