Centre de documentation
scientifique

Comparing nearest neighbor configurations in the prediction of species-specific diameter distributions / Janne Raty in Annals of Forest Science, vol 75 n° 1 (March 2018)  

Public [article]  inAnnals of Forest Science > vol 75 n° 1 (March 2018) Titre : Comparing nearest neighbor configurations in the prediction of species-specific diameter distributions Type de document : Article/Communication Auteurs : Janne Raty, Auteur ; Petteri Packalen, Auteur ; Matti Maltamo, Auteur Année de publication : 2018 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] classificateur non paramétrique [Termes IGN] diamètre des arbres [Termes IGN] Finlande [Termes IGN] forêt boréale [Termes IGN] image aérienne [Termes IGN] télémètre laser aéroporté [Termes IGN] volume en bois [Vedettes matières IGN] Sylviculture Résumé : (Auteur) We examine how the configurations in nearest neighbor imputation affect the performance of predicted species-specific diameter distributions. The simultaneous nearest neighbor imputation for all tree species and separate imputation by tree species are evaluated with total volume calibration as a prediction method for diameter distributions. This study considers the predictions of species-specific diameter distributions in Finnish boreal forests by means of airborne laser scanning (ALS) data and aerial images. The aim was to investigate different configurations in non-parametric nearest neighbor (NN) imputation and to determine how changes in configurations affect prediction error rates for timber assortment volumes and the error indices of the diameter distributions. Non-parametric NN imputation was used as a modeling method and was applied in two different ways: (1) diameter distributions were predicted at the same time for all tree species by simultaneous NN imputation, and (2) diameter distributions were predicted for one tree species at a time by separate NN imputation. Calibration to a regression-based total volume prediction was applied in both cases. The results indicated that significant changes in the volume prediction error rates for timber assortment and for error indices can be achieved by the selection of responses, calibration to total volume, and separate NN imputation by tree species. verall, the selection of response variables in NN imputation and calibration to total volume improved the predicted diameter distribution error rates. The most successful prediction performance of diameter distribution was achieved by separate NN imputation by tree species. Numéro de notice : A2018-314 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s13595-018-0711-0 Date de publication en ligne : 06/03/2018 En ligne : https://doi.org/10.1007/s13595-018-0711-0 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=90438 [article]

Spatial-spectral unsupervised convolutional sparse auto-encoder classifier for hyperspectral imagery / Xiaobing Han in Photogrammetric Engineering & Remote Sensing, PERS, vol 83 n° 3 (March 2017)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 83 n° 3 (March 2017) . - pp 195 - 206 Titre : Spatial-spectral unsupervised convolutional sparse auto-encoder classifier for hyperspectral imagery Type de document : Article/Communication Auteurs : Xiaobing Han, Auteur ; Yanfei Zhong, Auteur ; Liangpei Zhang, Auteur Année de publication : 2017 Article en page(s) : pp 195 - 206 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classificateur non paramétrique [Termes IGN] cohérence (physique) [Termes IGN] extraction de traits caractéristiques [Termes IGN] image hyperspectrale Résumé : (Auteur) The traditional spatial-spectral classification methods applied to hyperspectral remote sensing imagery are conducted by combining the spatial information vector and the spectral information vector in a separate manner, which may cause information loss and concatenation deficiency between the spatial and spectral information. In addition, the traditional morphological-based spatial-spectral classification methods require the design of handcrafted features according to experience, which is far from automatic and lacks generalization ability. To automatically represent the spatial-spectral features around the central pixel within a spatial neighborhood window, a novel spatial-spectral feature classification method based on the unsupervised convolutional sparse auto-encoder (UCSAE) with a window-in-window strategy is proposed in this study. The UCSAE algorithm features a unique spatial-spectral feature extraction approach which is executed in two stages. The first stage represents the spatial-spectral features within a spatial neighborhood window on the basis of spatial-spectral feature extraction of sub-windows with a sparse auto-encoder (SAE). The second stage exploits the spatial-spectral feature representation with a convolution mechanism for the larger outer windows. The UCSAE algorithm was validated by two widely used hyperspectral imagery datasets (the Pavia University dataset and the Washington DC Mall dataset) obtaining accuracies of 90.03 percent and 96.88 percent, respectively, which are better results than those obtained by the traditional hyperspectral spatial-spectral classification approaches. Numéro de notice : A2017-088 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.83.3.195 En ligne : https://doi.org/10.14358/PERS.83.3.195 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84423 [article]

