High-Resolution Terrain Modeling Using Airborne LiDAR Data with Transfer Learning
| Autor: | Saied Pirasteh, Weikai Tan, Weiya Ye, Huxiong Li, Jun Liu, Jonathan Li, Sarah Narges Fatholahi |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
LiDAR
Computer science business.industry Science Elevation Point cloud deep learning Pattern recognition Convolutional neural network interpolation Triangulated irregular network Lidar Feature (computer vision) digital terrain model General Earth and Planetary Sciences point cloud Artificial intelligence business Digital elevation model Interpolation |
| Zdroj: | Remote Sensing, Vol 13, Iss 3448, p 3448 (2021) Remote Sensing; Volume 13; Issue 17; Pages: 3448 |
| ISSN: | 2072-4292 |
| DOI: | 10.3390/rs13173448 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|