Centre de documentation
scientifique

A fast volume-gradient-based band selection method for hyperspectral image / X. Geng in IEEE Transactions on geoscience and remote sensing, vol 52 n° 11 tome 1 (November 2014)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 52 n° 11 tome 1 (November 2014) . - pp 7111 - 7119 Titre : A fast volume-gradient-based band selection method for hyperspectral image Type de document : Article/Communication Auteurs : X. Geng, Auteur ; Kang Sun, Auteur ; L. Ji, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp 7111 - 7119 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] bande spectrale [Termes IGN] gradient [Termes IGN] image hyperspectrale [Termes IGN] volume (grandeur) Résumé : (Auteur) In this paper, a subtle relationship is found between the volume of a subsimplex and the volume gradient of a simplex with respect to hyperspectral images. By using this relationship, we propose an efficient band selection method, namely, the volume-gradient-based band selection (VGBS) method. The VGBS method is an unsupervised method, which tries to remove the most redundant band successively. Interestingly, the VGBS method can find the most redundant band based only on the gradient of volume instead of calculating the volumes of all subsimplexes. Experiments on simulated and real hyperspectral data verify the efficiency of the proposed method. Numéro de notice : A2014-544 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2307880 En ligne : https://doi.org/10.1109/TGRS.2014.2307880 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74162 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2014111A	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Soil landscapes of Canada: Building a national framework for environmental information / P. Schut in Geomatica, vol 65 n° 3 (September 2011)  

Public [article]  inGeomatica > vol 65 n° 3 (September 2011) . - pp 293 - 309 Titre : Soil landscapes of Canada: Building a national framework for environmental information Type de document : Article/Communication Auteurs : P. Schut, Auteur ; S. Smith, Auteur ; W. Fraser, Auteur ; X. Geng, Auteur ; D. Kroetsch, Auteur Année de publication : 2011 Article en page(s) : pp 293 - 309 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées [Termes IGN] base de données localisées [Termes IGN] base de données thématiques [Termes IGN] Canada [Termes IGN] carte pédologique [Termes IGN] modélisation spatiale [Termes IGN] occupation du sol [Termes IGN] pédologie locale [Termes IGN] système d'information géographique Résumé : (Auteur) The Soil Landscapes of Canada (SLC) is a national soil map and accompanying database of environmental information for all of Canada, produced and maintained by the Canadian Soil Information Service (CanSIS) which is a part of Agriculture and Agri-Food Canada. The SLC maps were originally published as a set of paper products for individual provinces and regions. The maps were digitized in CanSIS, using one of the first geographic information systems in the world, and linked to soil and landscape attribute tables to serve an evolving variety of spatial modelling applications. The SLCs form the lowest level of the National ecological Framework for Canada. The latest public release of the SLC is version 3.2, which provides updated soil and landscape information for the agricultural areas of Canada. The SLC v3.2 digital coverage includes an extensive set of relational data tables. The component table lists the soil components in each agricultural polygon along with their predicted dominant slope, class, and extent. The soil component codes are also linked to soil attribute tables which define fundamental soil properties, such as classification and parent material, as well as a description of the soil horizons and key soil attributes to a depth of 100 cm. SLC v3.2 adds a new set of landform tables which identify the major landform type in each polygon and indicates the most likely soil components in the upper, mid slope, lower slope, and depressional positions. These soil and landform attributes are designed to support a wide variety of national and international environmental modelling applications, such as the prediction of soil quality change, soil carbon sequestration, and land productivity for different agricultural crops in response to agricultural policy, land management, and climate change scenarios. Future versions of the SLC are under development that will have improved spatial resolution and include soils data for areas beyond the present agricultural zone of Canada. Numéro de notice : A2011-549 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article DOI : 10.5623/cig2011-045 En ligne : https://doi.org/10.5623/cig2011-045 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31443 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
035-2011031	RAB	Revue	Centre de documentation	En réserve L003	Disponible