Centre de documentation
scientifique

GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates / Valerio Marsocci (2023)  

Public Titre : GeoMultiTaskNet: remote sensing unsupervised domain adaptation using geographical coordinates Type de document : Article/Communication Auteurs : Valerio Marsocci, Auteur ; Nicolas Gonthier, Auteur ; Anatol Garioud , Auteur ; Simone Scardapane, Auteur ; Clément Mallet , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2023 Conférence : CVPR 2023, IEEE Conference on Computer Vision and Pattern Recognition workshops 18/06/2023 22/06/2023 Vancouver Colombie britannique - Canada OA Proceedings Importance : 11 p. Format : 21 x 30 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] base de données d'occupation du sol [Termes IGN] image à très haute résolution [Termes IGN] jeu de données localisées [Termes IGN] métadonnées géographiques [Termes IGN] segmentation sémantique Résumé : (auteur) Land cover maps are a pivotal element in a wide range of Earth Observation (EO) applications. However, annotating large datasets to develop supervised systems for remote sensing (RS) semantic segmentation is costly and time-consuming. Unsupervised Domain Adaption (UDA) could tackle these issues by adapting a model trained on a source domain, where labels are available, to a target domain, without annotations. UDA, while gaining importance in computer vision, is still under-investigated in RS. Thus, we propose a new lightweight model, GeoMultiTaskNet, based on two contributions: a GeoMultiTask module (GeoMT), which utilizes geographical coordinates to align the source and target domains, and a Dynamic Class Sampling (DCS) strategy, to adapt the semantic segmentation loss to the frequency of classes. This approach is the first to use geographical metadata for UDA in semantic segmentation. It reaches state-of-the-art performances (47,22% mIoU), reducing at the same time the number of parameters (33M), on a subset of the FLAIR dataset, a recently proposed dataset properly shaped for RS UDA, used for the first time ever for research scopes here. Numéro de notice : C2023-004 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers HAL Thématique : IMAGERIE Nature : Communication DOI : 10.48550/arXiv.2304.07750 En ligne : https://doi.org/10.48550/arXiv.2304.07750 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=103083

FLAIR: French Land cover from Aerial ImageRy - Challenge FLAIR #1: semantic segmentation and domain adaptation / Anatol Garioud (2022)  

Public Titre : FLAIR: French Land cover from Aerial ImageRy - Challenge FLAIR #1: semantic segmentation and domain adaptation Type de document : Article/Communication Auteurs : Anatol Garioud , Auteur ; Stéphane Peillet, Auteur ; Eva Bookjans, Auteur ; Sébastien Giordano , Auteur ; Boris Wattrelos , Auteur Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2022 Importance : 9 p. Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] base de données d'occupation du sol [Termes IGN] image aérienne à axe vertical [Termes IGN] jeu de données localisées [Termes IGN] segmentation sémantique Résumé : (auteur) [context] The French National Institute of Geographical and Forest Information (IGN) has the mission to document and measure land-cover on French territory and provides referential geographical datasets, including high-resolution aerial images and topographic maps. The monitoring of land-cover plays a crucial role in land management and planning initiatives, which can have significant socio-economic and environmental impact. Together with remote sensing technologies, artificial intelligence (IA) promises to become a powerful tool in determining land-cover and its evolution. IGN is currently exploring the potential of IA in the production of high-resolution land cover maps. Notably, deep learning methods are employed to obtain a semantic segmentation of aerial images. However, territories as large as France imply heterogeneous contexts: variations in landscapes and image acquisition make it challenging to provide uniform, reliable and accurate results across all of France. The FLAIR-one dataset presented is part of the dataset currently used at IGN to establish the French national reference land cover map "Occupation du sol à grande échelle" (OCS- GE). Numéro de notice : P2022-010 Affiliation des auteurs : IGN (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.2211.12979 En ligne : https://doi.org/10.48550/arXiv.2211.12979 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102141

Monitoring grassland dynamics by exploiting multi-modal satellite image time series / Anatol Garioud (2022)  

