A novel approach basedon spatial-temporal information fusion is proposed to segment moving objects in videosequences. In the proposed approach, temporal and spatial information are integratedgradually by a region binding process during the segmentation, which is different to theprocess of combining temporal and spatial segmentation results. The significance of theproposed region binding algorithm is that regions are represented and characterizeddistributively. In the first stage of the proposed approach, current frame is segmentedinto many small regions primitively. Then, these small regions are bound to form theBinding-CCores (BC). Finally, the rest regions are bound to their neighboring BCs understrong or weak rules to get the final object regions. Experimental result demonstrated theperformance of the approach.