Compressed Domain Moving Object Segmentation in Local Motion Scene

Liu Long; Han Chong-zhao; Liu Jie-yu; Wang Zhan-hui

Volume 27 Issue 8

Aug. 2005

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2005 > 27(8): 1249-1253

Liu Long, Han Chong-zhao, Liu Jie-yu, Wang Zhan-hui. Compressed Domain Moving Object Segmentation in Local Motion Scene[J]. Journal of Electronics & Information Technology, 2005, 27(8): 1249-1253.

Citation:

Liu Long, Han Chong-zhao, Liu Jie-yu, Wang Zhan-hui. Compressed Domain Moving Object Segmentation in Local Motion Scene[J]. Journal of Electronics & Information Technology, 2005, 27(8): 1249-1253.

Liu Long, Han Chong-zhao, Liu Jie-yu, Wang Zhan-hui. Compressed Domain Moving Object Segmentation in Local Motion Scene[J]. Journal of Electronics & Information Technology, 2005, 27(8): 1249-1253.

Citation:

Liu Long, Han Chong-zhao, Liu Jie-yu, Wang Zhan-hui. Compressed Domain Moving Object Segmentation in Local Motion Scene[J]. Journal of Electronics & Information Technology, 2005, 27(8): 1249-1253.

PDF( 1320 KB)

Compressed Domain Moving Object Segmentation in Local Motion Scene

Received Date: 2004-04-05
Rev Recd Date: 2004-10-30
Publish Date: 2005-08-19

Abstract

Abstract

More and more attention has been paid to the study of moving object segmentation in MPEG compressed domain these years, which has already developed into a practical technology. In this paper, an algorithm by using motion vectors and DCT coefficients is put forward for segmenting moving object in MPEG compressed domain. As regards local motion scene, the algorithm produces a better result of segmentation than currently adopted ones. Firstly, the motion vectors are processed by accumulation and median filter; then the areas of non-zero motion vectors are rectified by the Bayesian decision to get high-quality segmentation.

FullText(HTML)

References(1)

References

Venkatesh R, Ramakrishnan K R. Content-based video retrieval using motion descriptors extracted from compressed domain.IEEE International Symposium on Circuits and Systems(ISCAS),Arizona, 2002, vol. 4:141 - 144.[2]Venkatesh R, Ramakrishnan K R. Compressed domain motion segmentation for video object extraction. Intl Conf. on Acoustics,Speech, and Signal Processing, Orlando, Sept. 2002, vol.4:3788 - 3791.[3]Wang H, Chang S F. A highly efficient system for automatic face region detection in MPEG video[J].IEEE Trans. on Circuit and System for Video Technology.1997, 7(4):615-[4]Orachat Sukmarg, Rao K R. Fast object detection and segmentation in mpeg compressed domain. TENCON 2000,Kuala Lumpur, Malaysia, Sept. 2000:1769 - 1770.[5]Eng How-Lung, Ma Kai-Kuang. Spatiotemporal segmentation of moving video objects over mpeg compressed domain[J].IEEE IntlConf. on Multimedia and Expo(ICME), New York.2000, Vol.3:1531-[6]Ji Salkmann, Park Hyun Wook. Moving object segmentation in DCT-based compressed video[J].Electronics Letters.2000, 36(21):1769-[7]ISO/IEC.JCT1/SC29 CD11172-2, MPEG1, international standard for coding of moving pictures and associated audio for digital storage media at up to about 1.5Mb/s. 1991.[8]ISO/IEC.JCT1/SC29 CD13818-2, MPEG2, coding of moving pictures and associated audio. 1993.

Relative Articles

Supplements(0)

Cited By

Proportional views