Motion segmentation based on dual interrelated models

Motion segmentation plays an important role in many vision applications, yet it is still a challenging problem in complex scenes. The typical conditions in real world scenarios like illumination variations, dynamic backgrounds and camera shaking make negative effects on segmentation performance. In this paper, a newly designed method for robust motion segmentation is proposed, which is mainly composed of two interrelated models. One is a normal random model(N-model), and the other is called enhanced random model(E-model). They are constructed and updated in spatio-temporal information for adapting to illumination changes and dynamic backgrounds, and operate in an Ada- Boost-like strategy. The exhaustive experimental evaluations on complex scenes demonstrate that the proposed method outperforms the state-of-the-art methods.