Journal of the Institute of Electronics and Information Engineers (전자공학회논문지)

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

DOI QR Code

Parallel Design and Implementation of Shot Boundary Detection Algorithm

샷 경계 탐지 알고리즘의 병렬 설계와 구현

  • Received : 2013.09.24
  • Published : 2014.02.25
Download PDF
⟨ Previous Next ⟩

Abstract

As the number of high-density videos increase, parallel processing approaches are necessary to process a large-scale of video data. When a processing method of video data requires thousands of simple operations, GPU-based parallel processing is preferred to CPU-based parallel processing by way of reducing the time and space complexities of a given computation problem. This paper studies the parallel design and implementation of a shot-boundary detection algorithm. The proposed shot-boundary detection algorithm uses pixel brightness comparisons and global histogram data among the blocks of frames, and the computation of these data is characterized with the high parallelism for the related operations. In order to maximize these operations in parallel, the computations of the pixel brightness and histogram are designed in parallel and implemented in NVIDIA GPU. The GPU-based shot detection method is tested with 10 videos from the set of videos in National Archive of Korea. In experiments, the detection rate is similar but the computation time is about 10 time faster to that of the CPU-based algorithm.

최근 고화질 영상의 증가와 더불어 대용량 영상 데이터의 처리는 높은 연산이 요구되어 병렬 처리 설계가 선택되고 있다. 영상 처리에서 나타나는 많은 단순 연산이 병렬처리 가능한 경우, CPU 기반 병렬처리보다는 GPU 기반 병렬처리를 적용하는 것이 계산문제의 시간과 공간 계산 복잡도를 줄일 수 있다. 본 논문은 영상에서 샷 경계 탐지 알고리즘의 병렬 설계와 구현을 연구하였다. 제안하는 샷 경계 탐지 알고리즘은 프레임 간 지역 화소 밝기 비교와 전역 히스토그램 정보를 이용하는데, 이들 데이터의 계산은 대량의 데이터에 대한 높은 병렬성을 갖는다. 이들 연산의 병렬처리를 최대화하기 위해 화소 밝기와 히스토그램의 계산을 NVIDIA GPU에서 병렬 설계 하였다. GPU 기반 샷 탐지 방법은 국가기록원에서 선택된 10개의 비디오 데이터에 대한 성능 테스트를 수행하였다. 테스트에서 GPU 기반 알고리즘의 탐지율은 CPU 기반 알고리즘과 유사하였으나 약 10배의 연산 속도가 개선되었다.

Keywords

References

  1. Jinhui Yuan, Huiyi Wang, Lan Xian, Wujie Zheng, Jianmin Li, Fuzong Li, Bo Zhang, "A Formal Study of Shot Boundary Detection," IEEE Trans. on Circuits and Systems for Video Technology, Vol. 17, No. 2, pp. 168-186, Feb. 2007. https://doi.org/10.1109/TCSVT.2006.888023
  2. J. G. Han, Y. S. Ko, S. H. Suh, S. H. Ha, "Performance Enhancement of Scaling Filter and Transcorder using CUDA", Journal of Korean Institute of Information Scientists and Engineers, Vol. 16, No. 4, pp. 507-511, Apr. 2010.
  3. NVIDIA, NVIDIA Manufacturing Day 2013, [online]Available:https://registration.gputechconf.com/form/session-listing
  4. H. J. Jhang, A. Kankanhalli, S. W. Smoliar, "Automatic Partitioning of Full-Motion Video," Multimedia Systems, Vol. 1, No. 1, pp. 10-28, June 1993. https://doi.org/10.1007/BF01210504
  5. Xiaoquan Yi, Nam Ling, "Fast Pixel-Based Video Scene Change Detection," IEEE Int. Symposium on Circuits and Systems, Vol. 4, pp. 3443-3446, May 2005
  6. A. Nagasaka, Y. Tanaka, "Automatic Video Indexing and Full-Video Search for Object Appearances," IFIP Proceeding of Visual Database Systems, pp. 113-127, 1992.
  7. Y. W. Han, S. I. Cheong, S. J. Kim, S. Y. Lee, S. H. Kim, "Improving Histogram Scene Change Detection Method Using Motion Vector," Proceedings of Fall Conf. on Korean Institute of Information Scientists and Engineers, Vol. 26, No. 2, pp. 410-412, Oct. 1999
  8. B. H. Shekar, K. Holla K. Raghurama, Kumari M. Sharmila, "Video Cut Detection Using Chromaticity Histogram," Int. Journal of Machine Intelligence, Vol. 3, No. 4, pp. 371-375, Dec. 2011
  9. Z. Cernekova, C. Kotropoulos, I. Pitas, "Video Shot Segmentation Using Singular Value Decomposition," Proc. 2003 IEEE Int. Conf. Multimedia and Expo, Baltimore, Maryland, Vol. 2, pp. 301-304, July 2003.
  10. Priyadarshinee Adhikari, Neeta Gargote, Jyothi Digge, B. G. Hogade, "Abrupt Scene Change Detection," World Academy of S, cience, Engineering and Technology 42 2008, No. 18, pp. 711-716, June 2008.
  11. R. Zabih, J. Miller, K. Mai, "A Feature-based Algorithm for Detecting and Classification Production effects," ACM Multimedia System, Vol. 7, No. 1, pp. 119-128, March 1999. https://doi.org/10.1007/s005300050115
  12. Robert A. Joyce, "Temporal Segmentation of Video using Frame and Histogram-Space," IEEE Trans. on Multimedia, Vol. 8, No. 1, pp. 130-140, Feb. 2006. https://doi.org/10.1109/TMM.2005.861285
  13. Matsumoto, Kazunori, "SVM-Based Shot Boundary Detection with a Novel Feature," IEEE Int. Conf. on Multimedia and Expo, pp. 1837-1840, July 2006.
  14. J. K. Jin, J. H. Cho, J. H. Jeong, "Fast Scene Change Detection Using Macro Block Information and Spatio-temporal Histogram," The Institute of Electronics Engineers of Korea, Vol. 48, No. 1, pp. 141-148, Jan. 2011.
  15. NVIDIA, CUDA C Best Practices Guide, [online] Available:http://docs.nvidia.com/cuda/cuda-c-best-practices-guide/index.html
  16. David B. Kirk, Wenmei W. Hwu, Programming Massively Parallel Processors:A Hands-on Approach, Elsevier, pp. 99-103, 2010.
  17. Jason Sanders, Edward Kandrot, CUDA By Example An Introduction to General-Purpose GPU Programming, Addison Wesley, pp. 79-81, 2010.
  18. Pablo Toharia, Oscar D. Robles, Ricardo Suarez, Jose Luis Bosque, Luis Pastor, "Shot Boundary Detection Using Zernike Moments In Multi-GPU Multi-CPU Architectures," Journal of Parallel and Distributed Computing, Vol. 72, No. 9, pp. 1127-1133, sep. 2012. https://doi.org/10.1016/j.jpdc.2011.10.011
  19. I. S. Jeong, O. J. Kwon, "Video Shot Boundary Detection using Relative Difference between Frames," Optical Engineering, Vol. 42, No. 3, pp.604-605, March 2003. https://doi.org/10.1117/1.1547771
  20. Shane Cook, CUDA Programming A Developer's Guide to Parallel Computing with GPUs, Elsevier, pp. 97-103, 2013.