The Journal of Korean Institute of Communications and Information Sciences (한국통신학회논문지)

The Korean Institute of Commucations and Information Sciences (한국통신학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Crowd Escape Behavior in Surveillance Video

감시 영상에서 군중의 탈출 행동 검출

  • Park, Junwook (Hanbat National University Dept. of Control and Instrumentation Engineering) ;
  • Kwak, Sooyeong (Hanbat National University Dept. of Electronics and Control Engineering)
  • Received : 2014.05.31
  • Accepted : 2014.07.24
  • Published : 2014.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents abnormal behavior detection in crowd within surveillance video. We have defined below two cases as a abnormal behavior; first as a sporadically spread phenomenon and second as a sudden running in same direction. In order to detect these two abnormal behaviors, we first extract the motion vector and propose a new descriptor which is combined MHOF(Multi-scale Histogram of Optical Flow) and DCHOF(Directional Change Histogram of Optical Flow). Also, binary classifier SVM(Support Vector Machine) is used for detection. The accuracy of the proposed algorithm is evaluated by both UMN and PETS 2009 dataset and comparisons with the state-of-the-art method validate the advantages of our algorithm.

본 논문에서는 감시 카메라 환경에서 발생할 수 있는 군중의 비정상 행동 검출 방법을 제안한다. 군중들의 비정상 행동을 산발적으로 퍼지면서 뛰는 행동, 한쪽 방향으로 갑자기 뛰는 행동 두 가지로 정의하였다. 이를 검출하기 위하여 영상에서 움직임 벡터를 추출하여 군중의 비정상 행동 검출에 적합한 서술자 MHOF(Multi-scale Histogram of Optical Flow)와 DCHOF(Directional Change Histogram of Optical Flow)제안하였으며, 이를 이진 분류기인 SVM(Support Vector Machine)을 이용하여 검출하였다. 제안한 방법은 공개 데이터셋인 UMN 데이터와 PETS 2009 데이터를 이용하여 성능을 평가하였고 다른 방법론과의 비교를 통해 제안하는 알고리즘의 우수성을 입증하였다.

Keywords

References

  1. A. Adam, E. Rivin, I. Shimshoni, and D. Reintz, "Robust real-time unusual event detection using multiple fixed-location monitors," IEEE Trans. Pattern Anal. Machine Intell., vol. 30, no. 3, pp. 555-560, Mar. 2008. https://doi.org/10.1109/TPAMI.2007.70825
  2. H.-S. Park and C.-S. Bae, "Real-time recognition and tracking system of multiple moving object," J. KICS, vol. 36, no. 7, pp. 421-427, Jul. 2011. https://doi.org/10.7840/KICS.2011.36C.7.421
  3. G. Bae, "Detection of abnormal behavior by scene analysis in surveillance video," J. KICS, vol. 36, no. 12, pp. 744-752, Dec. 2011. https://doi.org/10.7840/KICS.2011.36C.12.744
  4. T. Jang, Y. Shin, and J. Kim, "A study on the object extraction and tracking system for intelligent surveillance," J. KICS, vol. 38, no. 7B, pp. 589-595, Jul. 2013. https://doi.org/10.7840/kics.2013.38B.7.589
  5. R. Mehran, A. Oyama, and M. Shah, "Abnormal crowd behavior detection using social force model," IEEE Int. Conf. CVPR, pp. 935-942, Miami, FL, Jun. 2009.
  6. Y. Shi, Y. Gao, and R. Wang, "Real-time abnormal event detection in complicated scenes," Int. Conf. Pattern Recognition (ICPR), pp. 3653-3656, Istanbul, Aug. 2010.
  7. S. Wu, H.-S. Wong, and Y. Zhiwen, "A bayesian model for crowded escape behavior detection," IEEE Trans. Circuits and Syst. for Video Technol., vol. 24, no. 1, pp. 85-98, Jan. 2014. https://doi.org/10.1109/TCSVT.2013.2276151
  8. S. S. Pathan, A. Al-Hamadi, and B. Michaelis, "Incorporating social entropy for crowd behavior detection using SVM," Advances in Visual Computing, Springer Berlin Heidelberg, pp. 153-162, 2010.
  9. V. Vapnik, The nature of statistical learning theory, 2nd Ed., NY: Springer-verlag, 1995.
  10. UMN dataset, http://mha.cs.umn.edu/proj_events.shtml#crowd
  11. PETS 2009 dataset, http://pets2009.net/
  12. G. Farneback, "Two-frame motion estimation based on polynomial expansion," Lecture Notes in Comput. Sci., vol. 2749, pp. 363-370, Jun. 2003.
  13. D.-Y. Chen and P.-C. Huang, "Motion-based unusual event detection in human crowds," J. Visual Commun. Image Representation, vol. 22, no. 2, pp. 178-186, 2012.
  14. S. Wu, B. E. Moore, and M. Shah, "Chaotic invariants of lagrangian particle trajectories for anomaly detection in crowded scenes," IEEE Conf. Computer Vision and Pattern Recognition (CVPR), pp. 2054-2060, San Francisco, CA, Jun. 2010.