Locally Structured Multi-Task Multi-Kernel Tracker

Many impressive correlation filter trackers only construct a single kernel space for combined feature vector, or introduce independently multiple kernels with limit performance improvement, and neglect the spatial structure relationship among and inside target samples. In this paper, we propose a structured multi-task multi-kernel correlation particle filter tracker, which introduces multiple non-linear kernels for multiple channel features to fully take the strength of their powerful discriminability. Meanwhile, the developed tracker exploits the interdependencies and cooperations among different features to learn multi-task multi-kernel correlation filter jointly, and makes the learned multi-kernel filters complement and boost each other. Besides, by introducing cross patch similarity with the spatial constraints, the proposed tracker not only exploits the intrinsic structure information among target samples, but also preserves the spatial layout structure and correspondence of local image patches inside target samples. This is achieved by sparsity-induced mixed norm regulator. Furthermore, a shepherded particle filter tracking framework employs the affine motion modal to cover the states of target among adjacent frames as many as possible, including large scale variances and small move. Experiments on three popular datasets demonstrate that our tracker performs significantly better than other state-of-theart methods.