한국인터넷방송통신학회논문지 (The Journal of the Institute of Internet, Broadcasting and Communication)

  • 제10권6호
  • /
  • Pages.23-29
  • /
  • 2010
  • /
  • 2289-0238(pISSN)
  • /
  • 2289-0246(eISSN)
한국인터넷방송통신학회 (The Institute of Internet, Broadcasting and Communication)
권호 표지

시각적 가려짐을 극복하는 강인한 유기물 탐지 기법

Robust Detection Technique for Abandoned Objects to Overcome Visual Occlusion

  • 김원 (우송대학교 컴퓨터정보학과)
  • 투고 : 2010.11.14
  • 심사 : 2010.12.15
  • 발행 : 2010.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

오늘날은 사회 안전을 강화하기 위하여 공공장소에서 유기물을 자동으로 검출하는 지능적 비전 감시 시스템을 설계하는 것이 필요한 때이다. 그런데, 이미 인지된 유기물의 일부분 또는 전체는 주변사람들로 가려질 수가 있다. 필수 지표 중 하나인 PAT를 개선하기 위해서는 시스템이 이러한 가려짐 문제를 극복해야만 한다. 이 연구에서는 이러한 가려짐 문제를 고려하여 강인한 검출시스템을 구축하기 위해서 여러 단계로 구성된 새로운 설계 기법을 제안한다. 제안된 시스템의 유용성을 보이기 위하여 6개의 다양한 상황을 포함하는 이미지 스트림에 대해서 평가를 시행했고, 그 실험 결과는 침입과 유기 행위에 대해 각각 96%와 75%의 성능을 보인다. 마지막으로 다수의 사람에 의한 가림 현상에도 불구하고 제안된 시스템은 계속적으로 유기물을 인지하는 성능을 보이고 있다.

Nowadays it is required to design intelligent visual surveillance systems which automatically detect abandoned objects in public places to strengthen the social safety. Already recognized abandoned objects can be occluded partially or fully by surrounding people in public places after the first recognition. To improve an essential recognition performance index PAT, the system should overcome the occlusion problems. In this research, a design scheme is newly proposed to construct the robust detection system which is comprised of multiple stages considering the occlusion problem. To show the feasibilities of the proposed system, the evaluation was tried for the prepared image streams including 6 various situations and the experimental results show 96% and 75% in PAT performance for intrusion and abandoning events, respectively. Finally in spite of full occlusions by multiple persons, the proposed system shows the capability to continuously recognize the abandoned object after complex occlusions disappear.

키워드

참고문헌

  1. N. Bird, S. Atev, N. Caramelli, R. Martin, O. Masoud, and N. Papanikolopulos, "Real Time, Online Detection of Abandoned Objects in Public Areas," Proceedings of the IEEE International Conference on Robotics and Automation, Orlando, Florida, May 2006.
  2. F. Porikli, Y. Lvanov and T. Haga, "Robust Abandoned Object Detection Using Dual Foregrounds," EURASIP Journal on Advanced in Signal Processing, 2008.
  3. I. Haritaoglu, D. Harwood, and L. S. Davis, "W4 : Real-Time Surveillance of People and Their Activities," IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, August 2000.
  4. W. Hu, T. Tan, L. Wang, and S. Maybank, "A Survey on Visual Surveillance of Object Motion and Behaviors," IEEE Trans. on Systems, Man, and Cybernetics-Part C, vol. 34, no. 3, August 2004.
  5. W. Kim, "Automatic Detection System for Dangerous Abandoned Objects based on Vision Technology," Journal of The Institute of Webcasting, Internet and Telecommunication, August 2009.
  6. W. Kim, "A Smart Visual Surveillance System with Human Recognition for Enhanced Detection of Abandoned Objects", Korean Institute of Information Technology, vol. 8, no. 10, pp. 209-214, October 2010.
  7. J. Kong, Y. Zheng, Y. Lu, and B. Zhang, "A Novel Background Extraction and Updating Algorithm for Vehicle Detection and Tracking," Fourth International Conference on Fuzzy Systems and Knowledge Discovery, 2007.
  8. A. Mohan, C. Papageorgiou, and T. Poggio, "Example-based object detection in images by components," IEEE PAMI, pp. 349-361, April 2001.
  9. P. Viola, M. J. Jones, and D. Snow, "Detecting pedestrians using patterns of motion and appearance," The 9th ICCV, vol. 1, pp. 734-741, 2003.
  10. K. Mikolajczyk, C. Schmid, and A. Zisserman, "Human detection based on a probabilistic assembly of robust part detectors," The 8th ECCV, vol. I, pp. 69-81, 2004.
  11. N. Dalal and B. Triggs, "Histograms of oriented gradients for human detection," CVPR 2005, vol. 1, pp. 886-893, 2005.