Robust Structured Group Local Sparse Tracker Using Deep Features
This is an incremental improvement for visual tracking in computer vision, enhancing robustness and accuracy in challenging scenarios.
The paper tackles visual tracking by proposing a deep features-based structured group local sparse tracker (DF-SGLST) that uses group-sparsity regularization to incorporate local and spatial information, achieving superior performance on benchmarks like OTB50 and OTB100.
Sparse representation has recently been successfully applied in visual tracking. It utilizes a set of templates to represent target candidates and find the best one with the minimum reconstruction error as the tracking result. In this paper, we propose a robust deep features-based structured group local sparse tracker (DF-SGLST), which exploits the deep features of local patches inside target candidates and represents them by a set of templates in the particle filter framework. Unlike the conventional local sparse trackers, the proposed optimization model in DF-SGLST employs a group-sparsity regularization term to seamlessly adopt local and spatial information of the target candidates and attain the spatial layout structure among them. To solve the optimization model, we propose an efficient and fast numerical algorithm that consists of two subproblems with the closed-form solutions. Different evaluations in terms of success and precision on the benchmarks of challenging image sequences (e.g., OTB50 and OTB100) demonstrate the superior performance of the proposed tracker against several state-of-the-art trackers.