In this paper, we propose an approach for unsupervised segmentation of moving video objects (VOs) over MPEG compressed domain. The proposed algorithm utilizes the homogeneity property of the spatiotemporally localized VO's information-macroblock motion vectors (MVs) and DCT's DO coefficients, in order to achieve segmentation with accuracy of 8 ×8 DCT block size. First, macroblock MVs are utilized to identify the locations of moving VOs mainly based on our previous works in [1]-[3]. DC coefficients are then exploited to achieve finer boundary segmentation. For achieving both objectives, a maximum entropy fuzzy clustering algorithm is proposed to classify MVs and DC coefficients into homogeneous regions, respectively. Experimental results show that the developed algorithm has accurately segment VOs with accuracy of 8×8 DCT block size without any user intervention.
展开▼