基于OD数据校验的交通流量检测数据修正方法  

A Calibration Method of Traffic Detection Data Based on OD Data

在线阅读下载全文

作  者:靳引利[1,2] 李阳[1] 王琳[1] 

机构地区:[1]长安大学电子与控制工程学院,西安710064 [2]长安大学交通系统工程研究所,西安710064

出  处:《交通信息与安全》2015年第3期29-34,共6页Journal of Transport Information and Safety

摘  要:运行稳定,检测精度高的交通信息检测设备是智能交通的需求。针对高速公路车检器流量检测数据精度不高的问题,以OD数据得到的断面流量数据为基础,提出了修正车检器分车型流量检测数据的方法以及评估车检器稳定性的方法。研究过程主要运用数据预处理、数理统计等数据挖掘的关键技术对车检器流量检测数据进行挖掘分析,得出车检器分车型的修正系数,将还原后的流量检测数据与修正系数相比较对流量检测数据进行修正,将修正后的数据与实际的断面流量数据相比较得出车检器的稳定性,最后通过实例测试进行了修正结果的误差验证,测试结果表明,小型车和总流量的误差均在±4%之内,且90%的数据在±2%之内,方法对小型车及总流量的检测数据修正效果良好;中型车误差80%在±5%之内且大部分为负值,说明修正结果较实际断面流量普遍偏小;大型车误差在10%之内且为正值,说明误差较大且修正结果较实际断面流量偏大。大、中型车车流量误差偏大可能是由于车检器将一部分中型车判定为大型车所致。Intelligent transport systems need stable operation and high accurate traffic information detection devices.This paper propose a method to validate and correct the detected flow data of different types of vehicles and to assess the stability of the vehicle detector mainly based on OD sectional traffic data in order to address the problem of the accuracy of detected traffic data on freeways.Data preprocessing,mathematical statistics and other key technologies of data mining were used to obtained correction factors.Restored vehicle detection data was by correction factors and the calibrated data was compared with sectional traffic data to get stability of the vehicle detector.The results from a case study showed that error of the small cars and total flow were within ±4%,and 90% of the data were within ±2%,which indicated the proposed method was reliable to detect small cars and total flow data.The 80% error of middle sized cars were within±5% and most were in the negative side,which indicated the calibrated volume was less than actual traffic volume at the cross section.The errors for large cars were within 10% and positive,which indicated the calibrated volume was larger than actual traffic volume at the cross section.The errors of middle sized and large cars were mainly caused by the vehicle detectors,which identified a part of middle sized cars as large cars.

关 键 词:智能交通 交通流量检测 数据修正 OD数据检验 断面流量数据 数据挖掘 

分 类 号:U49[交通运输工程—交通运输规划与管理]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象