Centre de documentation
scientifique

Development of a network-based method for unmixing of hyperspectral data / V. Karathanassi in IEEE Transactions on geoscience and remote sensing, vol 50 n° 3 (March 2012)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 50 n° 3 (March 2012) . - pp 839 - 849 Titre : Development of a network-based method for unmixing of hyperspectral data Type de document : Article/Communication Auteurs : V. Karathanassi, Auteur ; D. Sykas, Auteur ; Konstantinos Topouzelis, Auteur Année de publication : 2012 Article en page(s) : pp 839 - 849 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse des mélanges spectraux [Termes IGN] distance euclidienne [Termes IGN] image hyperspectrale Résumé : (Auteur) This paper presents a new nonlinear unmixing method. Based on relative distances which imply nonlinearity, the method introduces the “fractional distance” as a key variable that quantifies interactions between pixels and endmembers. Relationships between fractional distances and abundance fractions are built through networks. Because an equal spectral mixture of ground spectral classes present on the surface sensed is likely impossible, the proposed method, due to its mathematical concept, reveals unknown endmembers. Three versions of the method have been developed: the nonconstrained, the sum-to-one, and the fully constrained versions. Evaluation of the method using synthetic and real data showed that the method is robust with clear and interpretable results and provides reliable abundance fractions, particularly the sum-to-one and the fully constrained versions of the method. The new unmixing method has also been compared with the fully constrained least squares method. Numéro de notice : A2012-099 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2011.2163412 Date de publication en ligne : 15/09/2011 En ligne : https://doi.org/10.1109/TGRS.2011.2163412 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31547 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2012031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes / Konstantinos Topouzelis in Geocarto international, vol 24 n° 3 (June - July 2009)  

Public [article]  inGeocarto international > vol 24 n° 3 (June - July 2009) . - pp 179 - 191 Titre : Potentiality of feed-forward neural networks for classifying dark formations to oil spills and look-alikes Type de document : Article/Communication Auteurs : Konstantinos Topouzelis, Auteur ; V. Karathanassi, Auteur ; P. Pavlaskis, Auteur ; D. Rokos, Auteur Année de publication : 2009 Article en page(s) : pp 179 - 191 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] classification par réseau neuronal [Termes IGN] détection [Termes IGN] fonction de base radiale [Termes IGN] hydrocarbure [Termes IGN] image radar [Termes IGN] marée noire [Termes IGN] Perceptron multicouche [Termes IGN] pollution des mers [Termes IGN] rétrodiffusion Résumé : (Auteur) Radar backscatter values from oil spills are very similar to backscatter values from very calm sea areas and other ocean phenomena. Several studies aiming at oil spill detection have been conducted. Most of these studies rely on the detection of dark areas, which have high Bayesian probability of being oil spills. The drawback of these methods is a complex process, mainly because non-linearly separable datasets are introduced in statistically based decisions. The use of neural networks (NNs) in remote sensing has increased significantly, as NNs can simultaneously handle non-linear data of a multidimensional input space. In this article, we investigate the ability of two commonly used feed-forward NN models: multilayer perceptron (MLP) and radial basis function (RBF) networks, to classify dark formations in oil spills and look-alike phenomena. The appropriate training algorithm, type and architecture of the optimum network are subjects of research. Inputs to the networks are the original synthetic aperture radar image and other images derived from it. MLP networks are recognized as more suitable for oil spill detection. Numéro de notice : A2009-186 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106040802488526 Date de publication en ligne : 19/05/2009 En ligne : https://doi.org/10.1080/10106040802488526 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29816 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-09031	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Detection and discrimination between oil spills and look-alike phenomena through neural networks / Konstantinos Topouzelis in ISPRS Journal of photogrammetry and remote sensing, vol 62 n° 4 (September 2007)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 62 n° 4 (September 2007) . - pp 264 - 270 Titre : Detection and discrimination between oil spills and look-alike phenomena through neural networks Type de document : Article/Communication Auteurs : Konstantinos Topouzelis, Auteur ; V. Karathanassi, Auteur ; P. Pavlakis, Auteur ; D. Rokos, Auteur Année de publication : 2007 Article en page(s) : pp 264 - 270 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image radar et applications [Termes IGN] analyse discriminante [Termes IGN] classification par réseau neuronal [Termes IGN] détection automatique [Termes IGN] image radar moirée [Termes IGN] marée noire [Termes IGN] radargrammétrie Résumé : (Auteur) Synthetic Aperture Radar (SAR) images are extensively used for dark formation detection in the marine environment, as their recording is independent of clouds and weather. Dark formations can be caused by man made actions (e.g. oil spill discharging) or natural ocean phenomena (e.g. natural slicks, wind front areas). Radar backscatter values for oil spills are very similar to backscatter values for very calm sea areas and other ocean phenomena because they damp the capillary and short gravity sea waves. The ability of neural networks to detect dark formations in high resolution SAR images and to discriminate oil spills from look-alike phenomena simultaneously was examined. Two different neural networks are used; one to detect dark formations and the second one to perform a classification to oil spills or look-alikes. The proposed method is very promising in detecting dark formations and discriminating oil spills from look-alikes as it detects with an overall accuracy of 94% the dark formations and discriminate correctly 89% of examined cases. Numéro de notice : A2007-428 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2007.05.003 En ligne : https://doi.org/10.1016/j.isprsjprs.2007.05.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=28791 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-07061	SL	Revue	Centre de documentation	Revues en salle	Disponible