Horizontal curves are designed to provide a safe and smooth transition between straight segments on a highway network. Although curves are often designed to meet very stringent standards, imperfections during construction and high operating speeds mean that they are still prone to collisions. Therefore, it is essential that attributes of curves are surveyed to ensure they meet design requirements. Moreover, knowledge of the locations of horizontal curves and their attributes is also required to provide drivers with accurate information in advanced curve-warning systems, which are expected to enhance safety. Unfortunately, conventional techniques to obtain information about horizontal alignments are extremely tedious and, in some cases, impractical. This paper proposes a method by which horizontal curves can be automatically detected and their attributes automatically measured on scans of the highways obtained using light detection and ranging (LiDAR) technology. The proposed method is tested on two different highway segments at the Province of Alberta, Canada, where LiDAR data were collected. Moreover, testing was also conducted using virtual highways with curves with known attributes generated in AutoCAD Civil 3D. The results show that the code is successful in detecting all curves on a highway segment; moreover, the attributes of those curves were estimated with a high degree of accuracy (average difference <3%).
Automated Extraction of Horizontal Curve Attributes using LiDAR Data
Transportation Research Record
Transportation Research Record: Journal of the Transportation Research Board ; 2672 , 39 ; 98-106
2018-05-05
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Automated Highway Sign Extraction Using Lidar Data
Transportation Research Record | 2017
|Automated Extraction of Horizontal Curve Information for Low-Volume Roads
Transportation Research Record | 2015
|Transportation Research Record | 2012
|