Détail de l'auteur
Auteur C. Sannier |
Documents disponibles écrits par cet auteur (2)
Ajouter le résultat dans votre panier Affiner la recherche Interroger des sources externesBenchmarking of convolutional neural network approaches for vegetation land cover mapping / Benjamin Carpentier (2021)
Titre : Benchmarking of convolutional neural network approaches for vegetation land cover mapping Type de document : Article/Communication Auteurs : Benjamin Carpentier, Auteur ; Antoine Masse Editeur : International Society for Photogrammetry and Remote Sensing ISPRS Année de publication : 2021 Collection : International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, ISSN 1682-1750 num. 43-B2-2021 Conférence : ISPRS 2021, Commission 2, XXIV ISPRS Congress, Imaging today foreseeing tomorrow 05/07/2021 09/07/2021 Nice Virtuel France OA Archives Commission 2 Importance : pp 915 - 922 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse comparative
[Termes IGN] carte d'occupation du sol
[Termes IGN] carte de la végétation
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] image Sentinel-MSI
[Termes IGN] série temporelleRésumé : (auteur) Satellite Image Time Series (SITS) are becoming available at high spatial, spectral and temporal resolutions across the globe by the latest remote sensing sensors. These series of images can be highly valuable when exploited by classification systems to produce frequently updated and accurate land cover maps. The richness of spectral, spatial and temporal features in SITS is a promising source of data for developing better classification algorithms. However, machine learning methods such as Random Forests (RF), despite their fruitful application to SITS to produce land cover maps, are structurally unable to properly handle intertwined spatial, spectral and temporal dynamics without breaking the structure of the data. Therefore, the present work proposes a comparative study of various deep learning algorithms from the Convolutional Neural Network (CNN) family and evaluate their performance on SITS classification. They are compared to the processing chain coined iota2, developed by the CESBIO and based on a RF model. Experiments are carried out in an operational context using with sparse annotations from 290 labeled polygons. Less than 80 000 pixel time series belonging to 8 land cover classes from a year of Sentinel-2 monthly syntheses are used. Results show on a test set of 131 polygons that CNNs using 3D convolutions in space and time are more accurate than 1D temporal, stacked 2D and RF approaches. Best-performing models are CNNs using spatio-temporal features, namely 3D-CNN, 2D-CNN and SpatioTempCNN, a two-stream model using both 1D and 3D convolutions. Numéro de notice : C2021-017 Affiliation des auteurs : non IGN Thématique : IMAGERIE/INFORMATIQUE Nature : Communication DOI : 10.5194/isprs-archives-XLIII-B2-2021-915-2021 Date de publication en ligne : 28/06/2021 En ligne : https://doi.org/10.5194/isprs-archives-XLIII-B2-2021-915-2021 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98069
Titre : Regional crop inventories in Europe assisted by remote sensing, 1988-1993 : Synthesis report of the Mars project, action 1 Type de document : Rapport Auteurs : C. Taylor, Auteur ; C. Sannier, Auteur ; J. Delince, Auteur ; F.J. Gallego, Auteur Editeur : Luxembourg : Office des Publications de l'Union Européenne Année de publication : 1997 Collection : Space Applications Institute Importance : 71 p. Format : 16 x 23 cm Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Agriculture
[Termes IGN] classification
[Termes IGN] Communauté Européenne
[Termes IGN] correction géométrique
[Termes IGN] cultures
[Termes IGN] image Landsat-TM
[Termes IGN] image SPOT XS
[Termes IGN] image SPOT-HRV
[Termes IGN] inventaire
[Termes IGN] télédétection spatialeRésumé : (Auteur) This report is a synthesis of the work, the results and an assessment of the achievements of Action I of the MARS Project. The report consist of this stand-alone executive summary and five additional sections. The first three enlarge on the main elements of the methodology : ground survey, remote sensing and the combination of these using regression. These sections also present a synthesis of the results and comments on their accuracy. Note de contenu : 1. CROP INVENTORY BY GROUND SURVEY
1.1 General Statistical Methodology
1.1.1 Summary of approach at each study site
1.1.2 Sample selection
1.1.3 Direct expansion estimates
1.1.4 Stratification
1.1.5 Example of stratified sample design
1.1.6 Efficiency of stratification
1.2 Application and variations.
1.2.1 Survey design
1.2.2 Field work
1.2.3 Data processing
1.3 Results and Conclusions
1.3.1 Accuracy of area estimates.
1.3.2 Timeliness of results
1.3.3 Efficiency of stratification
1.3.4 Yield estimates
2. SATELLITE REMOTE SENSING
2.1 Achievement of satellite image coverage
2.1.1 Satellite images used for regional inventories
2.1.2 Acquisition of satellite images
2.2 Remote sensing methodology
2.2.1 Fundamental concepts
2.2.2 Technical principles of geometric correction
2.2.3 Estimating the accuracy of geometric transformation
2.2.4 Technical principles of digital classification
2.2.5 Assessing the accuracy of digital classification
2.3 Application and results
2.3.1 Geometric correction
2.3.2 Classification of satellite imagery
2.3.3 Classification accuracy assessment
2.3.4 Timeliness
2.3.5 Yield estimation by remote sensing
3. CROP INVENTORY WITH REMOTE SENSING .
3.1 Methodology
3.1.1 Introduction
3.1.2 Relationship between ground survey and digital classification
3.1.3 The regression estimator
3.1.4 Neostratification imposed by satellite imagery.
3.1.5 Cost benefit of remote sensing
3.1.6 Implementation of the methodology
3.2 Results..
3.2.1 Improvement of estimates of main crop areas
3.2.2 Variation of results across test sites
3.2.3 Improved accuracy of crop area estimates vs. class area
3.2.4 Cost-effectiveness
3.2.5 Comparison with national statistics
3.2.6 Timeliness
3.2.7 Comparison with USDA-NASS results
4. TECHNICAL FACTORS INFLUENCING RESULTS.
4.1 Accuracy of ground surveys
4.2 Success of image coverage
4.3 Quality of geometric correction
4.4 Quality of regression relationships
4.5 Comments on Neostratification
4.6 Relationship between classification accuracy and improvement in precision .
4.7 Effect of different digital classification rulesNuméro de notice : 16739 Affiliation des auteurs : non IGN Nature : Rapport d'étude technique Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=41311 Exemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 16739-01 50.40 Livre Centre de documentation Environnement Disponible
