Skip to main content
SpringerLink
Log in

An efficient compressed domain moving object segmentation algorithm based on motion vector field

  • Published:
Journal of Shanghai University (English Edition)

Abstract

In this paper an efficient compressed domain moving object segmentation algorithm is proposed, in which the motion vector (MV) field parsed from the compressed video is the only cue used for moving object segmentation. First the MV field is temporally and spatially normalized, and then accumulated by an iterative backward projection to enhance salient motions and alleviate noisy MVs. The accumulated MV field is then segmented into motion-homogenous regions using a modified statistical region growing approach. Finally, moving object regions are extracted in turn based on minimization of the joint prediction error using the estimated motion models of two region sets containing the candidate object region and other remaining regions, respectively. Experimental results on several H.264 compressed video sequences demonstrate good segmentation performance.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Sukmarg O, Rao K R. Fast object detection and segmentation in MPEG compressed domain [C]// Proceedings of IEEE TENCON, Kuala Lumpur, Malaysia. [S.l.]:[s.n.], 2000, 3: 364–368.

    Google Scholar 

  2. Venkatesh B R, Ramakrishnan K R, Srinivasan S H. Video object segmentation: a compressed domain approach [J]. IEEE Transactions on Circuits and System for Video Technology, 2004, 14(4): 462–474.

    Article  Google Scholar 

  3. Mezaris V, Kompatsiaris I, Boulgouris N V, et al. Real-time compressed-domain spatiotemporal segmentation and ontologies for video indexing and retrieval [J]. IEEE Transactions on Circuits and System for Video Technology, 2004, 14(5): 606–621.

    Article  Google Scholar 

  4. Eng H L, Ma K K. Spatiotemporal segmentation of moving video objects over MPEG compressed domain [C]//Proceedings of IEEE International Conference on Multimedia and Expo, New York. [S.l.]: IEEE Press, 2000, 3: 1531–1534.

    Google Scholar 

  5. Porikli F. Real-time video object segmentation for MPEG encoded video sequences [C]//Proceedings of SPIE Conference on Real-Time Imaging VIII, San Jose, CA. [S.l.]: [s.n.], 2004, 5297: 195–203.

    Google Scholar 

  6. Jamrozik M L, Hayes M H. A compressed domain video object segmentation system [C]//Proceedings of IEEE International Conference on Image Processing, Rochester, New York. [S.l.]: IEEE Press, 2002, 1: 113–116.

    Google Scholar 

  7. LIU Z, SHEN L Q, ZHANG Z Y. Automatic video object segmentation from MPEG compressed domain [C]//Proceedings of the 7th International Workshop on Image Analysis for Multimedia Interactive Services, Incheon, Korea. [S.l.]: [s.n.], 2006, 1: 333–336.

    Google Scholar 

  8. LIU Long, LIU Guizhong, LIU Jieyu, et al. New moving object segmentation algorithm in MPEG compressed domain [J]. Journal of Xi’an Jiaotong University, 2004, 38(12): 1264–1267 (in Chinese).

    Google Scholar 

  9. Wiegand T, Sullivan G J, Bjontegaard G, et al. Overview of the H.264/AVC video coding standard [J]. IEEE Transactions on Circuits and System for Video Technology, 2003, 13(7): 560–576.

    Article  Google Scholar 

  10. ZENG W, DU J, GAO W, et al. Robust moving object segmentation on H.264/AVC compressed video using the block-based MRF model [J]. Real-Time Imaging, 2005, 11(4): 290–299.

    Article  Google Scholar 

  11. LIU Zhi, XU Jianfeng, LU Yu, et al. A real-time H.264 compressed domain based moving object segmentation algorithm [J]. Journal of Image and Graphics, 2006, 11(11): 1614–1618 (in Chinese).

    Google Scholar 

  12. Nock R, Nielsen F. Semi-supervised statistical region refinement for color image segmentation [J]. Pattern Recognition, 2005, 38(6): 835–846.

    Article  Google Scholar 

  13. Press W H, Flannery B P, Teukolsky S A, et al. Numerical Recipes in C: The Art of Scientific Computing [M]. Cambridge, Eng.: Cambridge University Press, 1992.

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Communication and Information Engineering, Shanghai University, Shanghai, 200072, P. R. China

    Zhi Liu  (刘 志), Li-quan Shen  (沈礼权) & Zhao-yang Zhang  (张兆杨)

  2. Key Laboratory of Advanced Display and System Application of the Ministry of Education, Shanghai, 200072, P. R. China

    Zhi Liu  (刘 志) & Zhao-yang Zhang  (张兆杨)

Authors
  1. Zhi Liu  (刘 志)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Li-quan Shen  (沈礼权)
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhao-yang Zhang  (张兆杨)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhi Liu  (刘 志).

Additional information

Project supported by the National Natural Science Foundation of China (Grant No.60572127), the Development Foundation of Shanghai Municipal Commission of Education (Grant No.05AZ43), and the Shanghai Leading Academic Discipline Project (Grant No.T0102)

About this article

Cite this article

Liu, Z., Shen, Lq. & Zhang, Zy. An efficient compressed domain moving object segmentation algorithm based on motion vector field. J. Shanghai Univ.(Engl. Ed.) 12, 221–227 (2008). https://doi.org/10.1007/s11741-008-0307-2

Download citation

  • Received:

  • Revised:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11741-008-0307-2

Keywords

Search

Navigation