Print Email Facebook Twitter Pointnet For The Automatic Classification Of Aerial Point Clouds Title Pointnet For The Automatic Classification Of Aerial Point Clouds Author Soilán, M. (University of Vigo) Lindenbergh, R.C. (TU Delft Optical and Laser Remote Sensing) Riveiro, B. (University of Vigo) Sánchez-Rodríguez, A. (University of Vigo) Date 2019 Abstract During the last couple of years, there has been an increased interest to develop new deep learning networks specifically for processing 3D point cloud data. In that context, this work intends to expand the applicability of one of these networks, PointNet, from the semantic segmentation of indoor scenes, to outdoor point clouds acquired with Airborne Laser Scanning (ALS) systems. Our goal is to of assist the classification of future iterations of a national wide dataset such as the Actueel Hoogtebestand Nederland (AHN), using a classification model trained with a previous iteration. First, a simple application such as ground classification is proposed in order to prove the capabilities of the proposed deep learning architecture to perform an efficient point-wise classification with aerial point clouds. Then, two different models based on PointNet are defined to classify the most relevant elements in the case study data: Ground, vegetation and buildings. While the model for ground classification performs with a F-score metric above 96%, motivating the second part of the work, the overall accuracy of the remaining models is around 87%, showing consistency across different versions of AHN but with improvable false positive and false negative rates. Therefore, this work concludes that the proposed classification of future AHN iterations is feasible but needs more experimentation. Subject Aerial Laser ScannerDeep LearningPoint Cloud ClassificationSemantic Segmentation To reference this document use: http://resolver.tudelft.nl/uuid:c65cd27c-c4d4-4a54-8e95-c9a88a8ee096 DOI https://doi.org/10.5194/isprs-annals-IV-2-W5-445-2019 ISSN 2194-9042 Source ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, 4 (2/W5), 445-452 Event 4th ISPRS Geospatial Week 2019, 2019-06-10 → 2019-06-14, Enschede, Netherlands Part of collection Institutional Repository Document type journal article Rights © 2019 M. Soilán, R.C. Lindenbergh, B. Riveiro, A. Sánchez-Rodríguez Files PDF isprs_annals_IV_2_W5_445_2019.pdf 1.54 MB Close viewer /islandora/object/uuid:c65cd27c-c4d4-4a54-8e95-c9a88a8ee096/datastream/OBJ/view