Coarse-to-Fine Classification of Road Infrastructure Elements from Mobile Point Clouds Using Symmetric Ensemble Point Network and Euclidean Cluster Extraction

Abstract

Classifying point clouds obtained from mobile laser scanning of road environments is a fundamental yet challenging problem for road asset management and unmanned vehicle navigation. Deep learning networks need no prior knowledge to classify multiple objects, but often generate a certain amount of false predictions. However, traditional clustering methods often involve leveraging a priori knowledge, but may lack generalisability compared to deep learning networks. This paper presents a classification method that coarsely classifies multiple objects of road infrastructure with a symmetric ensemble point (SEP) network and then refines the results with a Euclidean cluster extraction (ECE) algorithm. The SEP network applies a symmetric function to capture relevant structural features at different scales and select optimal sub-samples using an ensemble method. The ECE subsequently adjusts points that have been predicted incorrectly by the first step. The experimental results indicate that this method effectively extracts six types of road infrastructure elements: road surfaces, buildings, walls, traffic signs, trees and streetlights. The overall accuracy of the SEP-ECE method improves by 3.97% with respect to PointNet. The achieved average classification accuracy is approximately 99.74 % , which is suitable for practical use in transportation network management.

Tree Extraction from Airborne Laser Scanning Data in Urban Areas

“…In particular, the algorithm of ECE is widely used by researchers due to its simplicity and effectiveness [49]. To refine the tree extraction, an ECE method is operated, under the assumption that all neighboring objects in the point clouds are not directly connected.…”

Efficient Large-Scale Airborne Lidar Data Classification via Fully Convolutional Network

“…Point cloud classification has always been a hot research topic in the LiDAR data processing field, with several applications in, e.g., land cover classification, vegetation studies in forestry and agriculture, and road infrastructure management (Wang et al, 2020). Classification methods usually rely both on geometric information (i.e., the 3D coordinates of the surveyed points and their distribution in a neighboring region), as well as on the intensity of the backscattered pulse (Scaioni et al, 2018).…”

“…The main limitation of these approaches lies in the need of hand-crafted features, which can be sensible to changes in the data characteristics. Moreover, these approaches usually classify each point independently, without considering the labels assigned to neighboring points (Wang et al, 2020).…”

Classification of 3D Point Cloud Data from Mobile Mapping System for Detecting Road Surfaces and Potholes using Convolution Neural Networks

“…Hence, several studies use point cloud data to classify objects in the road environment, such as road surfaces, electric poles, trees, cars, buildings, and traffic signs [18], [19], [20]. Since modern MMS is equipped with 360-degree panoramic cameras, point clouds are recorded in the color values of red, green, and blue (RGB), allowing 3D renders to show color values reflecting original photographic data and adding dimensions to point cloud classification [21]. Nevertheless, no studies have yet compared the accuracy of point cloud classification with and without RGB values.…”