智能图像监控系统异常目标检测算法研究*

作者：谭元，吴成东，周芸，侯俊，王俏俏 日期：2009-04-21/span> 浏览：3289 查看PDF文档

智能图像监控系统异常目标检测算法研究*

谭元，吴成东，周芸，侯俊，王俏俏
(东北大学 信息科学与工程学院，辽宁 沈阳 110004)

摘要：为实现智能家居中的实时安全监控，提出了一种基于嵌入式平台和无线通讯的智能视频监控系统方案，并设计了智能视频监控系统中的异常目标检测算法。以背景差分法为基础，采用自适应阈值、运动目标跟踪及背景更新等方法，克服了背景光线变化、阴影及小目标带来的干扰，提出并实现了动态目标跟踪检测功能。该系统能够有效地对监控区域目标状态进行监测，并能根据监测结果进行报警等安全操作。实验结果表明，系统具有很高的实时性、可靠性和实用性。
关键词：视频监控;运动目标检测;帧间差分;自适应阈值
中图分类号：TP277文献标识码：A文章编号：1001-4551(2009)03-0012-04

Research of abnormal target detection algorithm in intelligent surveillance system
TAN Ji-yuan, WU Cheng-dong, ZHOU Yun, HOU Jun, WANG Qiao-qiao
(College of Information Science and Engineering, Northeastern University, Shenyang 110004, China)
Abstract: To implement real-time surveillance of the home security, an intelligent surveillance system based on embedded system platform and wireless communication technology was designed. To overcome interference coming from small target movement or background light changes, moving target detection algorithm was proposed. Abnormal matters at the monitor area can be detected exactly by analyzing the real time image information, and effective security actions will be taken with corresponding patterns. The experimental results show that the system possesses the advantages of real-time standard, high credibility and practicability.
Key words: intelligent surveillance system; abnormal target detection; frame subtract; adaptive threshold value
参考文献(References):
［1］MAE Y, SHIRAI Y, MIURA J, et al. Object Tracking in Cluttered Background based on Optical Flow and Edges［C］//Proceeding of the 13th International Conference on Pattern Recognition，1996:196-200.
［2］MEIER T, NGUN K N. Video segmentation for content-based coding［J］. IEEE Trans. on Circuits and Systems for Video Technology,1999,9(8):1190-1203.
［3］HARITAOGLU I, HARWOOD D, DAVIS L. W4: real-time surveillance of people and their activities［J］. IEEE Trans. Pattern Analysis and Machine Intelligence,2000,22(8):809-830.
［4］PENG Jin-ye, YU Bian-zhang. Multi-scale Bayesian Face Recognition by using Anti-symmetrical Biorthogonal Wavelets［C］//Info-tech and Info-net, 2001. Beijing: [s.n.]，2001:414-420.
［5］ZIVKOVIC Z. Improved Adaptive Gaussian Mixture Model for Back-ground Subtraction［C］//Proc. ICPR,2004. Cambridge: [s.n.],2004:28-31.
［6］VALERA M, VELASTIN S A. Intelligent distributed surveillance systems: a review［J］. Vision Image Signal Process，2005，152(2):192-204.
［7］GONZALES R C. Digital Image Processing Using Matlab［M］. Beijing: Publishing House of Electronics Industry,2007.
［8］EOGAMMAL A, HARWOOD D, DAVIS L. Non-parametric Model for Background Subtraction［C］//Proc. 6th European Conference of Computer Vision，2000. Dublin: [s.n.],2000:751-767.
［9］王成儒，顾广华.一种采用背景统计技术的视频对象分割算法［J］.光电工程，2004，8(31):57-60.