Visual Tracking Based on Kernelized Least Squares with Occlusion Detecting

In order to cope with the complex variation of target appearance during visual tracking, a robust tracking algorithm based on kernelized least squares (KLS) with occlusion detecting is proposed. First, Modeling the problem of tracking based on kernelized least squares with constrain, by showing that the dense sampling set of translated patches is circulant, using the well-established theory of circulant matrices, kernelized least squares is efficient computed with fast Fourier transform (FFT). Second, we propose a method to detect occlusion based on higher-order cumulants, and use it to improve the model updating. Extensive experimental results show that our approach outperforms state-of-the-art methods, while operating at real-time.