Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification

Lenco Dino, Gaetano Raffaele, Interdonato Roberto, Osé Kenji, Tong Minh Dinh Ho. 2019. Combining Sentinel-1 and Sentinel-2 Time Series via RNN for object-based land cover classification. In : IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium proceedings. IEEE, GRSS. Yokohama : IEEE, 4881-4884. ISBN 978-1-5386-9154-0 IGARSS 2019, Yokohama, Japon, 28 Juillet 2019/2 Août 2019.

Url - éditeur : https://ieeexplore.ieee.org/document/8898458

Résumé : Radar and Optical Satellite Image Time Series (SITS) are sources of information that are commonly employed to monitor earth surfaces for tasks related to ecology, agriculture, mobility, land management planning and land cover monitoring. Many studies have been conducted using one of the two sources, but how to smartly combine the complementary information provided by radar and optical SITS is still an open challenge. In this context, we propose a new neural architecture for the combination of Sentinel-1 (S1) and Sentinel-2 (S2) imagery at object level, applied to a real-world land cover classification task. Experiments carried out on the Reunion Island, a overseas department of France in the Indian Ocean, demonstrate the significance of our proposal.

Mots-clés libres : Deep Learning, Occupation du sol, Sentinel-1, Sentinel-2

Auteurs et affiliations

• Lenco Dino, IRSTEA (FRA)
• Gaetano Raffaele, CIRAD-ES-UMR TETIS (FRA)
• Interdonato Roberto, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-0536-6277
• Osé Kenji, IRSTEA (FRA)
• Tong Minh Dinh Ho, IRSTEA (FRA)

Source : Cirad-Agritrop (https://agritrop.cirad.fr/597778/)

Métriques

[ Page générée et mise en cache le 2023-11-24 ]