Descripteur
Termes IGN > informatique > intelligence artificielle > apprentissage automatique > méthode fondée sur le noyau
méthode fondée sur le noyau |
Documents disponibles dans cette catégorie (64)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Semisupervised transfer component analysis for domain adaptation in remote sensing image classification / Giona Matasci in IEEE Transactions on geoscience and remote sensing, vol 53 n° 7 (July 2015)
[article]
Titre : Semisupervised transfer component analysis for domain adaptation in remote sensing image classification Type de document : Article/Communication Auteurs : Giona Matasci, Auteur ; Michele Volpi, Auteur ; Mikhail Kanevski, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 3550 - 3564 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection
[Termes IGN] analyse comparative
[Termes IGN] classification à base de connaissances
[Termes IGN] classification automatique
[Termes IGN] découverte de connaissances
[Termes IGN] extraction automatique
[Termes IGN] méthode fondée sur le noyau
[Termes IGN] occupation du solRésumé : (Auteur) In this paper, we study the problem of feature extraction for knowledge transfer between multiple remotely sensed images in the context of land-cover classification. Several factors such as illumination, atmospheric, and ground conditions cause radiometric differences between images of similar scenes acquired on different geographical areas or over the same scene but at different time instants. Accordingly, a change in the probability distributions of the classes is observed. The purpose of this work is to statistically align in the feature space an image of interest that still has to be classified (the target image) to another image whose ground truth is already available (the source image). Following a specifically designed feature extraction step applied to both images, we show that classifiers trained on the source image can successfully predict the classes of the target image despite the shift that has occurred. In this context, we analyze a recently proposed domain adaptation method aiming at reducing the distance between domains, Transfer Component Analysis, and assess the potential of its unsupervised and semisupervised implementations. In particular, with a dedicated study of its key additional objectives, namely the alignment of the projection with the labels and the preservation of the local data structures, we demonstrate the advantages of Semisupervised Transfer Component Analysis. We compare this approach with other both linear and kernel-based feature extraction techniques. Experiments on multi- and hyperspectral acquisitions show remarkable cross- image classification performances for the considered strategy, thus confirming its suitability when applied to remotely sensed images. Numéro de notice : A2015-319 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2377785 En ligne : https://doi.org/10.1109/TGRS.2014.2377785 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76570
in IEEE Transactions on geoscience and remote sensing > vol 53 n° 7 (July 2015) . - pp 3550 - 3564[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-2015071 RAB Revue Centre de documentation En réserve L003 Disponible Spectral–spatial kernel regularized for hyperspectral image denoising full text / Yuan Yuan in IEEE Transactions on geoscience and remote sensing, vol 53 n° 7 (July 2015)
[article]
Titre : Spectral–spatial kernel regularized for hyperspectral image denoising full text Type de document : Article/Communication Auteurs : Yuan Yuan, Auteur ; Xianngtao Zheng, Auteur ; Xiaoqiang Lu, Auteur Année de publication : 2015 Article en page(s) : pp 3815 - 3832 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] filtrage du bruit
[Termes IGN] filtre adaptatif
[Termes IGN] image hyperspectrale
[Termes IGN] méthode fondée sur le noyauRésumé : (Auteur) Noise contamination is a ubiquitous problem in hyperspectral images (HSIs), which is a challenging and promising theme in many remote sensing applications. A large number of methods have been proposed to remove noise. Unfortunately, most denoising methods fail to take full advantages of the high spectral correlation and to simultaneously consider the specific noise distributions in HSIs. Recently, a spectral-spatial adaptive hyperspectral total variation (SSAHTV) was proposed and obtained promising results. However, the SSAHTV model is insensitive to the image details, which makes the edges blur. To overcome all of these drawbacks, a spectral-spatial kernel method for HSI denoising is proposed in this paper. The proposed method is inspired