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

International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences

Griffiths, D.^1¹ 

[1] Dept. of Civil, Environmental and Geomatic Engineering, University College London, Gower Street, London, WC1E 6BT, UK^1

关键词: point cloud;    classification;    deep learning;    augmentation;    dataset;   

DOI  :  10.5194/isprs-archives-XLII-2-W13-981-2019

学科分类：地球科学(综合)

来源: Copernicus Publications

【 摘 要 】

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.

【 授权许可】

CC BY