은닉 마르코브 모델을 이용한 비디오 요약 시스템

Video Summarization Using Hidden Markov Model

  • 발행 : 2004.10.01

초록

본 논문에서는 비디오 검색을 위한 비디오 사진 분류 시스템을 제안하였다. 제안된 시스템은 3개의 모듈인 특징 추출, 은닉 마르코브 모델 생성, 그리고 비디오 사진 분류로 구성되어 있다. 같은 등급에 속한 비디오 화면들이 반드시 유사하지 않으므로 견실한 Hidden Markov Model을 구성하기 위해서 는 충분한 학습이 필요하였다. 제안된 시스템은 텔레비전 야구 중계 방송의 비디오 화면을 15가지 등급으로 분류하여 분석 및 하는 실험을 한 결과 평균 84.72%의 인식률을 얻을 수 있었다.

This paper proposes a system to analyze and summarize the video shots of baseball game TV program into fifteen categories. Our System consists of three modules: feature extraction, Hidden Markov Model (HMM) training, and video shot categorization. Video Shots belongs to the same class are not necessarily similar, so we require that the training set is large enough to include video shot with all possible variations to create a robust Hidden Markov Model. In the experiments, we have illustrated that our system can recognize the 15 different shot classes with a success ratio of 84.72%.

키워드

참고문헌

  1. E. Ardizzone, M. L.Casia, and D. Monlinelli. 'Motion and color based Video Indexing'. lCPR, Vienna, Austria, Aug. 1996
  2. R. W. Picard. 'A Society of Models for Video and Image Libraries'. Per. Camp. Sec Technical 1996
  3. S. W SmoIiar and Ⅱ. Zhang. 'Content-Based Video Indexing and Retrieval'. IEEE Multimedia, 1(2): 62-72, 1994 https://doi.org/10.1109/93.311653
  4. M. Das, E. Riseman, and B. Draper. 'FORCUS: Searching for multi-colored objects in a Diverse Image Database,' IEEE CVPR, pp.756-761, 1997
  5. Y. Deng, D. Mukherjee, 'Object-based Video Representation,' SPIE: Storage and Retrieval for Image and Video Databases Ⅵ, pp.203-213, 1998
  6. A. Ilampapur et al., 'Mirage Video Engine,' SPIE: Storage and Retrieval for Image and Video Databases V, pp.188-197, 1997
  7. J. IIung, S. R. Kumar, M. mitra, W. Zhu, and R. Zabih, Image Indexing Using Color Corrlograms, CVPR, pp.762-768, 1997
  8. W. Niblack et al., 'The QBIC Project: Querying Images By Content Using Color, Texture, and Shape,' SPIE: Storage and Retrieval for Image and Video Databases, pp.173-181, 1993
  9. E. Petrakis and C. Faloutsos, 'Similarity Searching in Medical Image Databases,' IEEE Transactions on Knowledge and Data Engineering 9(3) pp.435-447, 1997 https://doi.org/10.1109/69.599932
  10. B. IIom and B. G. Shunck, 'Determining optical flow', Artif. Intelli., vol.17, pp.185-203, 1981 https://doi.org/10.1016/0004-3702(81)90024-2
  11. Rabiner, L. R., 'A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition,' Proceedings of the IEEE, vol.77, No.2, pp.257-285, February 1989
  12. M. M. Yeung and B. L. Yeo, 'Time constrained Clustering for segmentation of Video into Story Units.' IEEE ICPR, pp.375-380, 1996
  13. M. M. Yeung and B. Liu. 'Efficient matching and clustering of video shots.' IEEE ICIP Vol. I, pp.338-341, 1995
  14. Y. Linde, A. Buzo, and R. Gray, 'An Algorithm for Vector Quantizer Design'. IEEE Transaction on Communications, Vol. COM-28, No.1, pp.84-85, January, 1980