基于背景差法的几种背景建模方法的研究  

Intelligent wireless sensor nodes for traffic infor- mation detection

作　　者：仲元昌[1] 蔡增增[1] 赵贞贞[1] 宋扬[1] 

机构地区：[1]重庆大学通信工程学院/通信与测控中心,重庆400044

出　　处：《计算机工程与应用》2012年第24期62-66,100,共6页Computer Engineering and Applications

基　　金：国家自然科学基金（No.50875272,No.50735008）; 重庆市自然科学基金（CSTC,2008BB2340）

摘　　要：目前最常用也最有效的运动目标检测方法是背景差法,其中背景提取是背景差法的核心。主要比较了均值滤波法、中值滤波法、混合高斯分布法三种常用的背景建模的方法,说明了各算法在不同情况下的性能优劣。通过实验发现,均值滤波法和中值滤波法适合特定的场合,混合高斯法在场景复杂的情况下效果更好。In order to obtain accurate real-time traffic information parameters, the use of wireless sensor network technology and GPRS technology as an intelligent traffic-aware front-end and means of communication builds traf- fic information collection network and provides a more convenient solution for traffic information collection. Sensor nodes are designed for the traffic information detection and vehicle monitoring algorithm and the speed measure- ment algorithm are proposed. Experimental results show that the vehicle monitoring algorithm and the speed mea- surement algorithm can be implemented on the sensor nodes with limited capacity and get high accurate real-time traffic parameters, such as traffic flow, speed and so on. Traffic information collection network can meet the needs of large-scale network deployment and also can be used in intelligent traffic system.

关 键 词：运动目标检测 背景差 均值滤波法 中值滤波法 混合高斯分布法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]