방송공학회논문지 (Journal of Broadcast Engineering)

  • 제24권6호
  • /
  • Pages.939-947
  • /
  • 2019
  • /
  • 1226-7953(pISSN)
  • /
  • 2287-9137(eISSN)
한국방송∙미디어공학회 (The Korean Institute of Broadcast and Media Engineers)
권호 표지
DOI QR코드

DOI QR Code

SIFT를 이용한 장면전환 검출 및 필터링 기술

Scene Change Detection and Filtering Technology Using SIFT

  • 투고 : 2019.07.25
  • 심사 : 2019.10.29
  • 발행 : 2019.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

미디어 시장의 활성화로 영상의 압축, 검색, 편집, 저작권 보호등의 필요성이 높아지고 있다. 본 논문에서는 이 모든 분야에 사용되는 영상의 장면 전환을 검출하는 방법을 제안한다. 유통 과정에서 발생 가능한 해상도 변환, 자막 삽입, 압축, 영상 반전등의 변형이 추가되더라도 동일하게 장면 전환을 검출하기 위해 전처리 과정과 SIFT를 이용한 특징점 추출, 변형을 고려한 매칭 알고리즘을 제시한다. 또한 이를 필터링 기술에 적용하여 알고리즘에서 고려한 변형 이외의 변형에도 유효함을 확인한다.

With the revitalization of the media market, the necessity of compression, searching, editing and copyright protection of videos is increasing. In this paper, we propose a method to detect scene change in all these fields. We propose a pre-processing, feature point extraction using SIFT, and matching algorithm for detecting the same scene change even if distortions such as resolution change, subtitle insertion, compression, and flip are added in the distribution process. Also, it is applied to filtering technology and it is confirmed that it is effective for all transformations other than considering transform.

키워드

참고문헌

  1. KIET, Domestic single media market status and development possibility, KIET Industrial Economics Analysis, pp. 44-53, 2017.
  2. Y. M. Eom, S. I. Park, and C. W. Chung, “An analysis of Scene Change Detection using HEVC coding additional information,” Journal of Broadcast Engineering, Vol. 20, No. 6, pp. 871-879, Nov. 2015 https://doi.org/10.5909/JBE.2015.20.6.871
  3. TTA, Performance Evaluation of Video Contents Filtering, 2013
  4. M. D. Fabro, L. Boszormenyi, "State-of-the-art and future challenges in video scene detection: a survey," Multimedia Systems, Vol.19, No.5, pp.427-454, Oct. 2013. DOI: 10.1007/s00530-013-0306-4
  5. C. Jang, S. Lee, "Scene Detection for Movies and Dramas Using Primitive Scene Analysis," Journel of KIISE : Computing Practices and Letters, Vol.19, No.11, pp.601-605, Nov. 2013
  6. J. H. Yoo, H. S. Seok, and B. T. Zhang, "Bayesian Filtering for Background Change Detection in TV Dramas," Journal of KIISE: Computing Practices and Letters, Vol.18, No.4, pp. 341-345, Apr., 2012
  7. S. I. Cho, S. J. Kang, "Histogram Shape-Based Scene-Change Detection Algorithm," IEEE Access, 7, pp.27662-27667, 2019. doi: 10.1109/ACCESS.2019.2898889
  8. Korea Copyright Commission, "Hot Issues on the R&D : New Technology of Copyright," Newsletter, Vol.15, 2018
  9. S. K. Rakshit, et al., "VIDEO DATA FILTERING," US Patent 10,223,357, to International Business Machines Corporation, US Patent and Trademark Office, Washington D.C., 2016
  10. D. G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, Vol. 60, No. 2, pp. 91-110, Jan. 2004 https://doi.org/10.1023/B:VISI.0000029664.99615.94
  11. G. J. Bae, S. I. Cho, S.-J. Kang, and Y. H. Kim, ''Dual-dissimilarity measure-based statistical video cut detection,'' J. Real-Time Image Process., vol. 13, no. 1, pp. 1-11, Jun. 2017 https://doi.org/10.1007/s11554-017-0675-6
  12. G. Marchionini and G. Geisler, ''The open video digital library,'' Digit. Library Mag., vol. 8, no. 12, pp. 1082-9873, Dec. 2002.