Public Titre : Monitoring grassland dynamics by exploiting multi-modal satellite image time series Titre original : Suivi de la dynamique des prairies permanentes par analyse des séries temporelles multi-modales Type de document : Thèse/HDR Auteurs : Anatol Garioud , Auteur ; Clément Mallet , Directeur de thèse ; Silvia Valero, Directeur de thèse Editeur : Champs-sur-Marne [France] : Université Gustave Eiffel Année de publication : 2022 Importance : 194 p. Format : 21 x 30 cm Note générale : Bibliographie Thèse présentée et soutenue en vue de l'obtention du Doctorat de l'Université Gustave Eiffel, Spécialité Sciences et Technologies de l'Information Géographique Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse diachronique [Termes IGN] analyse multivariée [Termes IGN] apprentissage profond [Termes IGN] classification par Perceptron multicouche [Termes IGN] données auxiliaires [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] Mâcon [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] prairie [Termes IGN] régression [Termes IGN] série temporelle [Termes IGN] seuillage d'image [Termes IGN] superpixel [Termes IGN] surveillance agricole [Termes IGN] Toulouse Index. décimale : THESE Thèses et HDR Résumé : (Auteur) The vast grassland surfaces as well as the growing recognition of the ecosystem services thez provide have revealed urgent needs for their conservation and sutainable management. Despite the acknowledged importance of grassland management practices, there are currently no large-scale efforts reporting on their frequency and nature. Satellite remote sensing time series appear to be a suitable tool for efficient grassland monitoring and allow synoptic and regular analysis. The research conducted in this PhD aims to develop methods for the detection of grassland management practices from complementary optical and SAR multivariate time series. Advances in deep learning are employed to regress multivariate SAR time series and contextual knowledge towards optical NDVI. Resulting gap-free time series are used to efficiently explore methods aiming to detect vegetation status changes related to management practices on grasslands. Note de contenu : INTRODUCTION 1. Grasslands and remote sensing: context, diversity and challenges 1.1 Definition, extent and importance of grasslands 1.2 Earth observation from space: principles and applications over grasslands 1.3 Problem statement and objectives 1.4 Outline of the manuscript 2. Study areas and datasets 2.1 Study areas 2.2 Satellite data 2.3 Reference and ancillary datasets 2.4 Feature derived from sentinel images for grassland monitoring 2.5 Description of the feature engineering steps 2.6 Exploring the relationships between derived satellite features 2.7 Concluding remarks HIGH-TEMPORAL SAMPLED TIME-SERIES 3. Sentinels regression for vegetation monitoring 3.1 Monitoring vegetation through optical-SAR synergy 3.2 Retrieving missing data in optical time series 3.3 SenRVM: a deep learning-based regression framework 3.4 Concluding remarks 4. Outcomes of the SenRVM approach 4.1 Experimental design for training and evaluating SenRVM models 4.2 Assessment of SenRVM predictions 4.3 Empirical analysis of the SenRVM results 4.4 Generalization capabilities of single-class grassland SenRVM models 4.5 Further post-processing of SenRVM results 4.6 Concluding remarks MONITORING GRASSLANDS 5. Detecting and quantifying grassland management practices 5.1 Challenges and related work 5.2 The proposed methodology 5.3 Description of validation data 5.4 Experimental setup 5.5 Assessment of the proposed method 5.6 Potential outcomes 5.7 Concluding remarks GENERAL CONCLUSION 6. Conclusion and perspectives 6.1 Summary 6.2 Perspectives Numéro de notice : 26831 Affiliation des auteurs : UGE-LASTIG (2020- ) Thématique : FORET/IMAGERIE/INFORMATIQUE Nature : Thèse française Note de thèse : Thèse de Doctorat : Sciences et Technologies de l'Information Géographique : Gustave Eiffel : 2022 Organisme de stage : LASTIG (IGN) nature-HAL : Thèse DOI : sans En ligne : https://theses.hal.science/tel-03843683 Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100728

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
26831-01	THESE	Livre	Centre de documentation	Thèses	Disponible

SenRVM: A multi-modal deep learning regression methodology for continuous vegetation monitoring with dense temporal NDVI time series / Anatol Garioud (2022) 

