DeepSatData: Building large scale datasets of satellite images for training machine learning models
preprintposted on 2021-09-12, 08:50 authored 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.
Email Address of Submitting Authormichail.email@example.com
ORCID of Submitting Author0000-0002-6282-4529
Submitting Author's InstitutionImperial College London
Submitting Author's Country
- United Kingdom