A Fast and Robust Algorithm of Detection and Segmentation for Moving Object

Detecting and segmenting moving object is an important subject in computer visual analysis. Firstly, the algorithms of detecting moving target from static background in video sequences are discussed in this paper. Secondly, as the inter-frame subtraction can´t detect moving object accurately and mixture Gaussian models can´t solve the problems such as ghost, shadow and real-time application, a new method based on edge-characteristic and inter-frame difference is proposed. In this method the target foreground object can be segregated completely by filling the edge map. Finally, combined with mathematical morphology and connectivity analyzing, noise can be reduced and gaps can be smoothed out. Experimental results show that the proposed algorithm can get exact moving object quickly from complex background and eliminate disturbing of background and the illumination changes efficiently, with operating time reducing dramatically.