Robust object tracking via sparsity-based collaborative model

TLDR

Object tracking is challenged by drastic appearance changes, requiring robust appearance models that combine holistic templates and local representations. The paper proposes a robust object tracking algorithm based on a collaborative model. The method employs a sparsity‑based discriminative classifier and a sparsity‑based generative model, computes confidence values that favor foreground, uses a histogram‑based spatially aware patch representation with occlusion handling, and updates with both recent observations and the original template to mitigate drift. Experiments on challenging videos show the tracker outperforms several state‑of‑the‑art algorithms.

Abstract

In this paper we propose a robust object tracking algorithm using a collaborative model. As the main challenge for object tracking is to account for drastic appearance change, we propose a robust appearance model that exploits both holistic templates and local representations. We develop a sparsity-based discriminative classifier (SD-C) and a sparsity-based generative model (SGM). In the S-DC module, we introduce an effective method to compute the confidence value that assigns more weights to the foreground than the background. In the SGM module, we propose a novel histogram-based method that takes the spatial information of each patch into consideration with an occlusion handing scheme. Furthermore, the update scheme considers both the latest observations and the original template, thereby enabling the tracker to deal with appearance change effectively and alleviate the drift problem. Numerous experiments on various challenging videos demonstrate that the proposed tracker performs favorably against several state-of-the-art algorithms.