Effective multi-resolution background subtraction

In this paper, we propose a novel multi-resolution background sub traction method. We adopt coarse to fine strategy, which is the essence the multi-resolution scheme, to obtain the foreground mask. The rough mask is first gained relied on the Single Gaussian Model, which holds minor computation cost. Then, the slightly accuracy mask is calculated by the Saliency-based Extraction Model, which contains high accuracy and stability. Finally, Contour-based Refining Model is used to refine the mask edge. Our algorithm is evaluated against several video sequences, and experimental results show that the proposed method is suitable for various scenes and is appealing with respect to robustness.