by the observation that the spectral-spatial information is highly redundant in HSIs, which is sufficient to estimate the clear images. In this paper, a spectral-spatial kernel regularization is proposed to maintain the spectral correlations in spectral dimension and to match the original structure between two spatial dimensions. Moreover, an adaptive mechanism is developed to balance the fidelity term according to different noise distributions in each band. Therefore, it cannot only suppress noise in the high-noise band but also preserve information in the low-noise band. The reliability of the proposed method in removing noise is experimentally proved on both simulated data and real data. Numéro de notice : A2015-318 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2014.2385082 En ligne : https://doi.org/10.1109/TGRS.2014.2385082 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=76569
in IEEE Transactions on geoscience and remote sensing > vol 53 n° 7 (July 2015) . - pp 3815 - 3832[article]Réservation
Réserver ce documentExemplaires(1)
Code-barres Cote Support Localisation Section Disponibilité 065-2015071 RAB Revue Centre de documentation En réserve L003 Disponible Analytical estimation of map readability / Lars Harrie in ISPRS International journal of geo-information, vol 4 n°2 (June 2015)
[article]
Titre : Analytical estimation of map readability Type de document : Article/Communication Auteurs : Lars Harrie, Auteur ; Hanna Stigmar, Auteur ; Milan Djordjevic, Auteur Année de publication : 2015 Article en page(s) : pp 418 - 446 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] apprentissage dirigé
[Termes IGN] distribution spatiale
[Termes IGN] généralisation cartographique automatisée
[Termes IGN] lisibilité perceptive
[Termes IGN] régression multiple
[Termes IGN] séparateur à vaste marge
[Termes IGN] seuillage
[Termes IGN] test de performance
[Termes IGN] utilisateur
[Vedettes matières IGN] CartologieRésumé : (auteur) Readability is a major issue with all maps. In this study, we evaluated whether we can predict map readability using analytical measures, both single measures and composites of measures. A user test was conducted regarding the perceived readability of a number of test map samples. Evaluations were then performed to determine how well single measures and composites of measures could describe the map readability. The evaluation of single measures showed that the amount of information was most important, followed by the spatial distribution of information. The measures of object complexity and graphical resolution were not useful for explaining the map readability of our test data. The evaluations of composites of measures included three methods: threshold evaluation, multiple linear regression and support vector machine. We found that the use of composites of measures was better for describing map readability than single measures, but we could not identify any major differences in the results of the three composite methods. The results of this study can be used to recommend readability measures for triggering and controlling the map generalization process of online maps. Numéro de notice : A2015-701 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.3390/ijgi4020418 En ligne : https://doi.org/10.3390/ijgi4020418 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=78343
in ISPRS International journal of geo-information > vol 4 n°2 (June 2015) . - pp 418 - 446[article]
Titre : A fast summation method for translation invariant kernels Type de document : Article/Communication Auteurs : Fabien Casenave , Auteur Editeur : Ithaca [New York - Etats-Unis] : ArXiv - Université Cornell Année de publication : 2015 Importance : 19 p. Format : 21 x 30 cm Note générale : arXiv:1408.0210v3 [math.NA] 22 Aug 2015
ex titre : An Empirical Interpolation based Fast Summation Method for translation invariant kernelsLangues : Anglais (eng) Descripteur : [Termes IGN] méthode fondée sur le noyau Résumé : (auteur) We derive a Fast Multipole Method (FMM) where a low-rank approximation of the kernel is obtained using the Empirical Interpolation Method (EIM). Contrary to classical interpolation-based FMM, where the interpolation points and basis are fixed beforehand, the EIM is a nonlinear approximation method which constructs interpolation points and basis which are adapted to the kernel under consideration. The basis functions are obtained using evaluations of the kernel itself. We restrict ourselves to translation-invariant kernels, for which a modified version of the EIM approximation can be used in a multilevel FMM context; we call the obtained algorithm