UAV LiDAR Point Cloud Segmentation of A Stack Interchange with Deep Neural Networks
This work addresses the problem of road infrastructure mapping for transportation systems, but it is incremental as it applies existing deep learning methods to new data from a specific sensor.
This study tackled the challenge of accurately mapping complex multi-layer stack interchanges by using a UAV LiDAR system and a deep learning framework for semantic segmentation, achieving over 93% classification accuracy.
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.