考虑可视路表面积的小客车运行速度预测模型  

Prediction model of operating speed for passenger cars by considering visual area of road surface

作　　者：张驰[1,2] 闫晓敏[1] 华贵龙[1] 熊丽[1] 孟良[1] 

机构地区：[1]长安大学特殊地区公路工程教育部重点试验室,陕西西安710064 [2]中交第一公路勘察设计研究院有限公司,陕西西安710075

出　　处：《长安大学学报（自然科学版）》2016年第3期72-80,共9页Journal of Chang’an University(Natural Science Edition)

基　　金：交通运输部应用基础项目(2014319812170);国家科技支撑计划项目(2014BAG05B01);教育部博士点基金新教师项目(20120205120013);中央高校基本科研业务费专项资金项目(2013G2211005;CHD2011JC048)

摘　　要：为综合考虑道路平面、纵断面和横断面对小客车运行速度的影响,选用驾驶人可视路表面积为运行速度的研究指标,采用集视频采集技术、GPS定位技术、高精度车速拾取技术于一体的多功能数据采集仪,记录驾驶人可视路表面积及车速等信息;对采集的单帧彩色视野图像运用线形变换法进行灰度化处理,通过编写改进的OTSU算法对灰度图像进行路表和背景二值化分割;最后基于像素行扫描算法提取驾驶人可视路表面积,运用SPSS软件进行相关性分析并建立数学预测模型。研究结果表明:驾驶人可视路表面积与车辆运行速度呈正相关关系,两者变化量之间相关系数为0.676;模型预测值与实际观测值两者相对误差的平均值为3.88%;采用驾驶人可视路表面积预测运行速度简便、有效,能有效突破目前运行速度预测方法的局限性。In order to study the effects of horizontal curve,profile and cross section on vehicle’s operating speed,drivers’visual area of road surface was used as an index for evaluation.A multifunctional data acquisition instrument which integrates the technology of video collection,the technology of GPS and high precision speed picking-up was used to gather drivers’visual area of road surface and operating speed.The single frame colorful vision image was treated by graying with weighted algorithm.Using the improved OTSU algorithm for image segmentation drivers’visual area of road surface was extracted based on the line scan algorithm.The correlation between factors and operating speed model were established by SPSS.The results show that the correlation between road surface area and operating speed model is positively,and the correlation coefficient is 0.676.The average value of relative error between prediction value and observedvalue is 3.88%.The prediction model proposed is easy to manipulate and efficient in working,which can break the limitation of current prediction methods.7tabs,7figs,20 refs.

关 键 词：交通工程 运行速度模型 路表面积 OTSU算法 

分 类 号：U411[交通运输工程—道路与铁道工程]