Empirical Interpolation Fast Multipole Method (EIFMM). An important feature of the EIFMM is a built-in error estimation of the interpolation error made by the low-rank approximation of the far-field behavior of the kernel: the algorithm selects the optimal number of interpolation points required to ensure a given accuracy for the result, leading to important gains for inhomogeneous kernels. Numéro de notice : P2015-002 Affiliation des auteurs : LASTIG LAREG (2012-mi2018) Thématique : MATHEMATIQUE Nature : Preprint nature-HAL : Préprint DOI : 10.48550/arXiv.1408.0210 Date de publication en ligne : 22/08/2015 En ligne : https://doi.org/10.48550/arXiv.1408.0210 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=88642 Documents numériques
peut être téléchargé
A fast summation method - pdf auteurAdobe Acrobat PDF Noisy data smoothing in DEM construction using least squares support vector machines / C. Chen in Transactions in GIS, vol 18 n° 6 (December 2014)
[article]
Titre : Noisy data smoothing in DEM construction using least squares support vector machines Type de document : Article/Communication Auteurs : C. Chen, Auteur ; Y. Li, Auteur ; H. Dai, Auteur ; et al., Auteur Année de publication : 2014 Article en page(s) : pp 896 – 910 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications photogrammétriques
[Termes IGN] bruit (théorie du signal)
[Termes IGN] données lidar
[Termes IGN] modèle numérique du bâti
[Termes IGN] séparateur à vaste margeRésumé : (Auteur) Since spatial datasets are subject to sampling errors, a smoothing interpolation method should be employed to remove noise during DEM construction. Although least squares support vector machines (LSSVM) have been widely accepted as a classifier, their effect on smoothing noisy data is almost unknown. In this article, the smoothness of LSSVM was explored, and its effect on smoothing noisy data in DEM construction was tested. In order to improve the ability to deal with large datasets, a local method of LSSVM has been developed, where only the neighboring sampling points around the one to be estimated are used for computation. A numerical test indicated that LSSVM is more accurate than the classical smoothing methods including TPS and kriging, and its error surfaces are more evenly distributed. The real-world example of smoothing noise inherent in lidar-derived DEMs also showed that LSSVM has a positive smoothing effect, which is approximately as accurate as TPS. In short, LSSVM with a high efficiency can be considered as an alternative smoothing method for smoothing noisy data in DEM construction. Numéro de notice : A2014-576 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1111/tgis.12078 Date de publication en ligne : 26/02/2014 En ligne : https://doi.org/10.1111/tgis.12078 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=74766
in Transactions in GIS > vol 18 n° 6 (December 2014) . - pp 896 – 910[article]Detecting cars in UAV images with a catalog-based approach / Thomas Moranduzzo in IEEE Transactions on geoscience and remote sensing, vol 52 n° 10 tome 1 (October 2014)PermalinkCombining RapidEye and lidar satellite imagery for mapping of mining and mine reclamation / Aaron E. Maxwell in Photogrammetric Engineering & Remote Sensing, PERS, vol 80 n° 2 (February 2014)PermalinkGeneralized composite kernel framework for hyperspectral image classification / J. Li in IEEE Transactions on geoscience and remote sensing, vol 51 n° 9 (September 2013)PermalinkPermalinkActive learning methods for biophysical parameter estimation / Edoardo Pasolli in IEEE Transactions on geoscience and remote sensing, vol 50 n° 10 Tome 2 (October 2012)PermalinkA multi-resolution hybrid approach for building model reconstruction from lidar data / M. Satari in Photogrammetric record, vol 27 n° 139 (September - November 2012)PermalinkRepresentative multiple Kernel learning for classification in hyperspectral imagery / Y. Gu in IEEE Transactions on geoscience and remote sensing, vol 50 n° 7 Tome 2 (July 2012)PermalinkParameterizing support vector machines for land cover classification / X. Yang in Photogrammetric Engineering & Remote Sensing, PERS, vol 77 n° 1 (January 2011)PermalinkOptimizing Support Vector Machine learning for semi-arid vegetation mapping by using clustering analysis / L. Su in ISPRS Journal of photogrammetry and remote sensing, vol 64 n° 4 (July - August 2009)Permalinkvol 29 n° 21 - October 2008 - Satellite observations of the atmosphere, oceans and their interface in relation to climate, natural hazards and management of coastal zone (Bulletin de International Journal of Remote Sensing IJRS) / G. LevyPermalink