Deep learning for the classification of Sentinel-2 image series

Charlotte Pelletier, Geoffrey I. Webb, Francois Petitjean

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch

Abstract

Satellite image time series (SITS) have proven to be essential for accurate and up-to-date land cover mapping over large areas. Most works about SITS have focused on the use of traditional classification algorithms such as Random Forests (RFs). Deep learning algorithms have been very successful for supervised tasks, in particular for data that exhibit a structure between attributes, such as space or time. In this work, we compare for the first time RFs to the two leading deep learning algorithms for handling temporal data: Recurrent Neural Networks (RNNs) and temporal Convolutional Neural Networks (TempCNNs). We carry out a large experiment using Sentinel-2 time series. We compare both accuracy and computational times to classify 10,980 km 2 over Australia. The results highlights the good performance of TemCNNs that obtain the highest accuracy. They also show that RNNs might be less suited for large scale study as they have higher runtime complexity.
Original languageEnglish
Title of host publication2019 IEEE International Geoscience & Remote Sensing Symposium - Proceedings
EditorsIrena Hajnsek, Akira Iwasaki, Hiroyoshi Yamada
Place of PublicationPiscataway NJ USA
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages461-464
Number of pages4
ISBN (Electronic)9781538691533, 9781538691540
ISBN (Print)9781538691557
DOIs
Publication statusPublished - 2019
EventIEEE International Geoscience and Remote Sensing Symposium 2019 - Yokohama, Japan
Duration: 28 Jul 20192 Aug 2019
Conference number: 39th
https://igarss2019.org/ (Website)
https://ieeexplore.ieee.org/xpl/conhome/8891871/proceeding (Proceedings)

Conference

ConferenceIEEE International Geoscience and Remote Sensing Symposium 2019
Abbreviated titleIGARSS 2019
CountryJapan
CityYokohama
Period28/07/192/08/19
Internet address

Keywords

  • time series

Cite this