Department of Geoinformatics, Faculty of Geodesy, University of Zagreb, Kačićeva 26, 10000 Zagreb, Croatia.
Department of Transport Planning, Faculty of Transport and Traffic Sciences, University of Zagreb, Vukelićeva 4, 10000 Zagreb, Croatia.
Sensors (Basel). 2022 Jul 23;22(15):5510. doi: 10.3390/s22155510.
The United Nations (UN) stated that all new roads and 75% of travel time on roads must be 3+ star standard by 2030. The number of stars is determined by the International Road Assessment Program (iRAP) star rating module. It is based on 64 attributes for each road. In this paper, a framework for highly accurate and fully automatic determination of two attributes is proposed: roadside severity-object and roadside severity-distance. The framework integrates mobile Lidar point clouds with deep learning-based object detection on road cross-section images. The You Only Look Once (YOLO) network was used for object detection. Lidar data were collected by vehicle-mounted mobile Lidar for all Croatian highways. Point clouds were collected in .las format and cropped to 10 m-long segments align vehicle path. To determine both attributes, it was necessary to detect the road with high accuracy, then roadside severity-distance was determined with respect to the edge of the detected road. Each segment is finally classified into one of 13 roadside severity object classes and one of four roadside severity-distance classes. The overall accuracy of the roadside severity-object classification is 85.1%, while for the distance attribute it is 85.6%. The best average precision is achieved for safety barrier concrete class (0.98), while the worst AP is achieved for rockface class (0.72).
联合国（UN）表示，到 2030 年，所有新道路和 75%的道路行驶时间必须达到 3+星级标准。星级数量由国际道路评估计划（iRAP）星级评定模块确定。它基于每条道路的 64 个属性。本文提出了一种用于高度准确和全自动确定两个属性的框架：路边严重程度-对象和路边严重程度-距离。该框架将移动激光雷达点云和基于深度学习的道路横断面图像中的目标检测相结合。使用 You Only Look Once（YOLO）网络进行目标检测。激光雷达数据由车载移动激光雷达在所有克罗地亚高速公路上采集。点云以.las 格式采集，并裁剪成 10 米长的段，与车辆路径对齐。为了确定这两个属性，需要高精度地检测道路，然后根据检测到的道路边缘确定路边严重程度-距离。最后，每个路段被分类为 13 个路边严重程度对象类之一和 4 个路边严重程度距离类之一。路边严重程度对象分类的整体准确率为 85.1%，而距离属性的准确率为 85.6%。对于安全屏障混凝土类（0.98），最佳平均精度最高，而对于岩面类（0.72），AP 最差。
