DOI QR코드

DOI QR Code

A Map-Based Boundray Input Method for Video Surveillance

영상 감시를 위한 지도기반 감시영역 입력 방법

  • Kim, Jae-Hyeok (Department of Computer Science and Engineering, Kongju National University) ;
  • Maeng, Seung-Ryol (Department of Computer Science and Engineering, Kongju National University)
  • 김재혁 (공주대학교 컴퓨터공학과) ;
  • 맹승렬 (공주대학교 컴퓨터공학과)
  • Received : 2013.11.13
  • Accepted : 2014.01.09
  • Published : 2014.01.31

Abstract

In this paper, we propose a boundary input method for video surveillance systems. Since intrusion of a moving object is decided by comparition of its position and the surveillance boundary, the boundary input method is a basic function in video surveillance. Previous methods are difficult to adapt to the change of surveillance environments such as the size of surveillance area, the number of cameras, and the position of cameras because those build up the surveillance boundary using the captured image in the center of each camera. In our approach, the whole surveillance boundary is once defined in the form of polygon based on the satellite map and transformed into each camera environment. Its characteristics is that the boundary input is independent from the surveillance environment. Given the position of a moving object, the time complexity of its intrusion detection shows O(n), where n is the number of polygon vertices. To verify our method, we implemented a 3D simulation and assured that the input boundary can be reused in each camera without any redefinition.

본 논문에서는 영상감시 시스템을 위한 감시영역 입력방법을 제안한다. 이동물체의 침입 여부는 감시영역과 비교를 통해 이루어지므로 이를 입력하는 방법은 영상감시의 가장 기본적인 기능이다. 기존의 방법은 각 카메라 별로 획득된 영상을 기반으로 감시영역을 설정하기 때문에 감시영역의 크기. 카메라 수, 카메라 위치 등 감시환경의 변화에 대응하기 어려운 단점이 있다. 제안하는 입력방법은 위성지도를 기반으로 감시영역 전체를 다각형으로 정의하고, 이를 각 카메라 환경으로 변환하는 접근방법을 사용한다. 이 방법의 특징은 감시환경에 독립적이라는 점이다. 다각형의 정점의 수를 n이라 하면 침입탐지 수행시간은 O(n)의 복잡도를 보인다. 제안하는 방법의 타당성을 검증하기 위해 3D 시뮬레이션을 수행하였으며, 각 카메라 수와 위치에 무관하게 입력된 감시영역을 재사용할 수 있음을 확인하였다.

Keywords

References

  1. Freer, J. A, "Automatic video surveillance with intelligent scene monitoring and intruder detection", Security Technology, 30th Annual 1996 International Carnahan Conference, pp. 89-94, Oct, 1996
  2. Jong-Un, Won, "A Study on the Adaptive Object Recognition in Safe Zone Monitoring", The Korean Society for Railway, 2010.
  3. Sehchan Oh, "Train detection in railway platform area using image processing technology", Journal of the Korea Academia-Industrial cooperation Society, Vol. 13, No. 12, pp. 6098-6104, 2012 DOI: http://dx.doi.org/10.5762/KAIS.2012.13.12.6098
  4. Axis, "Axis Video Motion Detection", www.axis.com/products/video_motion_detection/index.htm
  5. i2v system, "Video Intrution Detection", www.i2vsys.com/products.html
  6. Ilguk, Jo, "Digital Image Monitoring Apparatus Through Setting Virtual Tripzone and The Method", KIPO, 2011
  7. Shimrat, M., "Algorithm 112 : Position of point relative to polygon" Communications of the ACM Volume 5 Issue 8, 1962. DOI: http://dx.doi.org/10.1145/368637.368653
  8. R. Courant, H. Robbins, "What is Mathematics, Fourth Printing", pp. 267-269, Oxford University Press, 1969
  9. Joseph O' Rourke, "Computational Geometry in C", Cambridge, 1998
  10. Chan-Ung, Jun, "Positioning and Mapmatching Technique using DR/DGPS Integrated Kalman Filter", Chung-Ang University, 2003
  11. Gallagher, A.C., "Using Vanishing Points To Correct Camera Rotation In Images", Computer and Robot Vision,. Proceedings. The 2nd Canadian Conference on, pp. 460-467, May, 2005
  12. Guo-Qing Wei, "Determining vanishing point and camera parameter: new approaches", Pattern Recognition, 1988., 9th International Conference on, pp. 450-452, Nov, 1988 DOI: http://dx.doi.org/10.1109/ICPR.1988.28263
  13. Edward Angel, "Interactive Computer Graphics 5th edition", Pearson Education, 2008