Journal of KIISE:Computing Practices and Letters (한국정보과학회논문지:컴퓨팅의 실제 및 레터)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

A Surveillance System Combining Model-based Multiple Person Tracking and Non-overlapping Cameras

모델기반 다중 사람추적과 다수의 비겹침 카메라를 결합한 감시시스템

  • 이윤미 (덕성여자대학교 전산정보통신대학원) ;
  • 이경미 (덕성여자대학교 컴퓨터공학부)
  • Published : 2006.08.01
Download PDF
⟨ Previous Next ⟩

Abstract

In modem societies, a monitoring system is required to automatically detect and track persons from several cameras scattered in a wide area. Combining multiple cameras with non-overlapping views and a tracking technique, we propose a method that tracks automatically the target persons in one camera and transfers the tracking information to other networked cameras through a server. So the proposed method tracks thoroughly the target persons over the cameras. In this paper, we use a person model to detect and distinguish the corresponding person and to transfer the person's tracking information. A movement of the tracked persons is defined on FOV lines of the networked cameras. The tracked person has 6 statuses. The proposed system was experimented in several indoor scenario. We achieved 91.2% in an averaged tracking rate and 96% in an averaged status rate.

현대사회는 광범위한 지역에 산재된 다수의 카메라로부터 사람을 자동적으로 식별하고 추적할 수 있는 감시시스템을 요구하고 있다. 본 논문에서는 넓은 시야의 확보가 용이한 고정된 다수의 비겹침 감시카메라와 사람 추적기술을 결합하여, 한 카메라에서 추적된 사람의 정보를 서버를 통해 다른 카메라에 전달하는 방법을 제안한다. 제안된 방법은 추적대상을 자동적으로 추적하고 서버에 전달함으로써, 한번 추적된 추적대상의 움직임 경로 및 추적 상태를 끝까지 추적할 수 있다. 본 논문에서는 추적대상을 식별하고 전달하기 위해 사람모델을 이용하였다. 서버를 통해 연결된 각 카메라들의 관계와 카메라 상에서 움직이는 사람의 이동은 FOV 라인에 의해 제약되어 추적대상의 정보전달에 이용되었다. 추적대상은 추적되는 동안 6 단계의 상태정보를 가진다. 제안된 시스템은 다양한 실내 동영상에 대해 실험되었으며, 91.2% 의 평균추적율과 96% 의 평균 상태율을 획득하였다.

Keywords

References

  1. O. Javed, Z. Rasheed, O. Alatas and M. Shah, 'KNIGHTM: A real-time surveillance system for multiple overlapping and non-overlapping cameras,' in proc. of the fourth International Conference on Multimedia and Expo, 2003 https://doi.org/10.1109/ICME.2003.1221001
  2. O. Javed, Z. Rasheed, K. Shafique and M. Shah, 'Tracking across in multiple cameras with disjoint views,' in proc. of the IEEE International Conference. Computer Vision, pp. 952 - 957, 2003 https://doi.org/10.1109/ICCV.2003.1238451
  3. P.D. O'Malley, M.C. Nechyba and AA Arroyo, 'Human activity tracking for wide-area surveillance,' in Proc. of Florida Conference on Recent Advances in Robotics, 2002
  4. C. Sminchisescu and A Telea, 'Human body pose estimation using silhouette shape analysis', in proc. of WSCG International Conference on Computer Graphics, Visualization and Corriputer Vision, 2002
  5. D. Makris, T. Ellis and J. Black, 'Bridging the gaps between cameras,' in prof. of IEEE Conference on Computer Vision and Pattern Recognition, 2004 https://doi.org/10.1109/CVPR.2004.1315165
  6. Q. Cai and J.K Aggarwal, 'Tracking human motion using multiple cameras,' Computer and Vision Research Center
  7. S. Khan and M. Shah, 'Consistent labeling of tracked objects in multiple cameras with overlapping field of view,' IEEE transactions on Pattern Analysis and Machine Intelligence, vol. 25, no. 10, 2003 https://doi.org/10.1109/TPAMI.2003.1233912
  8. S.L. Dockstader and AM. Tekalp, 'Multiple camera tracking of interacting and occluded human motion,' in proc. of the IEEE, vol. 89, no. 10, pp. 1441-1455, 2001 https://doi.org/10.1109/5.959340
  9. 이경미, 이윤미, '조명변화와 겹침에 강건한 적응적 모델 기반 다중객체 추적', 한국정보과학회논문지 : 소프트웨어 및 응용, vol. 32, no. 5, pp. 449-460, 2005
  10. A. Terrazas, 'Java Media APIs: Cross-platform imaging, media and visualization,' SAMS, 2002
  11. T.H. Chang and S. Gong, 'Tracking multiple people with a multi-camera system,' in proc. of European Workshop on Advanced Video based Surveillance Systems, 2001 https://doi.org/10.1109/MOT.2001.937977
  12. A Chilgunde, P. Kumar, S. Ranganath and H.W. Min, 'Multi-camera target tracking in blind regions of cameras with non-overlapping fields of view,' in proc. of British Machine Vision Conference, 2004
  13. R. Bowden and P. Kaewtrakulpong, 'Towards automated wide area visual surveillance: tracking objects between spatially-separated, uncalibrated views,' IEEE Image Signal Process, vol. 152, no. 2, 2005 https://doi.org/10.1049/ip-vis:20041233