Browse > Article
http://dx.doi.org/10.6109/jkiice.2012.16.6.1148

An Intelligent Surveillance System using Fuzzy Contrast and HOG Method  

Kim, Kwang-Baek (신라대학교 컴퓨터공학과)
Publication Information
Journal of the Korea Institute of Information and Communication Engineering / v.16, no.6, 2012 , pp. 1148-1152 More about this Journal
Abstract
In this paper, we propose an intelligent surveillance system using fuzzy contrast and HOG method. This surveillance system is mainly for the intruder detection. In order to enhance the brightness difference, we apply fuzzy contrast and also apply subtraction method to before/after the surveillance. Then the system identifies the intrusion when the difference of histogram between before/after surveillance is sufficiently large. If the incident happens, the camera stops automatically and the analysis of the screen is performed with fuzzy binarization and Blob method. The intruder is detected and tracked in real time by HOG method and linear SVM. The proposed system is implemented and tested in real world environment and showed acceptable performance in both detection rate and tracking success rate.
Keywords
Fuzzy Contrast; HOG Method; Surveillance System; Fuzzy Binarization; Blob Method;
Citations & Related Records
연도 인용수 순위
  • Reference
1 류재호, 최경열, 조재현, 송두헌, 김광백, "퍼지 이진화를 이용한 침입자 감시 시스템에 관한 연구," 해양정보통신학회 춘계종합학술대회논문집, pp.201-204, 2010.
2 김광백, 김영주, "퍼지 소속 함수를 이용한 개선된 이진화 방법," 한국컴퓨터정보학회논문지, 10권, 1호, pp.67-72, 2005.
3 서용호, 박세준, 양태준, "사람 및 얼굴검출에 기반한 이동로봇의 강인한 객체추적 기술 구현," 한국정보기술학회눈문지, 8권 12호, pp.21-28, 2010.
4 A. Kandel, G. Langholz, Fuzzy Control Systems, CRC Press, Inc., 1994.
5 D. Comaniciu and V. Ramesh, "Mean shift and optimal prediction for efficient object tracking," Proceedings of IEEE Int. Conf. Image Processing, Vol. 3. pp.70-73, Sept., 2000.
6 C. Schuldt, "Recognizing human actions: a local SVM approach," Proceedings of the 17th International Conference on Pattern Recognition, pp.23-26, Aug., 2004.