The Journal of Korean Institute of Information Technology (한국정보기술학회논문지)

Korean Institute of Information Technology (한국정보기술학회)
권호 표지
DOI QR코드

DOI QR Code

Real-Time Change Detection Architecture Based on SOM for Video Surveillance Systems

영상 감시시스템을 위한 SOM 기반 실시간 변화 감지 기법

  • 김종원 (순천향대학교 전기통신시스템공학과) ;
  • 조정호 (순천향대학교 전기공학과)
  • Received : 2019.01.07
  • Accepted : 2019.02.10
  • Published : 2019.04.30
⟨ Previous Next ⟩

Abstract

In modern society, due to various accidents and crime threats committed to an unspecified number of people, individual security awareness is increasing throughout society and various surveillance techniques are being actively studied. Still, there is a decline in robustness due to many problems, requiring higher reliability monitoring techniques. Thus, this paper suggests a real-time change detection technique to complement the low robustness problem in various environments and dynamic/static change detection and to solve the cost efficiency problem. We used the Self-Organizing Map (SOM) applied as a data clustering technique to implement change detection, and we were able to confirm the superiority of noise robustness and abnormal detection judgment compared to the detection technique applied to the existing image surveillance system through simulation in the indoor office environment.

현대 사회는 불특정 다수를 대상으로 자행되는 각종 사고와 범죄 위협으로 인하여 사회 전반에 걸쳐 개인의 보안 의식이 증가되며 다양한 감시 기법이 활발히 연구되고 있으나, 여전히 단순 부주의 또는 오작동으로 인한 강인성 저하가 발생하여 보다 높은 신뢰성을 갖는 감시 기법이 요구된다. 이에, 본 논문에서는 다양한 환경 및 동·정적 변화 감지에서의 낮은 강인성을 보완하고 비용 효율성 문제를 해결하기 위한 실시간 변화감지 기법을 제안한다. 변화 감지 구현을 위해 데이터 군집화 기법으로 응용되고 있는 자기 조직화 신경망을 활용하였으며, 실내 사무실 환경에서의 모의실험을 통해 기존 영상 감시 시스템에서 응용되는 감지 기법 대비 뛰어난 잡음 강인성과 이상 감지 판단의 우수성을 확인할 수 있었다.

Keywords

References

  1. M. L. Wang, C. C. Huang, and H. Y. Lin, "Intelligent Surveillance System Based on Omnidirectional Vision Sensor", IEEE Cybernetics and Intelligent Systems, Jun. 2006.
  2. M. Valera and S. A. Velastin, "distributed surveillance systems: a review", IEEE Vision, Image and Signal Processing, Vol. 152, No. 2, pp. 192-204, Apr. 2005. https://doi.org/10.1049/ip-vis:20041147
  3. F. Ortega-Zamorano, M. A. Molina-Cabello, E. Lopez-Rubio, and E. J. Palomo, "Smart motion detection sensor based on video processing using self-organizing maps", Expert Systems With Applications, Vol. 64, pp. 476-489, Dec. 2016. https://doi.org/10.1016/j.eswa.2016.08.010
  4. D. Vallejo, F. J. Villanueva, J. A. Albusac, C. Glez-Morcillo, and J. J. Castro-Schez, "Intelligent Surveillance for Understanding Events in Urban Traffic Environments", International Journal of Distributed Sensor Networks, Vol. 10, No. 8, Aug. 2014.
  5. M. L. Wang, C. C. Huang, and H. Y. Lin, "An Intelligent Surveillance System Based on an Omnidirectional Vision Sensor", IEEE Conference on Cybernetics and Intelligent Systems, Jul. 2006.
  6. T. Kohonen, "The self-organizing map", Neurocomputing, Vol. 21, pp. 1-6, May 1998. https://doi.org/10.1016/S0925-2312(98)00030-7
  7. R. Dlugosz, T. Talaska, W. Pedrycz, and R. Wojtyna, "Realization of the conscience mechanism in CMOS implementation of winner-take-all self-organizing map networks", IEEE Transactions on Neural Networks Vol. 21 No. 6, pp. 961-971, Jun. 2010. https://doi.org/10.1109/TNN.2010.2046497
  8. A. Ultsch and H. P. Siemon, "Kohonen's Self Organizing Feature Maps for Exploratory Data Analysis", International Neural Networks Conference (INNC), pp. 305-308, 1990.
  9. D. L. Olson and D. Delen, "Advanced Data Mining Techniques", Springer, pp. 138, Feb. 2008.
  10. C. Zhan, X. Duan, S. Xu, Z. Song, and M. Luo, "An improved moving object detection algorithm based on frame difference and edge detection", Image and Graphics, pp. 519-523, Aug. 2007.
  11. I. Cohen and G. Medioni, "Detecting and Tracking moving objects for video surveillance", IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Vol. 2, pp. 319-325, Jun. 1999.
  12. J. A. Vijverberg, M. J. H. Loomans, C. J. Koeleman, and P. H. N. de With, "Global illumination Compensation for Background Subtraction Using Gaussian-Based Background Difference Modeling", IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. , Sep. 2009.
  13. Z. Zivkovic and F. van der Heijden, "Efficient adaptive density estimation per image pixel for the task of background subtraction", Pattern recognition letters, Vol. 27, No. 7, pp. 773-780, May 2006. https://doi.org/10.1016/j.patrec.2005.11.005