Journal of Korea Multimedia Society (한국멀티미디어학회논문지)

Korea Multimedia Society (한국멀티미디어학회)
권호 표지

Video Segmentation Method using Improved Adaptive Threshold Algorithm and Post-processing

개선된 적응적 임계값 결정 알고리즘과 후처리 기법을 적용한 동영상 분할 방법

  • Received : 2009.11.18
  • Accepted : 2010.04.17
  • Published : 2010.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

As a tool used for video maintenance, Video segmentation divides videos in hierarchical and structural manner. This technique can be considered as a core technique that can be applied commonly for various applications such as indexing, abstraction or retrieval. Conventional video segmentation used adaptive threshold to split video by calculating difference between consecutive frames and threshold value in window with fixed size. In this case, if the time difference between occurrences of cuts is less than the size of a window or there is much difference in neighbor feature, accurate detection is impossible. In this paper, Improved Adaptive threshold algorithm which enables determination of window size according to video format and reacts sensitively on change in neighbor feature is proposed to solve the problems above. Post-Processing method for decrement in error caused by camera flash and fast movement of large objects is applied. Evaluation result showed that there is 3.7% improvement in performance of detection compared to conventional method. In case of application of this method on modified video, the result showed 95.5% of reproducibility. Therefore, the proposed method is more accurated compared to conventional method and having reproducibility even in case of various modification of videos, it is applicable in various area as a video maintenance tool.

급격하게 증가하고 있는 동영상의 관리 도구로써 동영상을 계층적이고 구조적으로 구분하는 동영상 분할은 색인, 요약, 검색 등 다양한 응용 분야에서 공통적으로 적용될 수 있는 핵심 기술이라 할 수 있다. 기존의 적응적 임계값을 사용하는 동영상 분할 방법은 연속되는 프레임 간의 차이 값과 일정 간격의 크기를 갖는 윈도우에서 임계값을 계산하여 동영상 분할을 수행하였다. 그러나 이 경우, 윈도우의 크기보다 전환점의 발생 간격이 짧거나, 주변의 차이 값이 변동이 많으면, 정확한 검출을 하지 못한다. 상기 문제점을 개선하기 위하여 본 논문에서는 동영상의 포맷에 따라 윈도우의 크기를 결정하고, 윈도우 안에서 가중치를 사용하여 주변 값의 변화에 민감하게 반응하는 개선된 적응적 임계값 결정 알고리즘을 제안한다. 또한 카메라 불빛과 큰 물체의 빠른 움직임 등에 의한 오검출을 줄이기 위해 후처리 기법을 적용하였다. 실험을 통해서 제안된 방법은 기존 방법과 비교하여 3.7%의 성능 향상을 보이며, 변형된 동영상에서 95.5%의 재현성을 갖는 것을 확인하였다. 따라서 제안된 동영상 분할 방법은 기존 방법과 비교하여 정확성이 높고, 다양한 변형에도 재현성을 가지므로 동영상 관리 도구로써 많은 응용 분야에 적용할 수 있다.

Keywords

Acknowledgement

Supported by : 인하대학교

References

  1. N. Bhat and K. Nayar, "Ordinal measures for image correspondence," IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol. 20, No.4, pp. 415-423, 1998. https://doi.org/10.1109/34.677275
  2. I. Koprinska and S. Carrato, "Temporal Video Segmentation: A Survey," Signal Processing; Image Communication, Vol.16, pp.477-500, 2001. https://doi.org/10.1016/S0923-5965(00)00011-4
  3. G. Ananger and T.D.C. Little, "A survey of technologies for parsing and indexing digital video," Journal of Visual Communication and Image Representation, pp.28-43, 1996
  4. U. Gargi, R. Kasturi, and S. H. Strayer, "Performance Characterization of Video Shot Change Detection Methods," IEEE Trans. on Circuits and Systems for Video Technology, Vol.10, No.1, 2000.
  5. C. Cotsaces, N. Nikolaidis, and I. Pitas, "Video shot detection and condensed representation: a review," IEEE Signal Processing Magazine, Vol.23, No.2, pp. 28-37, 2006. https://doi.org/10.1109/MSP.2006.1621446
  6. H. J. Zhang, A. Kankanhalli, and S. W. Smoliar, "Automatic Partitioning of Full-motion Video," Proceeding of the second ACM on Multimedia Systems, Vol.1, No.1, pp. 10-28, 1993.
  7. A. Hampapur, R. Jain, and T. Weymouth, "Digital Video Segmentation," Proceeding of the second ACM on Multimedia, pp. 357-364, 1994.
  8. R. Kasturi, and R. Jain, "Dynamic Vision," IEEE Computer Society Press in Computer Vision: Principles, pp. 469-480, 1991.
  9. Y. Tonomura, "Video handing based on structured information for hypermedia systems in," International Conference Multimedia Information Systems, pp. 333-344, 1991.
  10. H. Ueda, T. Miyatake, and S. Yoshizawa, "IMPACT: An Interactive Natural-motion-picture Dedicated Multimedia Authoring System," Proceeding of the ACM on Human Factors in Computing Systems, pp. 343-350, 1991.
  11. A. Nagasaka, and Y. Tanaka, "Automatic Video Indexing and Full-Video Search for Object Appearances," Proceeding of the IFIP on Visual Database Systems II, pp. 113-127, 1992.
  12. U. Gragi, R. Kasturi, and S. Antani, "Evaluation of video sequence indexing and hierarchical video indexing," Proceeding of the SPIE on Storage and Retrieval in Image and Video Databases, pp. 1522-1530, 1995,
  13. E. Tsamoura, "Video Shot Meta-segmentation based on Multiple Criteria for Gradual Transition Detection," International Workshop on Content-based Multimedia Indexing, pp. 51-57, 2008
  14. D. Zhang and HJ. Zhang, "A New Shot Boundary Detection Algorithm" Proceeding of the SPIE on Advances in Multimedia Information Processing, Vol.2195, pp. 63-70, 2001