Foreground segmentation for static video via multi-core and multi-modal graph cut

Foreground detection is essential for semantic understanding and discovery for surveillance videos but still suffers from inefficiency and poor shape or silhouette detection. We argue to leverage multiple modalities (e.g., color appearance, foreground likelihood, spatial continuity, etc.) for foreground detection and propose a rigorous fusion method by graph cut. We further devise three strategies (e.g., dividing the graph cut problem into several subtasks, exploiting multi-core platform, etc.) to speed up the detection. Experimenting in open benchmarks, the proposed method outperforms other rival approaches in terms of detection accuracy and frame rate.