Abstract
Video object segmentation is an important task towards the framework of MPEG-4 and MPEG-7 standardization phase. Especially, the MPEG group has adopted the concept of Video Objects (VOs) and Video Object Planes (VOPs) for improving the coding efficiency and providing multimedia functionalities to the future encoders [1][2]. While frame-based coding and description schemes provide limited capabilities in terms of access, identification and manipulation of individual objects, object-based coding and description offers a new range of capabilities, where objects are separately described giving a new dimension to playing with, creating or accessing video content. Video objects correspond to meaningful entities of arbitrary shape in a digital video stream, such as a human, a chair, while VOPs are the projection of VOs into a plane. Such an extraction plays an important role in many other image analysis problems: content-based indexing and retrieval [3][4], reconstruction of a 3D human model from several 2D images [5], human face detection and recognition [6][7], video surveillance of specific areas and identification of objects by industrial robots [8].
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
MPEG Video Group, “MPEG-4 Video Verification Model-Version 2.1,” ISO/IEC JTCI/SC29AVG11, May 1996.
T. Sikora, “The MPEG-4 Video Standard Verification Model,” IEEE Trans. on Circuits and Systems for Video Techn. vol. 7, no. 1, pp. 19–31, Feb. 1997.
Special issue on visual information management, Communications of ACM, Dec. 1997. Guest Editor: Ramesh Jain.
N. Doulamis, A. Doulamis, Y. Avrithis and S. Kollias, “Video Content Representation Using Optimal Extraction of Frames and Scenes” Proc. of IEEE Inter. Confer. on Image Processing (ICIP), Chicago, USA, Oct. 1998.
J. D. Foley, A. van Dam, S. K. Feiner and J. F. Hughes. Computer Graphics: Principles and Practice. Addison-Wesley Publishing Company, 1995.
B. Moghaddam, A. Pentland, “Probabilistic Visual Learning for Object Representation,” IEEE Trans. Patt. Anal. Machine Intell., vol. 19, pp. 696–710.
N. Tsapatsoulis, N. Doulamis, A. Doulamis and S. Kollias, “Face Extraction from Non-uniform Background and Recognition in Compressed Domain,” Proc. of IEEE Inter. Confer. on Acoustics Speech and Signal Processing, (ICASSP), vol. 5, pp. 2701–2704, Seattle, USA, May 1998.
D. H. Ballard and C. M. Brown. Computer Vision. Prentice Hall, Englewood Cliffs, New Jersey.
A. Doulamis, N. Doulamis and S. Kollias, “Retrainable Neural Networks for Image Analysis and Classification,” Proc. of IEEE Inter. Confer. on Systems, Man & Cybern. (SMC), pp. 3558–3562, Orlando Oct. 1997.
P. Salembier and H. Sanson, “Robust Motion Estimation Using Connected Operators,” Proc. of IEEE Inter. Confer. on Image Processing, ICIP, pp. 77–80, vol. 1, Santa Barbara, USA, October 1997.
H. Wang and Shih-Fu Chang, “A Highly Efficient System for Automatic Face Region Detection in MPEG Video Sequences,” IEEE Trans. on Circuits & Systems for Video Techn., special issue on Multimedia Systems and Technologies, 1997.
A. Aydin Alatan, E. Tuncel and L. Onural, “Object Segmentation via Ruled-based Data Fusion,” Proc. of Work. On Image Analysis for Mult. Inter. Services, (WIAMIS), pp. 51–55, Louvain-la-Neuve Belgium, June 1997.
A. Doulamis, N. Doulamis and S. Kollias, “A Neural Network Based Scheme for Unsupervised Video Object Segmentation,” Proc. of IEEE Inter. Confer. on Image Processing (ICIP), Chicago, USA, Oct. 1998.
J. Zhang, J. Modestino and D. Langan, “Maximum-Likelihood Parameter Estimation for Unsupervised Stochastic Model-Based Image Segmentation,” IEEE Trans. on Image Processing, vol. 3, nol. 4, pp. 404–429, July 1994.
A. Dempster, N. Laird and D. Rubin, “Maxium Likelihood from Incomplete Data via the EM Algorithm,” J. Roy. Soc. Statist., Series B., no. 1, pp. 1–38, 1977.
D. Titterington, A. Smith and U. Makov. Statistical Analysis of Finite Mixture Distributions. New York, Wiley, 1985.
J. Zhang and J. Modestino, “A Statistical Model-fitting Approach to Cluster Validation with Applications to Image Processing,” IEEE Tran. Patt. Anal Machine. Intell., vol. 12, pp. 1009–1017, Oct. 1990.
R. Kinderman and J. L. Snell. Markov Random Fields and their Applications. Providence. America Mathematical Society 1980.
S. Geman and D. Geman, “Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images,” IEEE Trans. on Patt. Anal. Machine Intell., vol. PAMI-6, pp. 721–741, 1984.
J. Besag, “On the Statistical Analysis of Dirty Images,” J. Roy. Soc. Statist., Series B. vol. 48, pp. 259–302, 1986.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer Science+Business Media Dordrecht
About this chapter
Cite this chapter
Doulamis, N.D., Doulamis, A.D., Kollias, S.D. (1999). Video Object Segmentation Using the EM Algorithm. In: Tzafestas, S.G. (eds) Advances in Intelligent Systems. International Series on Microprocessor-Based and Intelligent Systems Engineering, vol 21. Springer, Dordrecht. https://doi.org/10.1007/978-94-011-4840-5_29
Download citation
DOI: https://doi.org/10.1007/978-94-011-4840-5_29
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-0393-6
Online ISBN: 978-94-011-4840-5
eBook Packages: Springer Book Archive