Abstract
Abstract. Automatic extraction of road features from LiDAR data is a fundamental task for different applications, including asset management. The availability of updated and reliable models is even more important in the context of smart roads. One of the main advantages of LiDAR data compared with other sensing instruments is the possibility to directly get 3D information. However, the task of deriving road networks form LiDAR data acquired with Airborne Laser Scanning (ALS) may be quite complex due to occlusions, low feature separability and shadowing from contextual objects. Indeed, even if roads elements can be identified in the ALS point cloud, the automated identification of the network starting form them can be involved due to large variability in the size of roads, shapes and presence of connected off-road features such as parking lots. This paper presents a workflow aimed at partially solving the automatic creation of a road network from high-resolution ALS data. The presented method consists of three main steps: (i) labelling of road points; (ii) a multi-level voting scheme; and (iii) the regularization of the extracted road segments. The developed method has been tested using the “Vaihingen”, “Toronto” and “Tobermory” data set provided by the ISPRS.
Highlights
Nowadays, smart roads are more and more important and relate to a large number of other topics such as digital transformation of infrastructures (Meijer et al, 2018), autonomous driving (Varaiya, 1993), connected vehicles (Lu et al, 2014), etc
Due to its relatively narrow scanning angle (Rottensteiner and Clode, 2008) Airborne laser scanning (ALS) data are generally free of serious occlusions of the road surface
LiDAR data presents a high potential for smart road application, the original point cloud cannot be directly used for further analysis and integration with other data sources
Summary
Smart roads are more and more important and relate to a large number of other topics such as digital transformation of infrastructures (Meijer et al, 2018), autonomous driving (Varaiya, 1993), connected vehicles (Lu et al, 2014), etc. Clode at al., (2007) presented one of the first approaches for automatic road extraction from LiDAR data This method identifies road candidate points by filtering from a given distance from a Digital Surface Model (DSM) derived by LiDAR data and integrating laser intensity (see Scaioni et al, 2018) of points to remove bare grounds. To partially cope with this aspect, in this paper we are presenting an automated procedure for road information extraction, i.e., road centreline and road width, that can be used in combination with a BIM/GIS framework. The paper is organized as follows: Section 2 presents an overview of the proposed method and the possible integration of road centreline extraction in a BIM/GIS framework.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
