Road Extraction From Point Clouds of Open-Pit Mine Using LPFE-Net

Abstract

Accurate road network data for open-pit mines is crucial for the effective implementation of ore mining and transportation scheduling systems, as well as the operation of unmanned mining trucks. It is still a challenging task to accurately extract roads from open-pit mines because of their blurred boundaries and varying scales. Based on the characteristics of open-pit mine roads, we propose a Local Point Feature Enhancement Network (LPFE-Net). The core of LPFE-Net is a Point Feature Enhancement Unit (PFE Unit) and a multi-scale residual module. Among them, the PFE unit is used to fuse the key features of the neighboring points. The multi-scale residual module superimposes PFE units to expand the perceptual field and uses multi-level residual connections to improve information flow and reduce model complexity. The experimental results show that the proposed LPFE-Net outperforms all the compared methods in the open-pit mine road extraction task while having a relatively fast extraction speed.