Online Video Object Segmentation via Boundary-Constrained Low-Rank Sparse Representation

Abstract

Graphcut-based algorithm is adopted in many video object segmentation systems because different terms can be probabilistically fused together in a framework. Constructing spatio-temporal coherences is an important stage in segmentation systems. However, many steps are involved when computing a key term with good discriminative power. If the cascade steps are adopted, the inaccurate output of the previous step will definitely affect the next step, leading to inaccurate segmentation. In this paper, a key term that is computed by a single framework referred to as boundary-constrained low-rank sparse representation (BCLRSR) is proposed to achieve the accurate segmentation. By treating the elements as linear combinations of dictionary templates, low-rank sparse optimization is adopted to achieve the spatio-temporal saliency. For adding the spatial information to the low-rank sparse model, a boundary constraint is adopted in the framework as a Laplacian regularization. A BCLRSR saliency is then obtained by the represented coefficients, which measure the similarity between the elements in the current frame and the ones in the dictionary. At last, the object is segmented by minimizing the energy function, which is formalized by the spatio-temporal coherences. The experiments on some public datasets show that our proposed algorithm outperforms the state-of-the-art methods.