Volume XLII-2/W13
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 981-987, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-981-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLII-2/W13, 981-987, 2019
https://doi.org/10.5194/isprs-archives-XLII-2-W13-981-2019
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

  05 Jun 2019

05 Jun 2019

WEIGHTED POINT CLOUD AUGMENTATION FOR NEURAL NETWORK TRAINING DATA CLASS-IMBALANCE

D. Griffiths and J. Boehm D. Griffiths and J. Boehm
  • Dept. of Civil, Environmental and Geomatic Engineering, University College London, Gower Street, London, WC1E 6BT, UK

Keywords: point cloud, classification, deep learning, augmentation, dataset

Abstract. Recent developments in the field of deep learning for 3D data have demonstrated promising potential for end-to-end learning directly from point clouds. However, many real-world point clouds contain a large class im-balance due to the natural class im-balance observed in nature. For example, a 3D scan of an urban environment will consist mostly of road and façade, whereas other objects such as poles will be under-represented. In this paper we address this issue by employing a weighted augmentation to increase classes that contain fewer points. By mitigating the class im-balance present in the data we demonstrate that a standard PointNet++ deep neural network can achieve higher performance at inference on validation data. This was observed as an increase of F1 score of 19% and 25% on two test benchmark datasets; ScanNet and Semantic3D respectively where no class im-balance pre-processing had been performed. Our networks performed better on both highly-represented and under-represented classes, which indicates that the network is learning more robust and meaningful features when the loss function is not overly exposed to only a few classes.