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

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

Video analysis using re-constructing of motion vectors on MPEG compressed domain

압축영역에서 움직임 벡터의 재추정을 이용한 비디오 해석 기법

  • Kim, Nak-U (Dept.of Media Engineering, Gsaim Art Technology college, Chungang University) ;
  • Kim, Tae-Yong (Dept.of Media Engineering, Gsaim Art Technology college, Chungang University) ;
  • Gang, Eung-Gwan (Dept.of Multi Media Engineering, Information Technology Computer Engineering College, Jeonju University) ;
  • Choe, Jong-Su (Dept.of Media Engineering, Gsaim Art Technology college, Chungang University)
  • 김낙우 (중앙대학교 첨단영상대학원 영상공학과) ;
  • 김태용 (중앙대학교 첨단영상대학원 영상공학과) ;
  • 강응관 (전주대학교 정보기술컴퓨터공학부 멀티미디어공학과) ;
  • 최종수 (중앙대학교 첨단영상대학원 영상공학과)
  • Published : 2002.05.01
Download PDF
⟨ Previous Next ⟩

Abstract

A macroblock(MB) in MPEG coded domain can have zero, one, or two motion vectors depending on its frame type and prediction direction (forward-, backward-, or hi-directionally). In this paper, we propose a method that converts these motion vectors on MPEG coded domain as a uniform set, independent of the frame type and the direction of prediction, and directly utilizes these re-analyzed motion vectors for understanding video contents. Also, using this frame-type-independent motion vector, we propose novel methods for detecting and tracking moving objects with frame-based detection accuracy on the compressed domain. These algorithms are performed directly from the MPEG bitstreams after VLC decoding with little time consumption. Experimental results show validity and outstanding performance of our methods.

본 논문은 MPEG 비디오에서 나타나는 여러 예측 형태의 움직임 벡터를 프레임 타입에 관계없이 단일 예측방향만을 갖도록 새롭게 추정하여 비디오 영상물의 분석에 직접적으로 활용하는 방안에 대해 제시하고 있다. 또한 재추정된 각 프레임에서의 움직임 벡터를 이용한 비디오 시퀀스 내에서의 객체 추출 및 추적 기법 등에 대해서도 새롭게 제안하였다. 제안된 알고리즘은 압축 영상에 대한 전체적인 복원과정을 거치지 않고, 압축 비디오 영역으로부터 쉽게 추출될 수 있는 매크로 블록 영역 상에서 수행되었으며, 실험 결과는 제안된 방법의 높은 성능을 잘 나타내어 주고 있다.

Keywords

References

  1. Y. Nakajima, K. Ujihara, A. Yoneyama, 'Universal scene change detection on MPEG-coded data domain,' in Proc. SPIE Visual Comm. and Image Proc., vol. 3024, pp. 992-1003, 1997 https://doi.org/10.1117/12.263179
  2. N.V. Patel and I.K. Sethi, 'Video shot detection and characterization for video databases,' Pattern Recognition, vol. 30, no. 4, pp. 583-592, 1997 https://doi.org/10.1016/S0031-3203(96)00114-8
  3. H.L. Eng and K.K. Ma, 'Bidirectional motion tracking for video indexing,' Multimedia Signal Processing, pp. 153-158, 1999 https://doi.org/10.1109/MMSP.1999.793813
  4. J.G. Kim, H.S. Chang, J.W. Kim and H.M. Kim, 'Efficient camera motion characterization for MPEG video indexing,' IEEE International Conference on Multimedia and Expo, vol. 2, pp. 1171-1174, 2000 https://doi.org/10.1109/ICME.2000.871569
  5. O. Sukmarg and K.R. Rao, 'Fast object detection and segmentation in MPEG compressed domain,' Proceedings of TENCON 2000, vol. 3, pp. 364-368 https://doi.org/10.1109/TENCON.2000.892290
  6. A. Yoneyama, Y. Nakajima, H. Yanagihara and M. Sugano, 'Moving object detection and identification from MPEG coded data,' Proc. of International Conference on Image Processing, vol. 2, pp. 934-938, 1999 https://doi.org/10.1109/ICIP.1999.823035
  7. F. Bartolini, V. Cappellini and C. Giani, 'Motion estimation and tracking for urban traffic monitoring,' Proc. of International Conference on Image Processing, vol. 3, pp. 787790, 1996 https://doi.org/10.1109/ICIP.1996.560850
  8. ISO/IEC/JTC1/SC29/WG11, 13812-2, 1995
  9. R. Milanese, F. Deguillaume and A. Jacot-Descombes, 'Video segmentation and camera motion characterization using compressed data,' SPIE-Multimedia Storage and Archiving Systems Ⅱ, vol. 3229, pp. 23-31, 1997 https://doi.org/10.1117/12.290367
  10. V. Kobla and D. Doermann, 'Compressed domain video indexing techniques using DCT and motion vector information in MPEG video,' in Proc. SPIE Conference on Storage and Retrieval for Image and Video Database, vol. 3022, pages 200-210, 1997 https://doi.org/10.1117/12.263408