Journal of the Institute of Electronics Engineers of Korea SP (대한전자공학회논문지SP)

The Institute of Electronics and Information Engineers (대한전자공학회)
권호 표지

Video Shot Retrieval in H.264/AVC compression domain

H.264/AVC 압축 영역에서의 동영상 검색

  • Byun Ju-Wan (Dept. of Electronic Engineering, Dongguk University) ;
  • Kim Sung-Min (Dept. of Electronic Engineering, Dongguk University) ;
  • Won Chee-Sun (Dept. of Electronic Engineering, Dongguk University)
  • Published : 2006.09.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we present a video shot retrieval algorithm in H.264/AVC compression domain. Unlike previous standards such as MPEG-2 and 4, H.264/AVC supports a variable block size for motion compensation. Therefore, existing video retrieval algorithms exploiting the motion vectors in MPEG-2 and 4 domains are not appropriate for H.264/AVC. So, we devise a method to project motion vectors with larger than $4{\times}4$ block sizes into those for the smallest $4{\times}4$ blocks. It also uses correlations among features for the measure of similarity. Experimental results with standard videos of 10558 frames and commercial videos of 48161 frames show that the proposed method yields ANMRR less than 0.2.

본 논문은 H.264/AVC 압축 영역에서의 동영상 검색에 관한 것이다. 기존의 동영상 압축 표준인 MPEG-2 및 4와는 달리 H.264/AVC는 다양한 블록 단위의 움직임 보상으로 인해 기존의 MPEG-2 및 4에서 사용되었던 움직임 벡터를 이용한 방법들을 그대로 적용하기 어렵다. 따라서 본 논문에서는 이러한 문제를 해결하기 위해 H.264/AVC의 다양한 블록 크기의 움직임 벡터를 움직임 보상의 최소 단위인 $4{\times}4$ 블록 단위로 분할하고, 각각의 분할된 블록에 동일한 움직임 벡터를 할당하는 방법을 제안한다. 또한, 유사도 측정을 위해 두 영상으로부터 추출한 특징 간의 상관계수를 이용하였다. 실험은 10558 프레임의 MPEG 표준 동영상과 48161 프레임의 일반 동영상을 대상으로 이루어졌으며, 제안한 방법을 이용한 실험을 통해 0.2 이하의 ANMRR 결과를 나타내었다.

Keywords

References

  1. W.E. Farag and H.A. Wahab, 'A human-based technique for measureing video data similarity,' in Proc. of IEEE on International Symposium on Computers and Communication, Vol. 2, pp. 768-774, 2003 https://doi.org/10.1109/ISCC.2003.1214211
  2. Y. T. Kim and T.S. Chua, 'Retrieval of news video using video sequence matching,' in Proc. of IEEE Conf. on Multimedia Modeling, pp. 68-75, 2005 https://doi.org/10.1109/MMMC.2005.63
  3. J.F. Chen, H.Y. Mark Liao and C.W. Lin, 'Fast video retrieval via the statistics of motion,' in Proc. of IEEE Conf. on Acoustics, Speech and Signal Processing, Vol. 2, pp. 437-440, 2005 https://doi.org/10.1109/ICASSP.2005.1415435
  4. E. Ardizzone, M. La Cascia, A. Avanzato and A. Bruna, 'Video indexing using MPEG motin compensation vectors,' in IEEE international Conference on Multimedia Computing and Systems, Vol. 2, pp. 725-729, 1999 https://doi.org/10.1109/MMCS.1999.778574
  5. I.E.G. Richardson, H.264 and MPEG-4 video Compression, John Wiley & Sons, 2003
  6. T. Wiegand and G. Sullivan, 'Draft ITU-T recommendation and final draft international standard of joint video specification,' Joint Video Team of ISO/IEC MPEG & ITU-T VCEG, 2003
  7. A. Tamhankar and K.R. Rao, 'An overview of H.264/MPEG-4 Part 10,' 4th EURASIP Conf. on Video/Image Processing and Multimedia Communications, 2003 https://doi.org/10.1109/VIPMC.2003.1220437
  8. S.-S. Cheung and A. Zakhor, 'Efficient video similarity measurement with video signature,' IEEE Transactions on Circuits and Systems for Video Technology, Vol. 13, pp. 59-74, 2003 https://doi.org/10.1109/TCSVT.2002.808080
  9. K. Konstantinos and T. Sergios, Pattern recognition, Academic press, 2003
  10. B.S. Manjunath, A. Philippe and S. Thomas, Introduction to MPEG-7 multimedia content interface, John Wiley & Sons, 2002