대한전자공학회논문지SP (Journal of the Institute of Electronics Engineers of Korea SP)

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

지능형 비디오 분석을 위한 적응적 배경 생성 기반의 이상행위 검출

Abnormal Behavior Detection Based on Adaptive Background Generation for Intelligent Video Analysis

  • Lee, Seoung-Won (Dept. of Image Engineering. Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Kim, Tae-Kyung (Dept. of Image Engineering. Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University) ;
  • Yoo, Jang-Hee ;
  • Paik, Joon-Ki (Dept. of Image Engineering. Graduate School of Advanced Image Science, Multimedia, and Film, Chung-Ang University)
  • 투고 : 2010.08.31
  • 심사 : 2010.11.29
  • 발행 : 2011.01.25
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

지능형 비디오 분석시스템은 불특정 다수의 객체가 가지는 행동을 분석하고, 불의의 사고를 사전에 예측하여 관리자에게 경고를 전달하는 기술을 필요로 한다. 본 논문은 적응적으로 배경을 생성하여 월담, 실신, 버려진 물체, 배회와 같이 사전에 정의된 이상행위를 분석하는 기술을 제안한다. 제안된 비디오 분석 시스템은 배경 생성과 이상 행위 분석 모듈로 구성된다. 강건한 배경 생성을 위해서 영상 내의 움직임 변화를 검출하여 매 순간마다 움직임이 없는 영역을 지속적으로 갱신하고, 이를 기반으로 객체를 검출한다. 또한 객체 검출의 정확성을 높이기 위해 검출된 결과에서 잡음과 그림자 제거 단계를 추가하였다. 이상행위 분석 모듈에서는 검출된 객체로부터 무게 중심, 실루엣, 크기, 이동 궤적 정보를 추출한다. 이때 이상행위의 판단은 월담, 실신, 버려진 물체, 배회에 따라 시나리오 환경으로 구성하고 분석하였다. 실험 결과에서 제안된 시스템은 복잡한 배경 환경에서도 이동 객체 검출 및 이상행위 분석이 가능하였다.

Intelligent video analysis systems require techniques which can predict accidents and provide alarms to the monitoring personnel. In this paper, we present an abnormal behavior analysis technique based on adaptive background generation. More specifically, abnormal behaviors include fence climbing, abandoned objects, fainting persons, and loitering persons. The proposed video analysis system consists of (i) background generation and (ii) abnormal behavior analysis modules. For robust background generation, the proposed system updates static regions by detecting motion changes at each frame. In addition, noise and shadow removal steps are also were added to improve the accuracy of the object detection. The abnormal behavior analysis module extracts object information, such as centroid, silhouette, size, and trajectory. As the result of the behavior analysis function objects' behavior is configured and analyzed based on the a priori specified scenarios, such as fence climbing, abandoning objects, fainting, and loitering. In the experimental results, the proposed system was able to detect the moving object and analyze the abnormal behavior in complex environments.

키워드

참고문헌

  1. 원병철, "스토리지 활용한 보안시스템 구축사례," 월간 시큐리티 월드, 제 157권, 42-43쪽, 2010년 2월
  2. 임현주, "2010년 이 기업을 주목하라," 월간 CCTV 저널, 제 12권, 69-84쪽, 2010년 1월
  3. A. Hampapur, S. Borger, L. Brown, C. Carson, J. Connell, M. Lu, A. Senior, V. Reddy, C. Shu, and Y. Tian, "S3: the IBM smart surveillance system: from Transactional systems to observational systems," Proc. Int. Conf. Acoustics, Speech and Signal Processing, Vol. 4, pp. 1385-1388, April 2007.
  4. T. Cootes, C. Taylor, D. Cooper, and J. Graham, "Training models of shape from sets of examples," Proc. Int. Conf. British Machine Vision, pp. 9-18, September 1992.
  5. A. Koschan, S. Kang, J. Paik, B. Abidi, and M. Abidi, "Color active shape models for tracking non-rigid objects," Pattern Recognition Letters, Vol. 24, pp. 1751-1765, July 2003. https://doi.org/10.1016/S0167-8655(02)00330-6
  6. T. Kim, J. Im, and J. Paik, "Video object segmentation and its salient motion detection using adaptive background generation," IET Electronics Letters, Vol. 45, pp. 542-543, May 2009. https://doi.org/10.1049/el.2009.0663
  7. S. Velastin, B. Boghossian, B. Lo, J. Sun, and M. Vicencio-Silva, "PRISMATICA: toward ambient intelligence in public transport environments," IEEE Trans. Systems, Man, Cybernetics, Vol. 35, no. 1, pp. 164-182, January 2005.
  8. N. Bird, O. Masoud, N. Papanikolopoulos, and A. Isaacs, "Detection of loitering individuals in public transportation areas," IEEE Trans. Intelligent Transportation Systems, Vol. 6, no. 2, pp. 167-177, June 2005. https://doi.org/10.1109/TITS.2005.848370
  9. P. Spagnolo, A. Caroppo, M. Leo, T. Martiriggiano, and T. D'Orazio, "An abandoned/removed objects detection algorithm and its evaluation on PETS datasets," Proc. Int. Conf. Video, Signal Based Surveillance, pp. 17-21, November 2006.
  10. E. Yu and J. Aggarwal, "Human action recognition with extremities as semantic posture representation," Proc. Int. Conf. Computer Vision, Pattern Recognition, pp. 1-8, June 2009.
  11. A. Singh, S. Sawan, M. Hanmandlu, V. Madasu, and B. Lovell, "An abandoned object detection system based on dual background segmentation," Proc. Int. Conf. Advanced Video, Signal Based Surveillance, pp. 352-357, September 2009.
  12. B. Lei and L. Xu, "Real-time outdoor video surveillance with robust foreground extraction and object tracking via multi-state transition management," Pattern Recognition Letters, Vol. 27, pp. 1816-1825, November 2006. https://doi.org/10.1016/j.patrec.2006.02.017
  13. M. Hu, "Visual pattern recognition by moment invariants," IRE Trans. Information Theory, Vol. 8, no. 2, pp. 179-187, February 1962. https://doi.org/10.1109/TIT.1962.1057692
  14. i-LIDS dataset for AVSS 2007.