TechRxiv
DeepSatData__extracting_large_scale_datasets.pdf (3.09 MB)

DeepSatData: Building large scale datasets of satellite images for training machine learning models

Download (3.09 MB)
preprint
posted on 12.09.2021, 08:50 by Michael TarasiouMichael Tarasiou
This paper presents DeepSatData a pipeline for automatically generating satellite imagery datasets for training machine learning models. We also discuss design considerations with emphasis on dense classification tasks, e.g. semantic segmentation. The implementation presented makes use of freely available Sentinel-2 data which allows the generation of large scale datasets required for training deep neural networks (DNN). We discuss issues faced from the point of view of DNN training and evaluation such as checking the quality of ground truth data and comment on the scalability of the approach.

History

Email Address of Submitting Author

michail.tarasiou10@imperial.ac.uk

ORCID of Submitting Author

0000-0002-6282-4529

Submitting Author's Institution

Imperial College London

Submitting Author's Country

United Kingdom