Vectorisation automatique des forêts dans les minutes de la carte d’état-major du 19e siècle / Pierre-Alexis Herrault in Revue internationale de géomatique, vol 25 n° 1 (mars - mai 2015)  

Public [article]  inRevue internationale de géomatique > vol 25 n° 1 (mars - mai 2015) . - pp 35 - 51 Titre : Vectorisation automatique des forêts dans les minutes de la carte d’état-major du 19e siècle Type de document : Article/Communication Auteurs : Pierre-Alexis Herrault, Auteur ; David Sheeren , Auteur ; Mathieu Fauvel, Auteur ; Martin Paegelow, Auteur Année de publication : 2015 Article en page(s) : pp 35 - 51 Note générale : Bibliographie Langues : Français (fre) Descripteur : [Vedettes matières IGN] Géomatique [Termes IGN] carte d'Etat-Major [Termes IGN] classificateur non paramétrique [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] extraction automatique [Termes IGN] forêt [Termes IGN] vectorisation Résumé : (Auteur) Dans cet article, nous proposons une nouvelle méthode pour extraire automatiquement les forêts dans les cartes d’état-major du 19e siècle numérisées. La démarche proposée est constituée de quatre étapes principales : filtrage de l’image, changement d’espace colorimétrique, identification des forêts à l’aide d’un détecteur non paramétrique (SVDD), post-traitement. La méthode est suffisamment robuste pour prendre en compte la diversité des représentations possibles des forêts dans ces cartes anciennes. Les résultats montrent des performances élevées avec une précision globale de détection obtenue de 95%. Cette approche ouvre de nouvelles perspectives pour les différentes études environnementales incluant une dimension historique. Numéro de notice : A2015-067 Affiliation des auteurs : non IGN Thématique : FORET/GEOMATIQUE Nature : Article DOI : 10.3166/RIG.25.35-51 Date de publication en ligne : 14/01/2015 En ligne : https://doi.org/10.3166/RIG.25.35-51 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=75374 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
047-2015011	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Partial iterates for symmetrizing non-parametric color correction / Bruno Vallet in ISPRS Journal of photogrammetry and remote sensing, vol 82 (August 2013)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 82 (August 2013) . - pp 93 - 101 Titre : Partial iterates for symmetrizing non-parametric color correction Type de document : Article/Communication Auteurs : Bruno Vallet , Auteur ; Lâmân Lelégard , Auteur Année de publication : 2013 Article en page(s) : pp 93 - 101 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classificateur non paramétrique [Termes IGN] correction radiométrique [Termes IGN] luminance lumineuse [Termes IGN] mosaïquage d'images Résumé : (Auteur) Mosaic generation is a central tool in various fields ranging way beyond the scope of photogrammetry and requires the radiometry and color of the images to be corrected. Correction can either be done by a global parametric approach (looking for an optimal gain or gamma for each image of the mosaic), or by iteratively correcting image pairs with a non-parametric approach. Such non-parametric approaches allow for much finer correction but are asymmetric, i.e. they require the choice of a source image that will be corrected to match a target image. Thus the result on the whole mosaic will be very dependant on the order in which images are corrected. In this paper, we propose to use partial iterates to symmetrize non-parametric correction in order to solve this problem. Partial iterates formalize what partially applying a bijective function means and we explain how this can be done in both the continuous and discrete domain. This mechanism is applied to a simple non-parametric approach (histogram transfer of the luminance) to show its potential. Numéro de notice : A2013-413 Affiliation des auteurs : LASTIG MATIS (2012-2019) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2013.05.005 Date de publication en ligne : 11/06/2013 En ligne : https://doi.org/10.1016/j.isprsjprs.2013.05.005 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32551 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2013081	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Land cover classification of cloud-contaminated multitemporal high-resolution images / A. Salberg in IEEE Transactions on geoscience and remote sensing, vol 49 n° 1 Tome 2 (January 2011)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 49 n° 1 Tome 2 (January 2011) . - pp 377 - 387 Titre : Land cover classification of cloud-contaminated multitemporal high-resolution images Type de document : Article/Communication Auteurs : A. Salberg, Auteur Année de publication : 2011 Article en page(s) : pp 377 - 387 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] classificateur non paramétrique [Termes IGN] classification barycentrique [Termes IGN] classification dirigée [Termes IGN] classification par maximum de vraisemblance [Termes IGN] image Landsat-ETM+ [Termes IGN] image Landsat-TM [Termes IGN] image multitemporelle [Termes IGN] image optique [Termes IGN] Norvège [Termes IGN] occupation du sol Résumé : (Auteur) We show how methods proposed in the statistical community dealing with missing data may be applied for land cover classification, where optical observations are missing due to clouds and snow. The proposed method is divided into two stages: 1) cloud/snow classification and 2) training and land cover classification. The purpose of the cloud/snow classification stage is to determine which pixels are missing due to clouds and snow. All pixels in each optical image are classified into the classes cloud, snow, water, and vegetation using a suitable classifier. The pixels classified as cloud or snow are labeled as missing, and this information is used in the subsequent training and classification stage, which deals with classification of the pixels into various land cover classes. For land cover classification, we apply the maximum-likelihood (assuming normal distributions), -nearest neighbor, and Parzen classifiers, all modified to handle missing features. The classifiers are evaluated on Landsat (both Thematic Mapper and Enhanced Thematic Mapper Plus) images covering a scene at about 900 m a.s.l. in the Hardangervidda mountain plateau in Southern Norway, where 4869 in situ samples of the land cover classes water, ridge, leeside, snowbed, mire, forest, and rock are obtained. The results show that proper modeling of the missing pixels improves the classification rate by 5%-10%, and by using multiple images, we increase the chance of observing the land cover type substantially. The nonparametric classifiers handle nonignorable missing-data mechanisms and are therefore particularly suitable for remote sensing applications where the pixels covered by snow and cloud may depend on the land cover type. Numéro de notice : A2011-052 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2010.2052464 Date de publication en ligne : 26/07/2010 En ligne : https://doi.org/10.1109/TGRS.2010.2052464 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=30833 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2011011B	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Rewiew of non-parametric models for dam deformation analysis in China / N. Deng in Geomatica, vol 63 n° 3 (September 2009)  