Public Titre : SenRVM: A multi-modal deep learning regression methodology for continuous vegetation monitoring with dense temporal NDVI time series Type de document : Article/Communication Auteurs : Anatol Garioud , Auteur ; Silvia Valero, Auteur ; Clément Mallet , Auteur Editeur : Saint-Mandé : Institut national de l'information géographique et forestière - IGN (2012-) Année de publication : 2022 Conférence : LPS 2022, ESA Living Planet Symposium 22/05/2022 27/05/2022 Bonn Allemagne programme sans actes Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse d'image orientée objet [Termes IGN] dynamique de la végétation [Termes IGN] image Sentinel-MSI [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] phénologie [Termes IGN] régression [Termes IGN] série temporelle [Termes IGN] surveillance de la végétation Résumé : (auteur) The Earth's biosphere and the phenology of vegetation are at the heart of climatic, economic and social concerns. Human activities have led to a significant degradation of ecosystem services (e.g. carbon sequestration, biodiversity, water quality, flood, and erosion regulation) provided by various extensive ecosystems such as forests, grasslands or crops. A key parameter for relevant climate modeling, public policy implementations or commercial applications is the temporal resolution at which vegetation is observed. As a tool providing synoptic and regular coverage of Earth’s surfaces, satellite Earth Observation has been increasingly adopted, among others, for estimating biomass, yields, modeling different fluxes or detecting changes. Optical images have been historically used for vegetation monitoring, considering their efficient discrimination of phenomena related to photosynthetic activity. To deal with missing data due to clouds, many interpolation strategies integrating one or more optical sensors have been developed. Most of these strategies are based on trend modelling that does not reflect the real evolution of the vegetation cover in many cases (sudden climatic impact, man-made effects). As a result, data that may be weeks or months apart are often interpolated on areas suffering from high cloud cover. Copernicus Sentinels provide new opportunities and unprecedented observations for the monitoring of vegetation’s dynamics. In particular, concordant optical and SAR data sets provided by the Sentinel-1 and 2 satellites open the door to new multi-sensor methodologies aiming at the reconstruction of missing information. Taking into account the still numerous non-cloudy observations provided by the Sentinel-2 satellites, a deep learning regression methodology, namely the Sentinels Regression for Vegetation Monitoring (SenRVM), has been developed. Its goal is the translation of SAR features acquired regardless of the climatic conditions into NDVI. The developed architecture integrates several deep learning architectures such as Multilayer Perceptron and Recurrent Neural Networks. The SenRVM regression strategy proposes the integration of auxiliary data such as climatic and topographic features. This allows accurate NDVI time series to be predicted by minimizing effects exogenous to the vegetation’s phenology through SAR acquisitions contextualization. Object-oriented analysis of the results is carried out on large scale areas for various vegetation types with distinct phenologies (grasslands, crops and forests). The results are analyzed by taking into account spatial and temporal aspects or with an ablation study of the Network’s inputs. The proposed approach is further compared with traditional interpolation methods exploiting monomodal (Whittaker smoothing, linear weighted interpolation) or multimodal (Random Forest, Gaussian Regression Processes, single Multilayer Perceptron) features. The potential of high-temporal NDVI time series obtained by the SenRVM method for several vegetation-related applications is subsequently illustrated. In particular, the interest of the obtained time series to observe the phenology and its associated parameters of the three main vegetation classes is presented. Numéro de notice : C2022-011 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Poster nature-HAL : Poster-avec-CL DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100786

Documents numériques

peut être téléchargé SenRVM - poster Adobe Acrobat PDF

Recurrent-based regression of Sentinel time series for continuous vegetation monitoring / Anatol Garioud in Remote sensing of environment, vol 263 (15 September 2021)  

Public [article]  inRemote sensing of environment > vol 263 (15 September 2021) . - n° 112419 Titre : Recurrent-based regression of Sentinel time series for continuous vegetation monitoring Type de document : Article/Communication Auteurs : Anatol Garioud , Auteur ; Silvia Valero, Auteur ; Sébastien Giordano , Auteur ; Clément Mallet , Auteur Année de publication : 2021 Projets : 3-projet - voir note / Article en page(s) : n° 112419 Note générale : bibliographie This work is funded by the Agence de la transition écologique (ADEME) and the Centre National d'Études Spatiales (CNES). Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] classification par réseau neuronal [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] fusion d'images [Termes IGN] image Sentinel-MSI [Termes IGN] image Sentinel-SAR [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] régression [Termes IGN] série temporelle [Termes IGN] surveillance de la végétation Résumé : (auteur) Dense time series of optical satellite imagery describing vegetation activity provide essential information for the efficient and regular monitoring of vegetation. Nevertheless, the temporal resolution of optical sensors is strongly affected by cloud cover, resulting in significant missing information. The use of complementary acquisitions, such as Synthetic Aperture Radar (SAR) data, opens the door to the development of new multi-sensor methodologies aiming at the reconstruction of missing information. However, the joint exploitation of new radar and optical missions, such as the Sentinel, raises new challenges given the different nature and response of the two data sources. In this work, the SenRVM methodology is proposed as a new multi-sensor approach to regress SAR time series towards Normalized Difference Vegetation Index (NDVI). A deep Recurrent Neural Network architecture which integrates SAR acquisitions and ancillary data is adopted. The regression task permits a continuous optical temporal resolution of 6 days. Multiple experiments are carried out to assess the SenRVM framework by studying two large-scale areas in France. Through an extensive interpretation of the results, SenRVM is evaluated on three main vegetation types (grasslands, crops, and forests). High accurate results (R2 > 0.83 and MAE Numéro de notice : A2021-499 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2021.112419 Date de publication en ligne : 25/06/2021 En ligne : https://doi.org/10.1016/j.rse.2021.112419 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98004 [article]

Preface: the 2021 edition of the XXIVth ISPRS congress / Clément Mallet in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2021 (July 2021)  

Permalink

Assessing the interest of a multi-modal gap-filling strategy for monitoring changes in grassland parcels / Anatol Garioud (2021)  

Permalink

Preface: the 2020 edition of the XXIVth ISPRS congress / Clément Mallet in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, vol V-1-2020 (August 2020)  

Permalink

On the joint exploitation of optical and SAR satellite imagery for grassland monitoring / Anatol Garioud (2020)  

Permalink

Challenges in grassland mowing event detection with multimodal Sentinel images / Anatol Garioud (2019)  

Permalink

Joint analysis of SAR and optical satellite images time series for grassland event detection / Anatol Garioud (2019)

Permalink