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

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

중간값 필터와 신경망 회로를 사용한 자동 컷 검출 알고리즘

An Automatic Cut Detection Algorithm Using Median Filter And Neural Network

  • 전승철 (漢陽大學敎 컴퓨터工學과 VIP&MC 硏究室) ;
  • 박성한 (漢陽大學敎 컴퓨터工學과 VIP&MC 硏究室)
  • Jun, Seung-Chul (VIP&MC Lab. Department of Computer Science & Engineering HanYang University) ;
  • Park, Sung-Han (VIP&MC Lab. Department of Computer Science & Engineering HanYang University)
  • 발행 : 2002.07.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문은 MPEG 스트림 데이터에서 효과적으로 화면 전환 경계를 찾아내는 알고리즘을 제안한다. 이를 위하여 먼저 연속적인 장면의 변화 정도를 표시하는 척도로써 히스토그램 차이 값(histogram difference value)과 픽셀 차이 값(pixel difference value)을 각각 하나의 신호로 취급한다. 이 신호에 중간 값 필터를 적용하여 얻어진 값과 원래의 신호의 차이값인 MFD(Median filtered difference) 값을 구한다. 이렇게 얻어진 MFD의 값이 크면 회면 전환이 일어남을 나타내며 따라서 컷 검출의 기준이 될 수 있다. 또한, 인공 신경망을 사용하여 컷 경계가 되는 MFD값의 문턱치를 결정한다. 제안된 알고리즘은 변화량이 심한 동영상이나 급작스럽게 밝아지는 프레임을 포함하는 동영상에서 적절히 컷 전환을 검출함을 보여 준다. 실험결과에서 제안된 알고리즘의 성능을 보여준다.

In this paper, an efficient method to find shot boundaries in the MPEG video stream data is proposed. For this purpose, we first assume that the histogram difference value(HDV) and pixel difference value(PDV) as an one dimensional signal and apply the median filter to these signals. The output of the median filter is subtracted from the original signal to produce the median filtered difference(MFD). The MFD is a criterion of shot boundary. In addition a neural network is employed and trained to find exactly cut boundary. The proposed algorithm shows that the cut boundaries are well extracted, especially in a dynamic video.

키워드

참고문헌

  1. Y. Deng and B.B.Manjunath, 'Content-based Search of Video Using Color, Texture and Motion', 1997 IEEE Intemational Conference on Image Processing, 1997, volume I, pp. 534-537 https://doi.org/10.1109/ICIP.1997.638826
  2. E. Sahouria ans A. Zakhor, 'Motion Indexing of Video', 1997 IEEE International Conference on Image Processing, 1997, volume I, pp. 526-529 https://doi.org/10.1109/ICIP.1997.638824
  3. K. J . Han and Ahmed H. Tewfik, 'Eigen-Image Based Video Segmentation and Indexing',1997 IEEE International Corference on Image Processing, October 26-29, volume II, pp 538-541 https://doi.org/10.1109/ICIP.1997.638827
  4. B. L. Yeo and B. Liu, 'Rapid scene change detection on compressed vido', IEEE Transaction on Circuit and Systems for Video Technilogy, Vol 5, Num 6, pp. 533-544, Dec, 1995 https://doi.org/10.1109/76.475896
  5. Y. Nakajima, 'Umiversal scenc change detection on MPEG-coded data domain', Visual Communications and Image Processing 99, 12-14 Februay 1997 San Jose, California, volume 3024 https://doi.org/10.1117/12.263179
  6. T. Kanek and O. Hori, 'Cut Detection Technique from MPEG Compressed Video Using Likelihood Ratio Test', 14th Intemational Conference on Pattem Recognition, August 16-20, 1998 Brisbane, Australia, volume II, pp. 1481-1483 https://doi.org/10.1109/ICPR.1998.711985
  7. M Lee and B.W. Hwang and S. Sull and S.W. Lee, 'Automic video Paring Using Shot Boundary Detection and Camera Operation Analysis', 14th Intermational Conference 01 Pattern Recognition, August 16-20, 1998 Brisbane, Austrolia, volume II, pp. 1481-1483
  8. M,R. Naphade and P.Mehrotra and A. M. Ferman and J. Wamick and T, S. Huang and A. M. Tekap, 'A High-Performance Shot Boundary Detection Algorithm Using Multiple Ques', 1988 IEEE International Conference on Image Trocessing, 1998, volume I, pp. 884-887 https://doi.org/10.1109/ICIP.1998.723662
  9. M. Sugano and Y, Nakajima and H, Yanagihara and A. Yoneyama, 'A Fast Scene Detection on MPEG Docing Parameter Domain', 1998 IEEE Imternational Conference on Image Processing, volume I, pp. 888-892