UAV LiDAR Point Cloud Segmentation of A Stack Interchange with Deep Neural Networks

TL;DR

This paper presents a deep learning approach for segmenting UAV-acquired LiDAR point clouds of complex stack interchanges, achieving over 93% accuracy and demonstrating the potential of a new low-cost LiDAR sensor for urban mapping.

Contribution

It introduces an end-to-end 3D deep learning framework for semantic segmentation of complex interchange point clouds and evaluates a novel low-cost LiDAR sensor for urban mapping.

Findings

Achieved over 93% classification accuracy on complex interchange data.

Demonstrated the effectiveness of stacked convolution in capturing 3D features.

Validated the potential of Livox Mid-40 LiDAR sensor for high-definition urban mapping.

Abstract

Stack interchanges are essential components of transportation systems. Mobile laser scanning (MLS) systems have been widely used in road infrastructure mapping, but accurate mapping of complicated multi-layer stack interchanges are still challenging. This study examined the point clouds collected by a new Unmanned Aerial Vehicle (UAV) Light Detection and Ranging (LiDAR) system to perform the semantic segmentation task of a stack interchange. An end-to-end supervised 3D deep learning framework was proposed to classify the point clouds. The proposed method has proven to capture 3D features in complicated interchange scenarios with stacked convolution and the result achieved over 93% classification accuracy. In addition, the new low-cost semi-solid-state LiDAR sensor Livox Mid-40 featuring a incommensurable rosette scanning pattern has demonstrated its potential in high-definition urban mapping.