Centre de documentation
scientifique

Automatic segment-level tree species recognition using high resolution aerial winter imagery / Anton Kuzmin in European journal of remote sensing, vol 49 n° 1 (2016)  

Public [article]  inEuropean journal of remote sensing > vol 49 n° 1 (2016) . - pp 239 - 259 Titre : Automatic segment-level tree species recognition using high resolution aerial winter imagery Type de document : Article/Communication Auteurs : Anton Kuzmin, Auteur ; Lauri Korhonen, Auteur ; Terhikki Manninen, Auteur ; Matti Maltamo, Auteur Année de publication : 2016 Article en page(s) : pp 239 - 259 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] analyse d'image orientée objet [Termes IGN] analyse discriminante [Termes IGN] betula pubescens [Termes IGN] composition floristique [Termes IGN] forêt boréale [Termes IGN] hélicoptère [Termes IGN] hiver [Termes IGN] image à ultra haute résolution [Termes IGN] image aérienne [Termes IGN] neige [Termes IGN] Picea abies [Termes IGN] Pinus sylvestris Résumé : (auteur) Our objective was to automatically recognize the species composition of a boreal forest from high-resolution airborne winter imagery. The forest floor was covered by snow so that the contrast between the crowns and the background was maximized. The images were taken from a helicopter flying at low altitude so that fine details of the canopy structure could be distinguished. Segments created by an object-oriented image processing were used as a basis for a linear discriminant analysis, which aimed at separating the three dominant tree species occurring in the area: Scots pine, Norway spruce, and downy birch. In a cross validation, the classification showed an overall accuracy of 81.9%, and a kappa coefficient of 0.73. Numéro de notice : A2016-831 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.5721/EuJRS20164914 En ligne : http://dx.doi.org/10.5721/EuJRS20164914 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82714 [article]

Leaf area index estimation of boreal and subarctic forests using VV/HH ENVISAT/ASAR data of various swaths / Terhikki Manninen in IEEE Transactions on geoscience and remote sensing, vol 51 n° 7 Tome 1 (July 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 7 Tome 1 (July 2013) . - pp 3899 - 3909 Titre : Leaf area index estimation of boreal and subarctic forests using VV/HH ENVISAT/ASAR data of various swaths Type de document : Article/Communication Auteurs : Terhikki Manninen, Auteur Année de publication : 2013 Article en page(s) : pp 3899 - 3909 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] fauchée [Termes IGN] forêt boréale [Termes IGN] image Envisat-ASAR [Termes IGN] Leaf Area Index [Termes IGN] polarimétrie radar [Termes IGN] télédétection en hyperfréquence Résumé : (Auteur) This paper demonstrates the potential of dual polarization synthetic aperture radar (SAR) images in the estimation of the leaf area index (LAI) of boreal forests. The SAR data do not suffer from the low sun elevation and frequent cloud cover, which often complicate the use of optical wavelengths for LAI retrieval in the area. The analysis was based on a large number of environmental satellite (ENVISAT) advanced synthetic aperture radar (ASAR) alternating polarization vertical polarization (VV)/horizontal polarization (HH) single-look-complex images covering several test sites, boreal and subarctic, during summers 2003-2006. The swath range from IS1 to IS7 was studied. In all test sites, a linear regression with the VV/HH backscattering ratio as the independent variable could typically be used for the estimation of LAI. All swaths could be used for the estimation, but larger incidence angles generally performed better. The best results were obtained for swath IS6. The swaths could be used also together, but better results were obtained using the diverse swaths individually. The LAI estimation error decreased essentially exponentially with the number of pixels averaged to give one backscattering value. The LAI estimation accuracy for a set of average quality ASAR images of swath IS6 reached 0.1 when the averaging number of pixels was 33 150, which would correspond to an area of about 2.2 km2 for images with no overlap. The spatial LAI estimation error decreased with the number of images covering the same area. Numéro de notice : A2013-368 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2227327 En ligne : https://doi.org/10.1109/TGRS.2012.2227327 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32506 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013071A	RAB	Revue	Centre de documentation	En réserve L003	Disponible