Block characteristic based moving object segmentation in the H.264 compressed domain

An improved moving object segmentation approach which extracted motion field from H.264 compressed domain is proposed. Pre-treatments such as vector median filtering and forward block vector accumulation are used to obtain more obvious motion field. Then mix and hierarchical clustering algorithm based on improved k-means and EM is exploited to segment the moving on the macro-block level and on the block level. Experimental results demonstrate that this approach further improves the efficiency of the segmentation by hierarchical clustering. It provides satisfactory real-time segmentation results and good segmentation quality.