e324c038-08f3-4a11-aca2-7abbeda014e7 83867504-286c-4436-b3fc-436ffdc1d912 Thomas Houet LETG - Univ Rennes 2 thomas.houet@univ-rennes2.fr Christiane Weber UMR TETIS - CNRS Christiane.Weber@cnrs.fr Claudia Lavalley UMR TETIS - CNRS Claudia. Lavalley@cnrs.fr 2022-05-17T19:25:04 ISO 19115:2003/19139 1.0 4326 EPSG Toulouse 2015 Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature 2022-05-17T19:09:06 1.0 2015-01-01 e324c038-08f3-4a11-aca2-7abbeda014e7 Christiane Weber UMR TETIS - CNRS Christiane.Weber@cnrs.fr Hyperspectral data were obtained during an acquisition campaign led on Toulouse (France) urban area on July 2015 using Hyspex instrument which provides 408 spectral bands spread over 0.4 – 2.5 μ. Flight altitude lead to 2 m spatial resolution images. Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature: leaf type (5 classes), family (12 and 19 classes) and species (14 and 27 classes). The number of classes differ for the two latter as they depend on the minimum number of individuals considered (4 and 10 individuals per class respectively). Trees positions have been acquired using differential GPS and are given with centimetric to decimetric precision. A randomly selected subset of these trees has been used to train machine SVM and Random Forest classification algorithms. Those algorithms were applied to hyperspectral images using a number of classes for family (12 and 19 classes) and species (14 and 27 classes) levels defined according to the minimum number of individuals considered during training/validation process (4 and 10 individuals per class, respectively). Global classification precision for several training subsets is given by Brabant et al, 2019 (https://www.mdpi.com/470202) in terms of averaged overall accuracy (AOA) and averaged kappa index of agreement (AKIA). Provide with urban trees 3 level nomenclature Christiane Weber UMR TETIS - CNRS Christiane.Weber@cnrs.fr http://idg-tetis.teledetection.fr/data/vignettes/HYEPSVNTreesClassification.png SVN Toulouse urban Trees classification image/png remote sensing VHRS imagery HYPERSPECTRAL imagery urban studies General 2015-01-01T01:00:00 Land cover GEMET - INSPIRE themes, version 1.0 2008-06-01 artificial land urban ecology GEMET - Concepts 2010-01-13 LAND USE/LAND COVER CLASSIFICATION INFRARED IMAGERY VISIBLE IMAGERY URBAN AREAS GCMD Keywords viewer 2019-04-24 HYEP Urbain TETIS Thesaurus, version 1.0 21112019 2019-11-21 This work is licensed under a Creative Commons Attribution 4.0 License (CC BY 4.0, https://creativecommons.org/licenses/by/4.0). unclassified no classification in particular description geoscientificInformation environment 1.2842469 1.6042469 43.4444622 43.7644622 2015-07-01T00:00:00Z 2015-07-31T00:00:00Z some additional information ESRI Shapefile 1.0 https://zenodo.org/record/3611240/files/Fields_samples.7z?download=1 file for download geopackage file http://idg-tetis-gs.teledetection.fr:8080/geoserver/idg-tetis/wms OGC:WMS species_27classes WMS Service Data Quality check This is is some data quality check report 2022-05-17T19:09:06 some explanation about the conformance true Commission Regulation (EU) No 1089/2010 of 23 November 2010 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards interoperability of spatial data sets and services 2010-12-08T12:00:00 See the referenced specification true COMMISSION REGULATION (EC) No 1205/2008 of 3 December 2008 implementing Directive 2007/2/EC of the European Parliament and of the Council as regards metadata 2008-12-04T12:00:00 See the referenced specification true Hyperspectral data were obtained during an acquisition campaign led on Toulouse (France) urban area on July 2015 using Hyspex instrument which provides 408 spectral bands spread over 0.4 – 2.5 μ. Flight altitude lead to 2 m spatial resolution images. Supervised SVN classification results for 600 urban trees according to a 3 level nomenclature: leaf type (5 classes), family (12 and 19 classes) and species (14 and 27 classes). The number of classes differ for the two latter as they depend on the minimum number of individuals considered (4 and 10 individuals per class respectively). Trees positions have been acquired using differential GPS and are given with centimetric to decimetric precision. A randomly selected subset of these trees has been used to train machine SVM and Random Forest classification algorithms. Those algorithms were applied to hyperspectral images using a number of classes for family (12 and 19 classes) and species (14 and 27 classes) levels defined according to the minimum number of individuals considered during training/validation process (4 and 10 individuals per class, respectively). Global classification precision for several training subsets is given by Brabant et al, 2019 (https://www.mdpi.com/470202) in terms of averaged overall accuracy (AOA) and averaged kappa index of agreement (AKIA).