Robust Structured Multi-task Multi-view Sparse Tracking

TL;DR

This paper introduces a robust multi-task multi-view sparse tracking method that leverages structured sparse representations across different views and tasks within a particle filter framework, demonstrating superior performance on challenging sequences.

Contribution

The paper proposes a novel structured multi-task multi-view sparse tracking approach that considers relationships among views and tasks, with an efficient proximal gradient algorithm for optimization.

Findings

Outperforms state-of-the-art trackers on benchmark sequences.

Effectively handles challenges like occlusion and appearance changes.

Provides a fast and robust tracking solution.

Abstract

Sparse representation is a viable solution to visual tracking. In this paper, we propose a structured multi-task multi-view tracking (SMTMVT) method, which exploits the sparse appearance model in the particle filter framework to track targets under different challenges. Specifically, we extract features of the target candidates from different views and sparsely represent them by a linear combination of templates of different views. Unlike the conventional sparse trackers, SMTMVT not only jointly considers the relationship between different tasks and different views but also retains the structures among different views in a robust multi-task multi-view formulation. We introduce a numerical algorithm based on the proximal gradient method to quickly and effectively find the sparsity by dividing the optimization problem into two subproblems with the closed-form solutions. Both qualitative and quantitative evaluations on the benchmark of challenging image sequences demonstrate the superior performance of the proposed tracker against various state-of-the-art trackers.