Automatic forest road extraction from LiDAR data using convolutional neural networks - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Automatic forest road extraction from LiDAR data using convolutional neural networks

Abstract

Accurate location of access roads is important for forest management, in particular in mountain areas. In this paper, we are interested in their detection from LiDAR data using deep learning approaches. For this, we use images computed from an interpolated surface, called digital terrain model (DTM), of the 3D point cloud. In order to train and validate the neural network models, two ground truth datasets associated to DTM images are considered: (1) manual digitization of the road centerlines and (2) automatic extraction followed by supervised completion using two softwares based on discrete geometry tools. The trained network models are then evaluated over a test dataset using standard measures such as precision, recall, F-measure and prediction time.
Embargoed file
Embargoed file
0 5 8
Year Month Jours
Avant la publication

Dates and versions

hal-03886785 , version 1 (25-08-2023)

Identifiers

Cite

Paul Georges, Phuc Ngo, Philippe Even. Automatic forest road extraction from LiDAR data using convolutional neural networks. Reproducible Research in Pattern Recognition (RRPR), Aug 2022, Montreal, Canada. pp.91-107, ⟨10.1007/978-3-031-40773-4_8⟩. ⟨hal-03886785⟩
18 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More