Open Access Open Access  Restricted Access Subscription or Fee Access

Segmentation of Compressed Video using Macro Block Classification and Global Motion Estimation

H. Ambika, R. Rajalakshmi, R. Vijayalakshmi

Abstract


In this paper, the moving regions from the compressed video are segmented using various techniques such as Global motion estimation, markov random field model and macro block classification. First motion vectors are extracted from compressed video and are classified into different classes and global motion estimation was done on the motion vectors and coarse segmentation map was obtained. Then Motion vector quantization (VQ) based on similarity of local motion is used to find the likely number of moving regions. The inferred statistics are used to initialize prior probabilities for subsequent Markov Random field (MRF) classification, which produces coarse segmentation map. Finally, coarse to fine strategy is utilized to refine region boundaries.

Keywords


Global Motion Estimation, Markov random field, Macro block, Compressed Video, Motion Vector.

Full Text:

PDF

References


R. Puri and K. Ramchandran (October 2002), “PRISM: a new robust video coding based on distributed compression principles,” in Proc. of Conference on Communication, Control, and Computing, Allenton, IL.

A. Aaron and B. Girod (September 2003), “Towards practical wyner ziv coding of video,” in Proc. of IEEE International Conference on Image Processing, Barcelona, Spain.

Y. Liu and S. Oraintara(May 2004), “Complexity comparison of fast block-matching motion estimation algorithms,” in Proc. of IEEE International Conference on Acoustics, Speech, and Signal Processing, pp. 17–21.

D. Slepian and J. K. Wolf(July 1973) , “Noiseless coding of correlated information sources,” IEEE Transaction on Information Theory, vol. 19, pp. 471– 490.

D. Wyner and J. Ziv(January 1976), “The rate-distortion function for source coding with side information at the decoder,” IEEE Transaction on Information Theory, vol. 22, pp. 1–10.

A. Aaron, S. Rane, E. Setton, and B. Girod(January 2004), “Transform domain wynerziv codec for video,” in in Proc. SPIE Visual Communications and Image Processing, San Jose, CA.

A. Aaron, S. Rane, and B. Girod( October 2004), “Wyner-ziv video coding with hashbased motion compensation at the receiver,” in in Proc. IEEE International Conference on Image Processing, Singapore.

H. Malvar, A. Hallapuro, M. Karczewicz, and L. Kerofsky(July 2003, “Lowcomplexity transform and quantization in h.264/AVC,” IEEE Transaction on Circuits and System for Video Technology, vol. 13, pp. 598–603.

C. W. Ting, L. M. Po, and C. H. Cheung (December 2003, “Center-biased frame selection algorithms for fast multi-frame motion estimation in h.264,” in Proc. of IEEE International Conference on Neural Networks and Signal Processing, Nanjing, China, pp. 1258–1261.

A. M. Bruckstein, M. Elad, and R. Kimmel(September 2003), “Down-scaling for better transform compression,” IEEE Transactions on Image Processing, vol. 12, pp. 1132–1144.

Y.-M. Chen, I. V. Bajić, and P. Saeedi(May 2009), “Coarse-to-fine moving region segmentation in compressed video,” in Proc. IEEE WIAMIS, London, U.K., , pp. 45–48.

A. Dante and M. Brookes(Sep. 2003), “Precise real-time outlier removal from motion vector fields for 3-D reconstruction,” in Proc. IEEE ICIP, pp. 393–396.

J. Besag(1986), “On the statistic analysis of dirty pictures,” J. Roy. Statist. Soc. B., vol. 48, no. 3, pp. 259–302.

R. Ewerth, M. Schwalb, P. Tessmann, and B. Freisleben(Sep. 2007, “Segmenting moving objects in MPEG videos in the presents of camera motion,” in Proc. ICIAP, pp. 92–96.

Y.-M. Chen, I. V. Bajić, and P. Saeedi(Jul. 2010), “Motion segmentation in compressed video using Markov random fields,” in Proc. IEEE ICME, Singapore, pp. 760–765.

Y. Su,M.-T. Sun, andV.Hsu(Feb. 2005), “Global motion estimation from coarsely sampled motion vector field and the applications,” IEEE Trans. Circuits Syst. Video Technol., vol. 15, no. 2, pp. 232–242.

A. Smolic, M. Hoeynck, and J.-R. Ohm( Sep. 2000), “Low-complexity global motion estimation fromP-framemotion vectors forMPEG-7 application,” in Proc. IEEE ICIP, pp. 271–274.

M. Haller, A. Krutz, and T. Sikora(May 2009), “Evaluation of pixel- and motion vector-based global motion estimation for camera motion characterization,” in Proc. WIAMIS, pp. 49–52.

M. Fischler and R. Bolles(, Jun. 1981), “Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography,” Commun. ACM, vol. 24, no. 6, pp. 381–395.

Z. Kato(Mar. 2008), “Segmentation of color images via reversible jump MCMC sampling,” Image Vis. Computing, vol. 26, no. 3, pp. 361–371.


Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.