Journal of Digital Contents Society (디지털콘텐츠학회 논문지)

Digital Contents Society (한국디지털콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on a Violence Recognition System with CCTV

CCTV에서 폭력 행위 감지 시스템 연구

  • Shim, Young-Bin (SookMyung Women's University Dept. of Multimedia Science) ;
  • Park, Hwa-Jin (SookMyung Women's University Dept. of Multimedia Science)
  • Received : 2014.08.10
  • Accepted : 2015.02.12
  • Published : 2015.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

With the increased frequency of crime such as assaults and sexual violence, the reliance on CCTV in arresting criminals has increased as well. However, CCTV, which should be monitored by human labor force at all times, has limits in terms of budget and man-power. Thereby, the interest in intelligent security system is growing nowadays. Expanding the techniques of an objects behavior recognition in previous studies, we propose a system to detect forms of violence between 2~3 objects from images obtained in CCTV. It perceives by detecting the object with the difference operation and the morphology of the background image. The determinant criteria to define violent behaviors are suggested. Moreover, provable decision metric values through measurements of the number of violent condition are derived. As a result of the experiments with the threshold values, showed more than 80% recognition success rate. A future research for abnormal behaviors recognition system in a crowded circumstance remains to be developed.

학교폭력 및 성폭력 등의 범죄가 증가되어감에 따라 범인 검거에 있어서 CCTV에 대한 의존도가 높아지고 있다. 그러나 항상 사람 노동력으로 감시하기에는 경제력 및 인력의 한계가 있어 최근에는 지능형 보안 시스템으로 관심이 높아지고 있다. 따라서 기존에 연구한 객체 행동 인식 기법을 확장하여 본 연구에서는 CCTV에 획득되는 영상으로부터 2~3 객체간의 폭력 행위를 감지하는 시스템을 제안한다. 배경영상과의 차연산 및 모폴로지를 통해 객체를 검출하고 인식하여 추적한다. 폭력행위의 특징을 이용하여 폭력행위 판단 근거를 제시하였다. 더욱이, 여러 폭력 상황에 대한 측정을 통해 보다 객관적인 판단 메트릭 임계값을 도출하였다. 이 값을 바탕으로 폭력 행위 인식 실험을 진행한 결과 80% 이상의 인식 성공률을 보였으며, 향후연구로 다수 군중이 있는 상황 등에서의 이상행위 감지 시스템에 대한 연구가 남아있다.

Keywords

References

  1. Informatization Strategy Office, "Detailed promotion plan for local CCTV Integrated Control Center building support project in 2011," National Information Society Agency, 2010.11
  2. Y.B.Shim, H.J.Park,"A study on the surveillance of multiple object's dangerous behaviors," Journal of Digital Contents Society, vol.14, no.4, pp. 455-462, 2013.12 https://doi.org/10.9728/dcs.2013.14.4.455
  3. IVS Technology, http://www.ivstech.co.kr/?c=user&mcd=main_krf
  4. H.J.Park, "Monitoring system for an abnormal behaviors by object's tracking," Journal of Digital Contents Society, vol.14, no.4, pp.589-596, 2013.12 https://doi.org/10.9728/dcs.2013.14.4.589
  5. A. Saha, J.Mulherjee, and S.Sural, "New pixel-decimation patterns for block matching in motion estimation," Signal Processing Image Communication, vol.23, no.10,pp.725-738,2008 https://doi.org/10.1016/j.image.2008.08.004
  6. T.W.Jnag, Y.T. hin, J.B. Kim, " A study on the object extraction and tracking system for intelligent surveillance," SoonSil University, May, 2013
  7. D. Comaniciu, V. Ramesh, and P. Meer, "Kernel-based object tracking," IEEE Trans. Patt. Analy. Mach. Intel, Vol.25, pp.564-575, 2003. https://doi.org/10.1109/TPAMI.2003.1195991
  8. J. Shi and C. Tomasi, "Good features to track," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.593-600, 1994.
  9. Tao H. Sawhney, H. and Kumar, R. "Object tracking with bayesian estimation of dynamic layer representations," IEEE Trans. Patt. Analy. Mach. Intell, Vol.24 No1, pp.75-89, 2002. https://doi.org/10.1109/34.982885
  10. M. Black and A. Jepson, "Eigentracking: Robust matching and tracking of articulated objects using a view-based representation," Int. J. Comput. Vision Vol.26 No.1, pp.63-84, 1998. https://doi.org/10.1023/A:1007939232436
  11. S. Avidan, "Support vector tracking," IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.184-191, 2001
  12. M. Isard and A. Blake. "Condensation - conditional density propagation for visual tracking," Int. J. Comput. Vision, Vol.29 No.1, pp.5-28, 1998. https://doi.org/10.1023/A:1008078328650
  13. Huttenlocher. D, Noh. J, and Rucklidge. W.,"Tracking nonrigid objects in complex scenes," IEEE International Conference on Computer Vision (ICCV), pp. 93-101, 1993.
  14. Kang. J, Cohen. I,and Medioni. G, "Object reacquisition using geometric invariant appearance model," In International Conference on Pattern Recongnition (ICPR), pp.759-762, 2004.

Cited by

  1. Area Classification, Identification and Tracking for Multiple Moving Objects with the Similar Colors vol.65, pp.3, 2016, https://doi.org/10.5370/KIEE.2016.65.3.477
  2. 감시 카메라와 RFID를 활용한 다수 객체 추적 및 식별 시스템 vol.6, pp.2, 2015, https://doi.org/10.3745/ktccs.2017.6.2.51
  3. 환경설계를 통한 범죄예방 및 개선방안 vol.18, pp.4, 2015, https://doi.org/10.9728/dcs.2017.18.4.733
  4. 어린이집 CCTV 빅데이터의 활용을 위한 기초 연구 vol.13, pp.6, 2017, https://doi.org/10.14698/jkcce.2017.13.06.043
  5. 서비스 우선순위를 이용한 스마트 관제 서비스의 개선 vol.19, pp.5, 2015, https://doi.org/10.9728/dcs.2018.19.5.1003
  6. Improvement of Safe Return Service using Distance Information vol.20, pp.5, 2015, https://doi.org/10.9728/dcs.2019.20.5.1023
  7. 수직 히스토그램 기반 그림자 제거 알고리즘을 이용한 영상 감지 시스템 설계 및 구현 vol.24, pp.1, 2015, https://doi.org/10.6109/jkiice.2020.24.1.91
  8. Improvement of Service Rate in Smart Surveillance Service using Fixed Camera vol.22, pp.5, 2015, https://doi.org/10.9728/dcs.2021.22.5.847