期刊文献+

考虑病害三维特征的沥青路面车辙异常检验方法 被引量:17

Asphalt pavement rutting anomaly inspection method considering 3D characteristics of distress
下载PDF
导出
摘要 针对复杂路况下车辙深度异常或横断面数据不完整的问题,提出了基于病害三维特征的路面车辙异常检验方法.首先,对三维图像中激光点异常值进行筛选及修正,利用横断面深度数据应用包络线算法提取最大车辙.考虑到裂缝、坑槽和拥包对车辙提取存在误判,利用三维高程数据建立病害种子检测模型以自动提取裂缝、坑槽和拥包种子点.测试结果表明,车辙深度相对误差小于7%,车辙深度测量重复性小于4%,包络线算法结果与人工测量值的相关系数高达0.9992.在车辙异常检验中,裂缝种子识别模型准确率和召回率的均值分别为92.18%和84.79%,且F值为88.33%,优于支持向量机及改进的Canny方法.坑槽及拥包种子识别模型检测正确率大于95%.所提方法不仅能高效地提取车辙深度,而且能准确地检验造成车辙检测异常的其他病害. To solve the problem of abnormal rut depth or incomplete cross-section data under complex road conditions,a rutting anomaly inspection method based on the three-dimensional(3D)characteristics of the disease was proposed.Firstly,the outliers of laser points on 3D images were filtered and corrected,and the maximum ruts were extracted by using the envelope algorithm based on the cross-section elevation data.Considering the misclassification of rutting extraction by cracks,potholes and shoving,a disease seed detection model was established by using 3D elevation data to automatically extract seeds of cracks,potholes and shoving.The experimental results show that the relative error of the rut depth is less than 7%.The repeatability of the rut depth measurement is less than 4%.The correlation coefficient between the results of the envelope algorithm and the manual measurement values is as high as 0.9992.In the rutting anomaly detection,the average accuracy and the recall rate of the crack recognition model are 92.18%and 84.79%,respectively,and the F-value 88.33%is better than those of the support vector machine and the improved Canny algorithm.The detection accuracy of the recognition model of potholes and shoving is more than 95%.The proposed method can not only effectively extract the rut depth efficiently,but also accurately detect other diseases in abnormal rutting.
作者 郎洪 陆键 陈圣迪 娄月新 Lang Hong;Lu Jian;Chen Shengdi;Lou Yuexin(Key Laboratory of Road and Traffic Engineering of Ministry of Education,Tongji University,Shanghai 201804,China;College of Transportation Engineering,Shanghai Maritime University,Shanghai 201306,China)
出处 《东南大学学报(自然科学版)》 EI CAS CSCD 北大核心 2020年第3期454-462,共9页 Journal of Southeast University:Natural Science Edition
基金 国家重点研发计划资助项目(2017YFC0803902).
关键词 车辙异常检验 三维线激光技术 图像处理 状态评估 rutting anomaly inspection three-dimensional line laser technology image processing condition assessment
  • 相关文献

参考文献10

二级参考文献121

共引文献182

同被引文献403

引证文献17

二级引证文献383

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部