Abstract
The existing road extraction methods do not sufficiently consider the 3D distribution characteristics of the point clouds, such as the occluded features, resulting in misclassification. For this reason, this paper, by analyzing the normal vector characteristics and spatial distribution features of 3D road point clouds, propose a method for extraction of the structured roads in urban areas using mobile 3D point clouds data. Firstly, the original point cloud is segmented and elevation filtered based on the trajectory data of the mobile laser scanning system; then the normal vector component length histogram is calculated, and the road surface points and the road curb points are separated by the single-peak histogram threshold selection method; finally, Euclidean clustering is applied to road surface point clustering and denoising. The test results prove that the method can extract road surface point clouds in different urban environments and reduce the influence of feature occlusion on road extraction.
Sign-in/Register to access full text options 
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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
