배경 모델링과 Modified CAMShift를 이용한 실시간 상황 감시 시스템

다국어 초록 (Multilingual Abstract)

In general, study on surveillance system using a sensors has been sufficiently studied. But study on surveillance system using CCTV(closed-circuit television) has been energetically implemented more than ever in recently. In this paper, we propose effective circumstances monitoring system that it use tracking algorithm using Modified CAMShift(Continuously Adaptive Mean Shift). Proposed system improve efficiency of system by little account for calculation to improve detection capacity and conduct speed in real time image. And we used adaptive Gaussian mixture model(Adaptive Gaussian Mixture Model) for noise. To detect and judge existence of moving object in region, we used a Modified CAMShift. The experimental results show that the proposed system using CCTV will be properly used in image surveillance system for detecting left behind and taken away a object in real time.

참고문헌 (Reference)

1 임혜연, "객체 추적 시스템을 위한 컬러 확률 분포를 이용한 개선된 객체 추적 알고리즘에 관한 연구" 한국정보기술학회 8 (8): 153-158, 2010

2 D. Comaniciu, "Real-time tracking of non-rigid objects using mean shift" 2 : 142-149, 2000

3 Gary R. Bradski, "Computer Vision Face Tracking For Use in a Perceptual User Interface" 1998

4 P. Kaew, "An Improved Adaptive Background Mixture Model for Real-Time Tracking with Shadow Detection" 2001

5 C. Stauffer C, "Adaptive background mixture model for real-time tracking" 244-252, 1999