Region-Based Segmentation of Generic Video Scenes Indexing

In this work we develop an object extraction method and propose efficient algorithms for object motion characterization. The set of proposed tools serves as a basis for development of objectbased functionalities for manipulation of video content. The estimators by different algorithms are compared in terms of quality and performance and tested on real video sequences. The proposed method will be useful for the latest standards of encoding and description of multimedia content – MPEG4 and MPEG7.

Authors:

• Aree A. Mohammed

Keywords:

• Object extraction
• Video indexing
• Segmentation
• Optical flow
• Motion estimators.

References:

[1] A. M. Aree, motion estimation by differential methods for
MPEG2 video coding, Journal of Dohuk University,2005, Vol.8,
No.2.
[2] S. Jehan-Besson, M. Barlaud, G. Aubert, Video object
segmentation using Eulerian region-based active contour, IEEE
International Conference on ICCV, 2001, Vol. 1, pp. 353-360.
[3] W. Wei and N. King, Automatic Video Object Segmentation for
MPEG-4. School of Computer Engineering, 2003, Nanyang
Technological University, Singapore.
[4] S. Jehan, M. Barlaud, and G. Aubert, Detection and tracking of
moving objects using a new level set based method, 2000,
ICPR.
[5] M. Changick and H. Jenq-Neng, Video Object Extraction for
Object-Oriented Applications. Journal on VLSI, 2001, 29(1),
pp. 7-21.
[6] B. G. Shunck and B. P. Horn, Determining optical flow.
Artificial Intelligence, 1981, Vol(17) :185-203.
[7] D. R. Walker and K. R. RAO, Improved pel-recursive motion
compensation. Artificial Intelligence, 1981,Vol (32): 1128-
1134.
[8] F. Cafforio, The differential method for image motion
estimation". Image sequence processing , 1983, 104-124
[9] J. R. Shewchuk, An introduction to the conjugate gradient
method. School of Computer Science, 1994.