Visual Tracking with Multilevel Sparse Representation and Metric Learning

Visual tracking arises in various real-world tasks where an object should be located in a video. Sparse representation can implement tracking problems by linearly representing object with a few templates. However, this approach has two main shortcomings. Namely, setting the templates updating frequency is difficult and meanwhile it is relatively weak in distinguishing the object from the background. For solving these problems, the author models a multilevel object template set that can be stratified by different updating time spans. The hierarchical structure and updating strategy promise the real-timeness, stability, and diversity of object template. Additionally, metric learning is combined to evaluate the object candidates and thereby improve the discriminative ability. Experiments on well-known visual tracking datasets demonstrate that the proposed method can track an object more robustly and accurately compared to the state-of-the-art approaches.