Object Tracking via 2DPCA and $\ell _{1}$ -Regularization

In this letter, we present a novel online object tracking algorithm by using 2DPCA and ℓ₁ -regularization. Firstly, we introduce ℓ₁-regularization into the 2DPCA reconstruction, and develop an iterative algorithm to represent an object by 2DPCA bases and a sparse error matrix. Secondly, we propose a novel likelihood function that considers both the reconstruction error and the sparsity of the error matrix. This likelihood function not only handles partial occlusion effectively but also encourages the tracked object to be well-aligned. Finally, to further reduce tracking drift, we enhance the tracker updates by considering the sparsity of the error matrix. Based on our observations, a dense error matrix usually relates to partial occlusion or mis-alignment. Both qualitative and quantitative evaluations on challenging image sequences demonstrate that the proposed tracking algorithm achieves more favorable performance than several state-of-the-art methods.