Object-Based Multi-Temporal and Multi-Source Land Cover Mapping Leveraging Hierarchical Class Relationships
| العنوان: | Object-Based Multi-Temporal and Multi-Source Land Cover Mapping Leveraging Hierarchical Class Relationships |
|---|---|
| المؤلفون: | Gbodjo, Yawogan Jean Eudes, Ienco, Dino, Leroux, Louise, Interdonato, Roberto, Gaetano, Raffaele, Ndao, Babacar |
| المساهمون: | Territoires, Environnement, Télédétection et Information Spatiale (UMR TETIS), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad)-AgroParisTech-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), ADVanced Analytics for data SciencE (ADVANSE), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Agroécologie et Intensification Durables des cultures annuelles (UPR AIDA), Centre de Coopération Internationale en Recherche Agronomique pour le Développement (Cirad), Département Performances des systèmes de production et de transformation tropicaux (Cirad-PERSYST), Département Environnements et Sociétés (Cirad-ES), Université Cheikh Anta Diop [Dakar, Sénégal] (UCAD) |
| المصدر: | Remote Sensing Volume 12 Issue 17 Pages: 2814 Remote Sensing, Vol 12, Iss 2814, p 2814 (2020) Remote Sensing, MDPI, 2020, 12 (17), ⟨10.3390/rs12172814⟩ |
| بيانات النشر: | Multidisciplinary Digital Publishing Institute, 2020. |
| سنة النشر: | 2020 |
| مصطلحات موضوعية: | Télédétection, satellite image time series, Cartographie de l' utilisation des terres, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], neural networks pretraining, land cover classification, Cartographie de l'occupation du sol, lcsh:Science, Observation satellitaire, Satellites d'observation de la terre, Analyse de données, object based image analysis, deep learning, P31 - Levés et cartographie des sols, multi-source remote sensing, lcsh:Q, U30 - Méthodes de recherche, Analyse de séries chronologiques, Analyse d'image |
| الوصف: | European satellite missions Sentinel-1 (S1) and Sentinel-2 (S2) provide at high spatial resolution and high revisit time, respectively, radar and optical images that support a wide range of Earth surface monitoring tasks, such as Land Use/Land Cover mapping. A long-standing challenge in the remote sensing community is about how to efficiently exploit multiple sources of information and leverage their complementarity, in order to obtain the most out of radar and optical data. In this work, we propose to deal with land cover mapping in an object-based image analysis (OBIA) setting via a deep learning framework designed to leverage the multi-source complementarity provided by radar and optical satellite image time series (SITS). The proposed architecture is based on an extension of Recurrent Neural Network (RNN) enriched via a modified attention mechanism capable to fit the specificity of SITS data. Our framework also integrates a pretraining strategy that allows to exploit specific domain knowledge, shaped as hierarchy over the set of land cover classes, to guide the model training. Thorough experimental evaluations, involving several competitive approaches were conducted on two study sites, namely the Reunion island and a part of the Senegalese groundnut basin. Classification results, 79% of global accuracy on the Reunion island and 90% on the Senegalese site, respectively, have demonstrated the suitability of the proposal. |
| وصف الملف: | application/pdf; text |
| اللغة: | English |
| تدمد: | 2072-4292 |
| DOI: | 10.3390/rs12172814 |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::977ca44e863c10b96c85ce427d4979c7Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.dedup.wf.001..977ca44e863c10b96c85ce427d4979c7 |
| قاعدة البيانات: | OpenAIRE |
| تدمد: | 20724292 |
|---|---|
| DOI: | 10.3390/rs12172814 |