基于实时视频图像处理的车辆排队长度检测  

Measurement of Vehicle Queue Length Based on Real-time Video Image Processing

作　　者：朱超军[1] 杨红雨[1] 刘东辉[1] 李浩民[1] 王世豪[1] 

机构地区：[1]四川大学计算机学院,四川成都610064

出　　处：《计算机技术与发展》2014年第4期45-48,共4页Computer Technology and Development

基　　金：国家"863"高技术发展计划项目(2012AA011804;2013AA013802);四川省科技创新苗子工程资助项目(2012ZZ026)

摘　　要：车辆排队长度是智能交通系统中最重要的参数之一。为了得到更加准确的参数数据,文中提出一种基于实时视频处理的车辆排队长度检测方法。对通过固定摄像头得到的实时道路监控视频图像序列,利用Sobel边缘检测和背景差分相结合的方式进行车辆存在检测,利用帧间差判断车辆是否运动,从而计算出车辆的排队长度。实验表明,此方法简单稳定,有效解决了车道标志线、车辆边缘不明显以及车辆阴影等问题,队列长度检测结果也较准确。Vehicle queue length is one of the most important parameters in Intelligent Traffic Systems （ITS）. Present a method to detect the length of the queue based on real-time video in order to obtain more accurate parameters. The video image sequence of real-time road by a stationary camera is conducted vehicle detection using the way combines Sobel edge detection and background difference, applying frame difference to determine whether a vehicle moves or not, calculating the vehicle queue length. Experimental results show that this method is simple and stable ,effectively solving the problems of the edge is not obvious, the lane mark line, and vehicle shadow, queue length test results are more accurate.

关 键 词：边缘检测 背景差分 帧间差 排队长度检测 

分 类 号：TP31[自动化与计算机技术—计算机软件与理论]