Abstract
3D GIS has attracted increasing attention from academics, industries, and governments with the increase in the requirements for the interoperability and integration of different sources of spatial data. Three-dimensional road extraction based on multisource remote sensing data is still a challenging task due to road occlusion and topological complexity. This paper presents a novel framework for 3D road extraction by integrating LiDAR point clouds and high-resolution remote sensing imagery. First, a multiscale collaborative representation-based road probability estimation method was proposed to segment road surfaces from high-resolution remote sensing imagery. Then, an automatic stratification process was conducted to specify the layer values of each road segment. Additionally, a multifactor filtering strategy was proposed in consideration of the complexity of ground features and the existence of noise in LiDAR points. Lastly, a least-square-based elevation interpolation method is used for restoring the elevation information of road sections blocked by overpasses. The experimental results based on two datasets in Hong Kong Island show that the proposed method obtains competitively satisfactory results.
Highlights
In the last twenty years, three-dimensional (3D) city modeling technology has been gradually applied in smart city infrastructure construction and urban intelligent transportation network construction [1,2]
We addressed the issue of 3D road extraction using Light Detection and Ranging (LiDAR) point clouds and high-resolution remote sensing imagery
An automated stratification process was used to determine the height level of each road segment, and a multifactor filtering strategy was proposed for LiDAR point denoising in accordance with complex ground features
Summary
In the last twenty years, three-dimensional (3D) city modeling technology has been gradually applied in smart city infrastructure construction and urban intelligent transportation network construction [1,2]. From geometric modeling of road surfaces to texture mapping, good results are achieved through manual road modeling at the expense of significant labor and time. As a result, this inefficient manual modeling severely limits the number of road models generated and their widespread use in various applications
Sign-in/Register to view highlights & summary 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.
