Airborne Laser Scanning Point Cloud Classification Using the DGCNN Deep Learning Method

Airborne Laser Scanning Point Cloud Classification Using the DGCNN Deep Learning Method

Widyaningrum, E. (TU Delft Optical and Laser Remote Sensing; Geospatial Information Agency)
Bai, Q. (TU Delft Civil Engineering & Geosciences)
Fajari, Marda K. (Geospatial Information Agency)
Lindenbergh, R.C. (TU Delft Optical and Laser Remote Sensing)

Civil Engineering & Geosciences

2021

Classification of aerial point clouds with high accuracy is significant for many geographical applications, but not trivial as the data are massive and unstructured. In recent years, deep learning for 3D point cloud classification has been actively developed and applied, but notably for indoor scenes. In this study, we implement the point-wise deep learning method Dynamic Graph Convolutional Neural Network (DGCNN) and extend its classification application from indoor scenes to airborne point clouds. This study proposes an approach to provide cheap training samples for point-wise deep learning using an existing 2D base map. Furthermore, essential features and spatial contexts to effectively classify airborne point clouds colored by an orthophoto are also investigated, in particularly to deal with class imbalance and relief displacement in urban areas. Two airborne point cloud datasets of different areas are used: Area-1 (city of Surabaya—Indonesia) and Area-2 (cities of Utrecht and Delft—the Netherlands). Area-1 is used to investigate different input feature combinations and loss functions. The point-wise classification for four classes achieves a remarkable result with 91.8% overall accuracy when using the full combination of spectral color and LiDAR features. For Area-2, different block size settings (30, 50, and 70 m) are investigated. It is found that using an appropriate block size of, in this case, 50 m helps to improve the classification until 93% overall accuracy but does not necessarily ensure better classification results for each class. Based on the experiments on both areas, we conclude that using DGCNN with proper settings is able to provide results close to production.

Accuracy assessment
Airborne point cloud
Classification
Deep learning
LiDAR

http://resolver.tudelft.nl/uuid:2b641f29-9451-4f40-8840-323d1cfe879a

https://doi.org/10.3390/rs13050859

2072-4292

Remote Sensing, 13 (5), 1-23

Institutional Repository

journal article

© 2021 E. Widyaningrum, Q. Bai, Marda K. Fajari, R.C. Lindenbergh