Abstract
In this paper, we present an effective algorithm for foreground objects segmentation for sports video. This algorithm consists of three steps: low-level features extraction, camera motion estimate, and foreground object extraction. We employ a robust M-estimator to motion vectors fields to estimate global camera motion parameters based on a four-parameter camera motion model, followed by outliers analysis using robust weights instead of the residuals to extract foreground objects. Based on the fact that foreground objects’ motion patterns are independent of the global motion model caused by camera motions such as pan, tilt, and zooming, we considers those macro-blocks as foreground, which corresponds to the outliers blocks during robust regression procedure. Experiments showed that the proposed algorithm can robustly extract foreground objects like tennis players and estimate camera motion parameters. Based on these results, high-level semantic video indexing such as event detection and sports video structure analysis can be greatly facilitated. Furthermore, basing the algorithm on compressed domain features can achieve great saving in computation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
International Organization for Standardization, Multimedia Content Description Interface-Part 5 Multimedia Description Schemes, ISO/IEC JTC 1/SC 29/WG 11, March 2001, Singapore (2001)
D. W. Murray and B. F. Buston: Scene Segmentation From Visual Motion Using Global Optimization, Vol.9, No.2. IEEE Transactions on Pattern Analysis and Machine Intelligence (1987) 220–228
T. Meier and K. Ngan: Automatic segmentation of moving-objects for video object plane generation, Vol.8. IEEE Transactions on Circuits and Systems for Video Technology (1998) 525–538
A. Neri, S. Colonnese, G. Russo, and P. Talone: Automatic moving object and background separation, Vol.66, No.2. Signal Processing (1998) 219–232
R. Mech and W. Wollborn: A noise robust method of segmentation of moving objects in video sequences, Vol.4. IEEE International Conference on Acoustics, Speech, and Signal Processing (1997) 2657–2660
D. Zhong, S. F. Chang: An Integrated Approach for Content-Based Video Object Segmentation and Retrieval, Vol.9, No.8. IEEE Transactions on Circuits and Systems for Video Technology (1999) 1259–1268
R. Wang, H. J. Zhang, and Y. Q. Zhang: A Confidence Measure Based Moving Object Extraction System Built For Compressed Domain. Proceedings of IEEE International Symposium on Circuits and Systems (2000) 21–24
A. Yoneyama, Y. Nakajima, H. Yanagihara, and M. Sugano: Moving Object Detection and Identification from MPEG coded data, Vol.2. Proceedings of International Conference on Image Processing (1999) 934–938.
Sukmarg O., Rao K. R.: Fast Object Detection and Segmentation in MPEG Compressed Domain, Vol.2. TENCON 2000 Proceedings (2000) 364–368.
J. H. Meng, S. F. Chang: CVEPS-A Compressed Video Editing and Parsing System, Proceedings ACM Multimedia (1996) 43
J. M. Odobez and P. Bouthemy: Robust Multisolution Estimation of Parametric Motion Models, Vol.6, No.4. Journal of Visual Communication and Image Representation (1995) 348–365
A. Smolic, M. Hoeynck and J. R. Ohm: Low-complexity Global Motion Estimation from PFrame Motion Vectors for MPEG-7 Applications, Vol.2. International Conference on Image Processing Proceedings (2000) 271–274
M. Irani and P. Anandan: A unified approach to moving object detection in 2d and 3d scenes, Vol.20, No.6. IEEE Transaction on Pattern Analysis and Machine Intelligence (1998) 577–589
Holland, P. W., and R. E. Welsch: Robust regression using iteratively reweighted leastsquares, A6. Communications in Statistics: Theory and Methods (1977) 813–827
William J. J. Rey: Introduction to Robust and Quasi-Robust Statistical Methods, Springer, Berlin, Heidelberg (1983)
Chatterjee, S. and A. S. Hadi: Influential Observations, High Leverage Points, and Outliers in Linear Regression. Statistical Science (1986)
Bob Burke, Frederick Shook: The Visual Grammar of Moving Picture Photograph, Chapter 3, in Television Field Production and Reporting, Longman Publisher USA (1995)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2002 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ling-Yu, D., Xiao-Dong, Y., Xu, M., Tian, Q. (2002). Foreground Segmentation Using Motion Vectors in Sports Video. In: Chen, YC., Chang, LW., Hsu, CT. (eds) Advances in Multimedia Information Processing — PCM 2002. PCM 2002. Lecture Notes in Computer Science, vol 2532. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36228-2_93
Download citation
DOI: https://doi.org/10.1007/3-540-36228-2_93
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00262-8
Online ISBN: 978-3-540-36228-9
eBook Packages: Springer Book Archive