Automatic moving object segmentation based on HOS and an improved active contour

A novel algorithm for automatic moving object segmentation is proposed in this paper. The proposed segmentation system includes two main modules, moving object model locating and contour correction. In the former module, HOS (higher-order statistics) is used to automatically separate the moving areas from the background. Then the morphological filter is used to remove the noises and holes. Based on the intersection operation of the two moving areas which obtained from three successive frames, the occlude background may be removed and moving object model can be obtained However, the result of the previous process fails to obtain the accurate moving object contour. To solve this problem, the initial contour of the moving object is extracted and an improved active contour which uses the gradient vector as the external force guides the initial contour moving to the actual video object contour. Experiment results testify that the proposed algorithm is of few parameters, robust to noise and best in result of segmentation.