효과적인 다봉 배경 모델링 및 물체 검출

Efficient Multimodal Background Modeling and Motion Defection

  • 발행 : 2009.06.15

초록

배경 모델링 및 물체 검출 기술은 실시간 비디오 처리 기술에서 중요한 부분을 차지하고 있다. 그동안 많은 연구들이 진행되었지만 안정적인 성능을 위해서는 아직도 상당한 계산량을 요구한다. 이 때문에 고해상도 영상 처리나 객체 추적, 행동 분석 및 대상 인식 등의 알고리즘과 함께 사용되는 경우, 실시간 처리에 어려움이 있다. 본 논문에서는 가장 일반적으로 쓰이는 배경 모델링 기법 중의 하나인 혼합정규모델(mixtures of Gaussian)을 근사화한 효과적인 다봉(multimodal) 배경 모델링 및 물체 검출 방법을 제안한다. 근사화의 타당성과 각 과정들을 유도 및 검증하였고, 실험을 통해 제안하는 알고리즘이 기존 방법의 안정성과 유연성을 유지하면서 3배 이상의 처리 속도를 나타냄을 보였다.

Background modeling and motion detection is the one of the most significant real time video processing technique. Until now, many researches are conducted into the topic but it still needs much time for robustness. It is more important when other algorithms are used together such as object tracking, classification or behavior understanding. In this paper, we propose efficient multi-modal background modeling methods which can be understood as simplified learning method of Gaussian mixture model. We present its validity using numerical methods and experimentally show detecting performance.

키워드

참고문헌

  1. W. Hu, T. Tan, L. Wang, S. Maybank, “A Survey on Visual Surveillance of Object Motion and Behaviors,” IEEE Trans. On systems, man, and cybernetics, pp. 334-351, 2004 https://doi.org/10.1109/TSMCC.2004.829274
  2. R. T. Collins, A. J. Lipton, T. Kanade, H. Fujiyoshi, D. Duggins, Y. Tsin, D. Tolliver, N. Enomoto, O. Hasegawa, P. Burt and L. Wixson "A System for Video Surveillance and Monitor-ing," Carnegie Mellon University, 2000
  3. I. Haritaoglu, D. Harwood, and S. Davis, “W4: real time surveillance of people and their acci-yectures,” IEEE Trans. Pattern Anal. Mach. Intell., pp. 809-830, 2000 https://doi.org/10.1109/34.868683
  4. C. R. Wren, A. Azarbayejani, T. Darrell, and A. P. Pentland, “Pfinder: Real-time tracking of the human body,” IEEE Trans. Pattern Anal. Mach. Intell., Vol.19, No.7, pp. 780-785, 1997 https://doi.org/10.1109/34.598236
  5. C. Stauffer, W. Grimsun, “Adaptive background mixture models for real-time tracking,” Proc. of the IEEE International Conference on Computer Vision and Pattern Recognition, pp. 246-252, 1999 https://doi.org/10.1109/CVPR.1999.784637
  6. A. Elgammal, H. Duraiswami, D. Harwood, and L. S. Davis, “Background and foreground modeling using nonparametric kernel density for visual surveillance,” Proc. IEEE. Vol.90, pp. 1151-1163, 2002 https://doi.org/10.1109/JPROC.2002.801448
  7. K. Toyoma, J. Krumm, B. Brumitt, and B. Meyers, "Wallflower: Piinciples and Practice of Background Maintenance," Proc. IEEE ICCV, pp. 255-261, 1999 https://doi.org/10.1109/ICCV.1999.791228
  8. Monari, E.,Pasqual, C, “Fusion of background estimation approaches for motion detection in non-static backgrounds,” AVSS, pp. 347-352, 2007 https://doi.org/10.1109/AVSS.2007.4425335
  9. A. Manzanera, J. C. Richefeu, "A robust and computationally efficient motion detection algo-rithm based on $\Sigma-\Delta$ background estimation," ICVGIP, 2004
  10. P. KaewTraKulPong and R. Bowden, "An Im-proved Adaptive Background Mixture Model for Real-Time Tracking with Shadow Detection," Proc. European Workshop Advanced Video Based Surveillance Systems, Sept. 2001
  11. D. Lee, "Effective Gaussian Mixture Learning for Viedo Background Subtraction," IEEE Trans. Pattern Anal. Mach. Intell. Vol.27, pp. 827-832, 2005 https://doi.org/10.1109/TPAMI.2005.102
  12. D. Park, H. Byun, "Nonstatic background model-ing including traffic region," Machine Learn-ing and Cybernetics, pp. 3423-3427, 2008 https://doi.org/10.1109/ICMLC.2008.4620996