EFFICIENT TRAINING OF SEMANTIC POINT CLOUD SEGMENTATION VIA ACTIVE LEARNING

• Published in: ISPRS annals of the photogrammetry, remote sensing and spatial information sciences Vol. V-2-2020; pp. 243 - 250
• Main Authors: Lin, Y., Vosselman, G., Cao, Y., Yang, M. Y.
• Format: Journal Article
• Language: English
• Published: Gottingen Copernicus GmbH 03.08.2020; Copernicus Publications
• Subjects: Accuracy; Active learning; Annotations; Datasets; Image segmentation; Lidar; Machine learning; Model accuracy; Photogrammetry; Semantics; Statistical methods; Statistical models; Three dimensional models; Training
• ISSN: 2194-9050; 2194-9042; 2194-9050
• DOI: 10.5194/isprs-annals-V-2-2020-243-2020

With the development of LiDAR and photogrammetric techniques, more and more point clouds are available with high density and in large areas. Point cloud interpretation is an important step before many real applications like 3D city modelling. Many supervised machine learning techniques have been adapted to semantic point cloud segmentation, aiming to automatically label point clouds. Current deep learning methods have shown their potentials to produce high accuracy in semantic point cloud segmentation tasks. However, these supervised methods require a large amount of labelled data for proper model performance and good generalization. In practice, manual labelling of point clouds is very expensive and time-consuming. Active learning can iteratively select unlabelled samples for manual annotation based on current statistical models and then update the labelled data pool for next model training. In order to effectively label point clouds, we proposed a segment based active learning strategy to assess the informativeness of samples. Here, the proposed strategy uses 40% of the whole training dataset to achieve a mean IoU of 75.2% which is 99.1% of the accuracy in mIoU obtained from the model trained on the full dataset, while the baseline method using same amount of data only reaches 69.6% in mIoU corresponding to 90.9% of the accuracy in mIoU obtained from the model trained on the full dataset.