A Fast, Robust Optical Flow Estimation Method for Compressed Video

You Jun-yong; Liu Gui-zhong; Li Hong-liang

doi:10.3724/SP.J.1146.2006.00175

Volume 29 Issue 9

Jan. 2011

Turn off MathJax

Article Contents

Article Navigation > Journal of Electronics & Information Technology > 2007 > 29(9): 2154-2157

You Jun-yong, Liu Gui-zhong, Li Hong-liang. A Fast, Robust Optical Flow Estimation Method for Compressed Video[J]. Journal of Electronics & Information Technology, 2007, 29(9): 2154-2157. doi: 10.3724/SP.J.1146.2006.00175

Citation:

You Jun-yong, Liu Gui-zhong, Li Hong-liang. A Fast, Robust Optical Flow Estimation Method for Compressed Video[J]. Journal of Electronics & Information Technology, 2007, 29(9): 2154-2157. doi: 10.3724/SP.J.1146.2006.00175

Citation:

PDF( 310 KB)

A Fast, Robust Optical Flow Estimation Method for Compressed Video

doi: 10.3724/SP.J.1146.2006.00175 cstr: 32379.14.SP.J.1146.2006.00175

Received Date: 2006-02-20
Rev Recd Date: 2006-07-31
Publish Date: 2007-09-19

Abstract

Abstract

To analyze quickly the motion information of videos, a fast optical flow estimation algorithm for compressed domain is proposed. Firstly the spatial partial derivatives of image luminance are estimated by using two AC coefficients, and then the predictive residual errors and motion vectors of blocks are appended to estimate the temporal partial derivatives. In addition, after the detailed analysis of those macro-blocks that had no forward motion estimation, the motion information is given approximatively relative to their forward reference frames. And then, a amendatory partial derivative estimation is given for the inconsecutive image blocks when occlusion and cut had happened. Finally, optical flow estimation is performed based on the least square method and partial derivative estimation. Experiments indicated that this method can more accurately estimate the optical flow than the L-K method in pixel domain and the exist method in compressed domain. Moreover the proposed method can greatly reduce the compute time than the estimation in pixel domain.

FullText(HTML)

References(1)

References

Horn B and Schunck G. Determining optical flow[J].Artificial Intelligence.1981, 17(1-3):185-203[2]Lucas B, and Kanade T. An iterative image registration technique with an application to stereo vision[A]. Proceeding the 7th International Joint Conference on Artificial Intelligence[C], Vancouver, 1981: 674-679.[3]Nagel H H. Constrains for the estimation of displacement vector fields from image sequences [A]. Proceeding International Joint Conference on Artificial Intelligence[C], Karlsruhe, Germany, 1983: 945-951.[4]Seferidis V. General approach to block-matching motion estimation[J]. Optical Engineering, 1993, 32(1): 79-91.[5]Lai J, Gauch J, and Crisman J. Computing optical flow in color image sequences[J]. Innovation and Technology in Biology and Medicine, 1994, 15(3): 76-87.[6]Snyder M A. On the mathematical foundations of smoothness constraints for the determination of optical flow and for surface reconstruction[J].IEEE Trans. on Pattern Analysis and Machine Intelligence.1991, 13(11):1105-1114[7]Coimbra M T and Davies M. Approximating optical flow within the MPEG-2 compressed domain[J].IEEE Trans.on Circuits and Systems for Video Technology.2005, 15(1):103-[8]Yeo B and Liu B. On the extraction of DC sequence from MPEG compressed video[A]. Proceeding ICIP[C], Washington, DC, USA, IEEE, 1995, 2: 260-263.

Relative Articles

Supplements(0)

Cited By

Proportional views