Journal of the Institute of Electronics Engineers of Korea CI (전자공학회논문지CI)

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

Moving Object Detection using Clausius Entropy and Adaptive Gaussian Mixture Model

클라우지우스 엔트로피와 적응적 가우시안 혼합 모델을 이용한 움직임 객체 검출

  • Park, Jong-Hyun (School of Electronic and Computer Engineering, Chonnam National University) ;
  • Lee, Gee-Sang (School of Electronic and Computer Engineering, Chonnam National University) ;
  • Toan, Nguyen Dinh (School of Electronic and Computer Engineering, Chonnam National University) ;
  • Cho, Wan-Hyun (Dept. of Statistical, Chonnam National University) ;
  • Park, Soon-Young (Department of Electronics Engineering, Mokpo National University)
  • 박종현 (전남대학교 전자컴퓨터공학부) ;
  • 이귀상 (전남대학교 전자컴퓨터공학부) ;
  • 또안 (전남대학교 전자컴퓨터공학부) ;
  • 조완현 (전남대학교 통계학과) ;
  • 박순영 (목포대학교 전자공학과)
  • Published : 2010.01.25
Download PDF
⟨ Previous Next ⟩

Abstract

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. In this paper, we propose a novel algorithm for the detection of moving objects that is the entropy-based adaptive Gaussian mixture model (AGMM). First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussians. Experiment results demonstrate that our method can detect motion object effectively and reliably.

비디오 시퀀스에서 움직임 있는 객체의 실시간 검출 및 추적은 스마트 감시 시스템에서 매우 중요한 요소로 분류되고 있다. 본 논문에서 우리는 움직임이 있는 객체의 검출을 위해 클라우지우스 엔트로피와 적응적 가우시안 혼합모델을 사용한 객체 검출 방법을 제안한다. 먼저, 엔트로피의 증가는 일반적으로 불안전한 조건에서 많은 엔트로피의 변화가 발생한 경우 복잡성 및 객체의 움직임이 증가함을 의미한다. 만약 순간적으로 엔트로피 변화가 큰 화소는 움직임 객체에 속한다고 고려하여 움직임 분할 특성을 적용한다. 따라서 우리는 먼저 클라우지우스 엔트로피 이론을 적용하여 엔트로피에 대한 에너지 변화량을 dense 맵으로 변환한다. 두 번째로 우리는 움직임 객체를 검출하기 위해 적응적 가우시안 혼합 모델을 적용하였다. 실험 결과에서 제안된 방법이 효율적으로 움직임이 있는 객체를 검출할 수 있었다.

Keywords

References

  1. A. Hampapur, L. Brown, J. Connell, A. Ekin, N. Haas, M. Lu, H. Merkl, S. Pankanti, A. Senior, C.F. Shu, Y..L. Tian, "Smart video surveillance," IEEE Signal Processing Magazine, no. 38-51, pp. 38-2005.
  2. L. Wang, W. Hu, and T. Tan, "Recent developments in human motion analysis," Pattern Recognition, vol. 36, pp 586-601, 2003.
  3. Y. Dedeoglu, "Moving objects detection, tracking and classification for smart video surveillance," Master's Thesis, Depart. of Computer Eng., Bilkent University, Ankara, 2004.
  4. I. Haritaoglu, D. Harwood, and L. S. Davis, "A real time system for detecting and tracking people," In Computer Vision and Pattern Recognition, pp 962-967, 1998.
  5. A. M. Mclvor, "Background subtraction techniques," In Proc. of Image and Vision Computing, Auckland, NewZealand, 2000.
  6. C. Stauffer and W. E. L. Grimson, "Learning Patterns of Activity Using Real-Time Tracking," IEEE Trans. on PAMI, vol. 22, no. 8, pp 747-757, 2000. https://doi.org/10.1109/34.868677
  7. J. Rittscher, J. Kato, S. Joga, A. Blake, "A probabilitic background model for tracking," Lecture Notes in Computer Science , vol. 1843, pp. 336-350, 2000.
  8. R. T. Collins, A.J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt, L. Wixon, "A system for video surveillance and monitoring," Technical report CMU-RI-TR-00-12, Robotics Institute, Carnegie Mellon University, 2000.
  9. J. Barron, D. Fleet, and S. Beauchermin, "Performance of Optical Flow Techniques," International Journal of Computer Vision, vol. 12, pp 42-77, 1994. https://doi.org/10.1016/0262-8856(94)90054-X
  10. N. Paragios and R. Deriche, "Geodesic active contours and level sets for the detection and tracking of motion objects," IEEE Trans. on PAMI, vol. 22, no. 3, pp 266-279, 2000. https://doi.org/10.1109/34.841758
  11. N. Paragios and R. Deriche, "Geodesic active regions and level sets methods for motion estimation and tracking," Computer Vision and Image Understanding, vol. 97, pp 259-282, 2005. https://doi.org/10.1016/j.cviu.2003.04.001
  12. H. Bao and Z. Zhang, "Motion objects segmentation using a new level set based method," Lecture Notes in Computer Science 3331, pp 312-318, 2004.
  13. N. Lu, J. Wang, Q. H. Wu and L. Yang, "An improved motion detection method for real-time surveillance," International Journal of Computer Science, vol. 35, pp. 1-16, 2008. https://doi.org/10.1007/s10915-007-9157-5
  14. Y.L. Tian, A. Hampapur, "Robust salient motion detection with complex background for Real-Time Video Surveillance," IEEE Workshop on Motion and Video Computing, vol. 2, 2005.
  15. P. Pierre, A to Z of Thermodynamics, Oxford University Press, 1998.
  16. 고은진, 원종호, 배창석, "동작분할을 위한 Clausius Normalized Field," 영상처리 및 이해에 관한 워크삽, 2009.
  17. C. Stauffer and W. E. L. Grimson, "Adaptive background mixture models for real time tracking," IEEE Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 246-252, 1999.
  18. J. Migdal and W. Eric L. Grimson, "Background Subtraction Using Markov Threshold," IEEE Workshop on Motion and Video Computing, vol. 2, pp. 58-65, 2005.
  19. H. L. Ribeiro and A. Gonzaga, "Hand Image Segmentation in Video Sequence by GMM: a Comparative Analysis," Computer Graphics and Image Processing, pp. 357-364, 2006.
  20. 박장한, 이재익, "적외선 영상에서 배경 모델링 기반의 실시간 객체 탐지 시스템," 대한전자공학회 논문지, vol. 46, no. 4, pp. 102-109, 2009.