基于HALCON的视频交通参数检测方法  

Video Detection of Traffic Parameters Based on HALCON

作　　者：占建云[1] 张毅[1] 王长君 姚丹亚[1] 陆磊[1] 

机构地区：[1]清华大学自动化系,北京100084 [2]公安部交通管理科学研究所,江苏无锡214151

出　　处：《公路交通科技》2008年第9期126-130,144,共6页Journal of Highway and Transportation Research and Development

基　　金：国家高技术研究发展计划(863计划)资助项目(2006AA11Z208);国家重点基础研究发展计划(973计划)资助项目(2006CB705506)

摘　　要：基于图像处理软件HALCON对视频交通参数检测方法进行讨论,研究双线性插值的图像距离标定方法和基于灰度统计的交通参数检测算法及流程,选取具有代表性的北京五道口交叉路口及成府路路段监控视频进行试验,证明方法的有效性,对试验结果中车速误差及混合交通启动车头时距规律进行深入分析,提出误差改进措施,并将混合交通排队车流启动车头时距规律与美国交通工程手册中车头时距规律进行对比分析。Video detection of traffic parameters was discussed based on HALCON. Bilinear interpolation was used for image distance calibration, and the detection algorithm and procedure based on grayscale statistics were given. Video data from typical intersection and section in Beijing （Wudaokou and Chengfu Road） were selected for testing, which demonstrates the effectiveness of the proposed methods. Further analysis was conducted to reduce the speed detection errors as well as the difference between headway distributions in China＇ s mixed traffic and in HCM2000.

关 键 词：交通工程 视频检测 双线性插值 灰度统计 交通参数 车头时距 

分 类 号：U491.1[交通运输工程—交通运输规划与管理]