基于帧间差分方法的道路车辆检测系统  

A Highway Vehicles Detection System Based on Frames Difference

作　　者：崔星[1] 闫清东[1] 

机构地区：[1]北京理工大学机械与车辆工程学院,北京100081

出　　处：《微计算机信息》2007年第10期117-119,共3页Control & Automation

基　　金：国防重点实验室基金资助项目

摘　　要：为了智能监控道路车流量,本文应用帧间差分方法建立了适用于公路环境的机器视觉系统。系统所用方法可以自动识别视频场景内所有移动车辆,计算每个目标的位置、面积,统计当前视野范围内车辆数目,计算某时间段内总车流量。实验结果表明,本文算法可对视频进行快速准确的识别,对环境光的变化具有较强的鲁棒性。To surveillance the moving vehicles in highway rapidly and accurately, a machine vision target detection algorithm based on frames difference is proposed. It can identify all the moving vehicles in current scene, each target’s location and area can be marked in the video, and the accumulated value of vehicles during a fixed time will be calculated in the program. Experimental results show that the algorithm has a good validity and robustness in target detection.

关 键 词：目标检测 机器视觉 差分图 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]