Title
Road type classification of MLS point clouds using deep learning
Author
Bai, Q. (TU Delft Aircraft Noise and Climate Effects; TU Delft Geoscience and Remote Sensing; CycloMedia Technology)
Lindenbergh, R.C. (TU Delft Optical and Laser Remote Sensing; TU Delft Geoscience and Remote Sensing) 
Vijverberg, J. (CycloMedia Technology)
Guelen, J. A.P. (CycloMedia Technology)
Department
Geoscience and Remote Sensing
Date
2021
Abstract
Functional classification of the road is important to the construction of sustainable transport systems and proper design of facilities. Mobile laser scanning (MLS) point clouds provide accurate and dense 3D measurements of road scenes, while their massive data volume and lack of structure also bring difficulties in processing. 3D point cloud understanding through deep neural networks achieves breakthroughs since PointNet and arouses wide attention in recent years. In this paper, we study the automatic road type classification of MLS point clouds by employing a point-wise neural network, RandLA-Net, which is designed for consuming large-scale point clouds. An effective local feature aggregation (LFA) module in RandLA-Net preserves the local geometry in point clouds by formulating an enhanced geometric feature vector and learning different point weights in a local neighborhood. Based on this method, we also investigate possible feature combinations to calculate neighboring weights. We train on a colorized point cloud from the city of Hannover, Germany, and classify road points into 7 classes that reveal detailed functions, i.e., sidewalk, cycling path, rail track, parking area, motorway, green area, and island without traffic. Also, three feature combinations inside the LFA module are examined, including the geometric feature vector only, the geometric feature vector combined with additional features (e.g., color), and the geometric feature vector combined with local differences of additional features. We achieve the best overall accuracy (86.23%) and mean IoU (69.41%) by adopting the second and third combinations respectively, with additional features including Red, Green, Blue, and intensity. The evaluation results demonstrate the effectiveness of our method, but we also observe that different road types benefit the most from different feature settings.
Subject
Deep learning
Local feature aggregation
Mobile mapping
Point clouds
Road type
Semantic segmentation
To reference this document use:
http://resolver.tudelft.nl/uuid:3f41caff-e98c-4b6b-a95e-80b9a0a245dd
DOI
https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-115-2021
ISSN
1682-1750
Source
International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 43 (B2-2021), 115-122
Event
2021 24th ISPRS Congress Commission II: Imaging Today, Foreseeing Tomorrow, 2021-07-05 → 2021-07-09, Virtual, Online, France
Part of collection
Institutional Repository
Document type
journal article
Rights
© 2021 Q. Bai, R.C. Lindenbergh, J. Vijverberg, J. A.P. Guelen