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

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

반복 과정을 통한 율-제한 주요 화명 선택 기법

Rate-Constrained Key Frame Selection Method using Iteration

  • 이훈철 (韓國科學技術院 電子電算學科 電氣 및 電子工學) ;
  • 김성대 (韓國科學技術院 電子電算學科 電氣 및 電子工學)
  • Lee, Hun-Cheol (Division of Electrical Engineering, Dept. of Electrical Engineering and Computer Science, KAIST) ;
  • Kim, Seong-Dae (Division of Electrical Engineering, Dept. of Electrical Engineering and Computer Science, KAIST)
  • 발행 : 2002.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

주요 화면은 보다 적은 양의 데이터를 사용해서 비디오가 갖는 시각적 내용물의 변화량을 효과적으로 표현하기 위해 많이 사용된다. 이와 같은 비디오 표현 방식은 대역폭이나 저장 용량이 제한된 상황에 적합하다. 이 경우 대역폭이나 저장 용량에 따라 주요 화면의 개수를 조절하는 능력은 주요 화면 선택 기법의 중요한 필요 사항 중 하나다. 본 논문에서는 주요 화면의 개수가 제한 조건일 때 순차적인 주요 화면을 찾는 방법을 제안한다. 제안하는 기법은 먼저 원하는 개수의 초기 주요 화면을 미리 선택하고 이들이 대표하는 서로 중복되지 않는 시구간을 정한 후 반복 과정을 통해 주요 화면의 위치와 시구간의 크기를 조절하면서 왜곡 값이 최소가 되도록 주요 화면과 시구간을 찾는다. 실험 결과 제안하는 방법이 선택하는 주요 화면들은 율-왜곡 관점에서 기존의 방법보다 우수하고 인간의 시각 인지와도 일치함을 알 수 있었다.

Video representation through representative frames (key frames) has been addressed frequently as an efficient way of preserving the whole temporal information of sequence with a considerably smaller amount of data. Such compact video representation is suitable for the purpose of video browsing in limited storage or transmission bandwidth environments. In a case like this, the controllability of the total key frame number (i.e. key frame rate) depending on the storage or bandwidth capacity is an important requirement of a key frame selection method. In this paper, we present a sequential key frame selection method when the number of key frames is given as a constraint. It first selects the desired number of initial key frames and determines non-overlapping initial time intervals that are represented by each key frame. Then, it adjusts the positions of key frames and time intervals by iteration, which minimizes the distortion. Experimental result demonstrates the improved performance of our algorithm over the existing approaches.

키워드

참고문헌

  1. F. Idris and S. Panchanathan, 'Review of Image and Video Indexing Techniques', Journal of Visual Communication and Image Representation, Vol. 8, No. 2, June, pp. 146-166, 1997 https://doi.org/10.1006/jvci.1997.0355
  2. MPEG-7: Context, Objectives and Technical Roadmap, V. 11, ISO/IEC JTC1/SC29/WG11/N2729, March 1999, Seoul
  3. Hong Jiang Zhang, Jianhua Wu, Di Zhong and Stephen W, Smoliar, 'An Integrated System for Content-based Video Tetrieval and Browsing', Pattern Recognition, Vol. 30, No.4, pp. 643-658, 1997 https://doi.org/10.1016/S0031-3203(96)00109-4
  4. Huncheol Lee, CheongWoo Lee and SeongDae Kim, 'Abrupt shot change detection using an unsupervised clustering of multiple features', Proc. of ICASSP2000, Vol. 4, pp. 2015-2018 https://doi.org/10.1109/ICASSP.2000.859228
  5. R. Brunelli, O. Mich, and C.Modena, 'A Survey of the Automatic Indexing of Video Date', Journal of Visual Communication and Image Representation, Vol.10, pp. 78-112,1999 https://doi.org/10.1006/jvci.1997.0404
  6. Ullas Gargi, Tangachar Kasturi, and Susan H. Srayer, 'Performance Characterization of Videl-Shot-Change Detection Methods', IEEE Trans. Circuits and Systems for Video Technology, pp.1-13, Vol. 10, No.1, 2000 https://doi.org/10.1109/76.825852
  7. Man-Kwan Shan and Suh-Yin Lee, 'Contentbased Video Tetrieval based on Similarity of Frame Sequence', Proc. Int'l Workshop on multimedia Database Management Systems, pp. 90-97, 1998
  8. Yap-Peng Tan, Sanjeev R. Kulkarmi and Peter J. Ramadge, 'A Framework for Measuring Video Similarity and Its Application to Video Query by Example', Proc. Int'l Conference on Image Processing, 1999 https://doi.org/10.1109/ICIP.1999.822864
  9. Monerva M. Yeung and Boon-Lock Yeo, 'Video Visualization for Compact Presentation and Fast Browsing of Pictorial Content', IEEE Trans Circuits and Systems for Video Technology, pp. 771-785, Vol. 7, No. 5, 1997 https://doi.org/10.1109/76.633496
  10. Monerva M, Yeung and Boon-Lock Yeo, 'Segmentation of Video by Clustering and Graph Analysis', Computer Vision and Image Understanding, Vol. 71, No. 1, pp. 94-109, 1998 https://doi.org/10.1006/cviu.1997.0628
  11. A. Nagasaka and Y. Tanaka, 'Automatic video indexing and full-video search for object appearances,' in Visual Database systems II, 1992
  12. B. Shahrary and D. C. Gibbon, 'Automatic generation of pictorial transcript of video programs', in Proc IS&T/SPIE Digital Video Compression: Algorithms and Technologies San Jose, CA, 1995, pp. 512-519
  13. Y, Zhuang, Y. Rui, T. S. Huang and S. Mehrotra, ' Adaptive Key frame Extraction using Unsupervised Clustering', Proc. ICIP, pp. 866-870, 1998
  14. Nikolaos D. Doulamis, Anastasios,D. Doulamis, Yannis, S. Avrithis and Stefanos D. Kollias, 'Video Content Representation using Optimal Extraction of Frames and Scene', Proceedings of ICIP 98, Vol.1, pp. 875-879, 1998 https://doi.org/10.1109/ICIP.1998.723660
  15. Hyun Sung Chang, Sanghoon Sulll and Sang Uk Lee, 'Efficient Video Indexing Scheme for Content-based Retroeval', IEEE Trans. Circuits and Systems for Video Technology, pp. 1269-1279, Vol. 9, 'No. 8, 1999 https://doi.org/10.1109/76.809161
  16. Minerva M. Yeung and Bede Liu, ' Efficient Matching and Clustering of Video Shoes', Proceedings of ICIP 95, 1995, pp. 338-342
  17. A. Hanjalic, R.L. Lagendijk, J. Boemond, 'A Content Representation', Proceedings of the First Intemational Workshop on Image Databases and Multi-Media Search, Amsterdam (NL), 1997
  18. R. L. Lagendijk,A. Hanjalic, M. Cecarelli, M. Soletic, and E. Persoon 'Visual Search in a SMASH System', Proceedings of ICIP 96, Vol. 3, pp. 671-674, 1996 https://doi.org/10.1109/ICIP.1996.560584
  19. Hun-Cheol Lee and Seong-Dae Kim, 'Rate-driven Key Frame Selection using Temporal Variation of Visual Content', Electronics Letters, Vol. 38, Issue 5, pp. 217-218, Feb. 2002 https://doi.org/10.1049/el:20020112