A Fast and Accurate Moving Object Extraction Method from Compressed Video Stream

Moscheni F, Bhatacharjee S, Kunt M. Spatiotemporal segmentation based on region merging.IEEE Trans. on PAMI, 1998, PAMI-20(9): 897-915.[2]Dufaux F, Moscheni F, Lippman A. Spatio-temporal segmentation based on motion and static segmentation. In Proc. of ICIP, Washington, USA, 1995: 306-309.[3]Torres L, Garcia D, Mates A. A robust motion estimation and segmentation approach to represent moving images with layers. In Proc. of ICASSP, Munich, Germany, 1997: 2661-2664.[4]Jarnrozik M L, Hayes M H. A compressed domain video object segmentation system. In Proc.of ICIP, New York: USA, 2002: 113-116.[5]Wang H, Chang S F. A highly efficient system for automatic face region detection in MPEG video[J].IEEE Trans. on Circuits and Systems for Video Technology.1998, 7(4):615-628[6]Babu R V, Ramakrishnan K R. Compressed domain motion segmentation for video object extraction. In Proc. of ICASSP, Florida, USA, 2002: 3788-3791.[7]Wang R, Zhang H J, Zhang Y Q. A confidence measure based moving object extraction system built for compressed domain. In Proc. of ISCAS, Geneva, Switzerland, 2000: 21-24.[8]Dempster A, Laird N, Rubin D. Maximum-likelihood from incomplete data via the EM algorithm.Journal of the Royal Statistical Society B, 1977, 39(1): 1-38.[9]Canny J F. A computational approach to edge detection. IEEE Trans. on PAMI, 1986, PAMI8(6): 679-698.