基于点云数据的道路变形类病害自动化检测方法

Automatic Detection Method of Pavement Deformation Distress Based on Point Cloud Data

摘要:

拥包、沉陷等路面变形是常见的病害类型，但传统基于二维图像的判断方法无法获取深度信息，线性激光扫描的方法精度较高但是单次扫描范围有限，难以短时获取全局状况，导致大尺度变形类病害识别困难。利用车载移动激光雷达系统获取三维点云数据，解决了变形类病害检测的难点，并可提取其三维特征。实测数据验证了方法的可靠性和有效性，可实现拥包、沉陷和坑槽等变形病害的自动化检测，有效提高了检测效率。与全站仪测量结果对比，该方法三维特征提取信息完整且准确率达84.662%。

Abstract:

Shoving and subsidence are common pavement distresses. However， the traditional judgment method based on two-dimensional image cannot obtain depth information. The linear laser scanning method is precise， yet the single scan range is limited. Thus， it is difficult to obtain the global situation in a short time when identifying deformation distresses. A method is proposed for detecting deformation distresses and extracting their 3D features by using a vehicle-mounted mobile lidar system. Point cloud data are segmented and abnormal deformation points are extracted. 3D features of deformation distress are obtained. The reliability and effectiveness of the method are verified by the measured data. The results show that the method can automatically detect the deformation such as shoving， subsidence， and potholes. It can effectively improve the detection efficiency. Compared with the total station measurement results， the 3D feature extraction results are complete with an accuracy of 84.662%.