Permalink

Urban-trees extraction from Quickbird imagery using multiscale spectex-filtering and non-parametric classification / Y.O. Ouma in ISPRS Journal of photogrammetry and remote sensing, vol 63 n° 3 (May - June 2008)  

Permalink

Fusion of support vector machines for classification of multisensor data / Björn Waske in IEEE Transactions on geoscience and remote sensing, vol 45 n° 12 Tome 1 (December 2007)  

Permalink

Nonparametric weighted feature extraction for classification / D.A. Landgrebe in IEEE Transactions on geoscience and remote sensing, vol 42 n° 5 (May 2004)  

Permalink

Classifying land development in high-resolution panchromatic satellite images using straight-line statistics / C. Unsalan in IEEE Transactions on geoscience and remote sensing, vol 42 n° 4 (April 2004)  

Permalink

Le boosting : une méthode de classification non paramétrique / Michel Arnaud in Revue internationale de géomatique, vol 12 n° 4 (décembre 2002 – février 2003)  

Permalink

A robust classification procedure based on mixture classifiers and nonparametric weighted feature extraction / B.C. Kuo in IEEE Transactions on geoscience and remote sensing, vol 40 n° 11 (November 2002)  

Permalink

Impact of contextual information integration on pixel fusion / Sophie Fabre in IEEE Transactions on geoscience and remote sensing, vol 40 n° 9 (September 2002)  

Permalink

A probabilistic modification of the decision rule in the skidmore-turner supervised nonparametric classifier / K.E. Lowell in Photogrammetric Engineering & Remote Sensing, PERS, vol 55 n° 6 (june 1989)  

Permalink

Unsupervised training area selection in forests using a nonparametric distance measure and spatial information / Andrew K. Skidmore in International Journal of Remote Sensing IJRS, vol 10 n° 1 (January 1989)  

Permalink