Extracting Urban Road Footprints from Airborne LiDAR Point Clouds with PointNet++ and Two-Step Post-Processing

Abstract

In this paper, a novel framework for the automatic extraction of road footprints from airborne LiDAR point clouds in urban areas is proposed. The extraction process consisted of three phases: The first phase is to extract road points by using the deep learning model PointNet++, where the features of the input data include not only those selected from raw LiDAR points, such as 3D coordinate values, intensity, etc., but also the digital number (DN) of co-registered images and generated geometric features to describe a strip-like road. Then, the road points from PointNet++ were post-processed based on graph-cut and constrained triangulation irregular networks, where both the commission and omission errors were greatly reduced. Finally, collinearity and width similarity were proposed to estimate the connection probability of road segments, thereby improving the connectivity and completeness of the road network represented by centerlines. Experiments conducted on the Vaihingen data show that the proposed framework outperformed others in terms of completeness and correctness; in addition, some narrower residential streets with 2 m width, which have normally been neglected by previous studies, were extracted. The completeness and the correctness of the extracted road points were 84.7% and 79.7%, respectively, while the completeness and the correctness of the extracted centerlines were 97.0% and 86.3%, respectively.

An Automatic Road Surface Segmentation in Non-Urban Environments: A 3D Point Cloud Approach With Grid Structure and Shallow Neural Networks

“…Finally, the researchers eliminated the incorrect road curb segments. The PointNet++ neural network was used by Ma et al [16]to automatically extract road footprints from airborne LiDAR point clouds and high-resolution coregistered images in urban areas. The raw LiDAR point features, such as 3D coordinates, intensity, and so on, as well as the RGB digital number (DN) values of the co-registered image, were used as network inputs.…”

Transport Infrastructure Management Based on LiDAR Synthetic Data: A Deep Learning Approach with a ROADSENSE Simulator

“…Conducting a health analysis as well as determining stability and other physical properties that can be inferred from LiDAR point clouds are the main focus areas in many research works [3]. It is important to highlight the applicability of LiDAR, especially for infrastructure inventory and management, based on semantic segmentation [4][5][6], where it is crucial to overcome the current limitations of technology related to the demanding costs and workforce linked to the huge datasets obtained. A three-dimensional model analysis can also be used to detect road safety issues related to sight distance on sharp vertical curves and horizontal curves.…”

Efficiency of Terrestrial Laser Scanning in Survey Works: Assessment, Modelling, and Monitoring

“…Finally, they employ X and Y filtered cloud coordinates to establish establish curbs slope function. Ma et al [14] extract road points by utilising the deep learning network PointNet++(see Qi et al [15]), afterwards, the road points are processed based on graphcut and constrained Triangulation Irregular Networks (TIN), and both the commission and omission errors are decreased.Finally, collinearity and width similarity are suggested to approximate the linking probability of road segments. Fernández-Arango et al [16] propose an approach for pedestrian space extracting and generating a high-definition 3D model.…”