Next Article in Journal
Remote Sensing of Pasture Degradation in the Highlands of the Kyrgyz Republic: Finer-Scale Analysis Reveals Complicating Factors
Next Article in Special Issue
Topologically Consistent Reconstruction for Complex Indoor Structures from Point Clouds
Previous Article in Journal
Disentangling LiDAR Contribution in Modelling Species–Habitat Structure Relationships in Terrestrial Ecosystems Worldwide. A Systematic Review and Future Directions
Previous Article in Special Issue
3DRIED: A High-Resolution 3-D Millimeter-Wave Radar Dataset Dedicated to Imaging and Evaluation
Article

High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning

1
School of Mechanical and Electrical Engineering, Shaoxin University, Shaoxing 312000, China
2
Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada
3
College of Computer Science and Artificial Intelligence, Wenzhou University, Wenzhou 325035, China
4
Faculty of Geosciences & Environmental Engineering, Southwest Jiaotong University, Chengdu 611756, China
*
Author to whom correspondence should be addressed.
Academic Editor: Joaquín Martínez-Sánchez
Remote Sens. 2021, 13(17), 3448; https://0-doi-org.brum.beds.ac.uk/10.3390/rs13173448
Received: 17 July 2021 / Revised: 22 August 2021 / Accepted: 27 August 2021 / Published: 31 August 2021
This study presents a novel workflow for automated Digital Terrain Model (DTM) extraction from Airborne LiDAR point clouds based on a convolutional neural network (CNN), considering a transfer learning approach. The workflow consists of three parts: feature image generation, transfer learning using ResNet, and interpolation. First, each point is transformed into a featured image based on its elevation differences with neighboring points. Then, the feature images are classified into ground and non-ground using ImageNet pretrained ResNet models. The ground points are extracted by remapping each feature image to its corresponding points. Last, the extracted ground points are interpolated to generate a continuous elevation surface. We compared the proposed workflow with two traditional filters, namely the Progressive Morphological Filter (PMF) and the Progressive Triangulated Irregular Network Densification (PTD). Our results show that the proposed workflow establishes an advantageous DTM extraction accuracy with yields of only 0.52%, 4.84%, and 2.43% for Type I, Type II, and the total error, respectively. In comparison, Type I, Type II, and the total error for PMF are 7.82%, 11.60%, and 9.48% and for PTD 1.55%, 5.37%, and 3.22%, respectively. The root means square error (RMSE) for the 1 m resolution interpolated DTM is only 7.3 cm. Moreover, we conducted a qualitative analysis to investigate the reliability and limitations of the proposed workflow. View Full-Text
Keywords: digital terrain model; LiDAR; point cloud; deep learning; interpolation digital terrain model; LiDAR; point cloud; deep learning; interpolation
Show Figures

Graphical abstract

MDPI and ACS Style

Li, H.; Ye, W.; Liu, J.; Tan, W.; Pirasteh, S.; Fatholahi, S.N.; Li, J. High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning. Remote Sens. 2021, 13, 3448. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13173448

AMA Style

Li H, Ye W, Liu J, Tan W, Pirasteh S, Fatholahi SN, Li J. High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning. Remote Sensing. 2021; 13(17):3448. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13173448

Chicago/Turabian Style

Li, Huxiong, Weiya Ye, Jun Liu, Weikai Tan, Saied Pirasteh, Sarah N. Fatholahi, and Jonathan Li. 2021. "High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning" Remote Sensing 13, no. 17: 3448. https://0-doi-org.brum.beds.ac.uk/10.3390/rs13173448

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop