An automated algorithm for extracting road edges from terrestrial mobile LiDAR data

Abstract

a b s t r a c tTerrestrial mobile laser scanning systems provide rapid and cost effective 3D point cloud data which can be used for extracting features such as the road edge along a route corridor. This information can assist road authorities in carrying out safety risk assessment studies along road networks. The knowledge of the road edge is also a prerequisite for the automatic estimation of most other road features. In this paper, we present an algorithm which has been developed for extracting left and right road edges from terrestrial mobile LiDAR data. The algorithm is based on a novel combination of two modified versions of the parametric active contour or snake model. The parameters involved in the algorithm are selected empirically and are fixed for all the road sections. We have developed a novel way of initialising the snake model based on the navigation information obtained from the mobile mapping vehicle. We tested our algorithm on different types of road sections representing rural, urban and national primary road sections. The successful extraction of road edges from these multiple road section environments validates our algorithm. These findings and knowledge provide valuable insights as well as a prototype road edge extraction toolset, for both national road authorities and survey companies. Ó

Automated road markings extraction from mobile laser scanning data

“…This was primarily due to the road boundaries extracted using our automated road edge extraction algorithm which were extended incorrectly into a grass and soil area. The road boundaries extracted in the first 50 m rural and the second 50 m urban road section can be referred in Kumar et al (2013). The LiDAR points belonging to grass and soil surface in the first road section produced high intensity values which were not removed by our road marking extraction algorithm due to their large physical dimension.…”

“…Pu et al (2011) segmented MLS data into traffic signs, poles, barriers, trees and building walls based on spatial characteristics of point cloud segments like size, shape, orientation and topological relationships. Similarly, Zhou and Vosselman (2012) used elevation attribute, while McElhinney et al (2010) and Kumar et al (2013) employed elevation, intensity and pulse width attributes to extract road edges in multiple route corridor environment from MLS data.…”

“…In Kumar et al (2013), we presented an automated algorithm for extracting road edges from MLS data. We input n number of 30 m × 10 m × 5 m LiDAR and n number of 10 m navigation data sections in the road edge extraction algorithm.…”

“…We input n number of 30 m × 10 m × 5 m LiDAR and n number of 10 m navigation data sections in the road edge extraction algorithm. The dimensions of input data sections were selected based on empirical tests as they impact the process efficiency in terms of computational cost (Kumar, 2012;Kumar et al, 2013). The algorithm outputs road boundary which is used to identify the LiDAR points that belong to the road surface.…”

“…Knowledge of the location, dimension and condition of road markings can be useful for road safety, route network maintenance and driver assistance systems. In Kumar et al (2013), we presented an automated algorithm for extracting road edges from MLS data. The automated road edge extraction algorithm is applied to estimate road boundaries from LiDAR data.…”