Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification par séparateurs à vaste marge
classification par séparateurs à vaste margeSynonyme(s)classification SVMVoir aussi |
Documents disponibles dans cette catégorie (253)



Etendre la recherche sur niveau(x) vers le bas
Investigating the impact of pan sharpening on the accuracy of land cover mapping in Landsat OLI imagery / Komeil Rokni in Geodesy and cartography, vol 49 n° 1 (January 2023)
![]()
[article]
Titre : Investigating the impact of pan sharpening on the accuracy of land cover mapping in Landsat OLI imagery Type de document : Article/Communication Auteurs : Komeil Rokni, Auteur Année de publication : 2023 Article en page(s) : pp 12 - 18 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] algorithme de Gram-Schmidt
[Termes IGN] carte d'occupation du sol
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] image Landsat-OLI
[Termes IGN] image multibande
[Termes IGN] image panchromatique
[Termes IGN] Kappa de Cohen
[Termes IGN] matrice de confusion
[Termes IGN] pansharpening (fusion d'images)
[Termes IGN] précision de la classificationRésumé : (auteur) Pan Sharpening is normally applied to sharpen a multispectral image with low resolution by using a panchromatic image with a higher resolution, to generate a high resolution multispectral image. The present study aims at assessing the power of Pan Sharpening on improvement of the accuracy of image classification and land cover mapping in Landsat 8 OLI imagery. In this respect, different Pan Sharpening algorithms including Brovey, Gram-Schmidt, NNDiffuse, and Principal Components were applied to merge the Landsat OLI panchromatic band (15 m) with the Landsat OLI multispectral: visible and infrared bands (30 m), to generate a new multispectral image with a higher spatial resolution (15 m). Subsequently, the support vector machine approach was utilized to classify the original Landsat and resulting Pan Sharpened images to generate land cover maps of the study area. The outcomes were then compared through the generation of confusion matrix and calculation of kappa coefficient and overall accuracy. The results indicated superiority of NNDiffuse algorithm in Pan Sharpening and improvement of classification accuracy in Landsat OLI imagery, with an overall accuracy and kappa coefficient of about 98.66% and 0.98, respectively. Furthermore, the result showed that the Gram-Schmidt and Principal Components algorithms also slightly improved the accuracy of image classification compared to original Landsat image. The study concluded that image Pan Sharpening is useful to improve the accuracy of image classification in Landsat OLI imagery, depending on the Pan Sharpening algorithm used for this purpose. Numéro de notice : A2023-142 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.3846/gac.2023.15308 Date de publication en ligne : 17/02/2023 En ligne : https://doi.org/10.3846/gac.2023.15308 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102712
in Geodesy and cartography > vol 49 n° 1 (January 2023) . - pp 12 - 18[article]Discriminating pure Tamarix species and their putative hybrids using field spectrometer / Solomon G. Tesfamichael in Geocarto international, vol 37 n° 25 ([01/12/2022])
![]()
[article]
Titre : Discriminating pure Tamarix species and their putative hybrids using field spectrometer Type de document : Article/Communication Auteurs : Solomon G. Tesfamichael, Auteur ; Solomon W. Newete, Auteur ; Elhadi Adam, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 7733 - 7752 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] Afrique du sud (état)
[Termes IGN] apprentissage automatique
[Termes IGN] canopée
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] espèce exotique envahissante
[Termes IGN] essence indigène
[Termes IGN] Extreme Gradient Machine
[Termes IGN] feuille (végétation)
[Termes IGN] image Landsat-8
[Termes IGN] image Sentinel-MSI
[Termes IGN] image SPOT 6
[Termes IGN] image Worldview
[Termes IGN] spectroradiomètre
[Termes IGN] Tamarix (genre)Résumé : (auteur) South Africa is home to a native Tamarix species, while two were introduced in the early 1900s to mitigate the effects of mining on soil. The introduced species have spread to other ecosystems resulting in ecological deteriorations. The problem is compounded by hybridization of the species making identification between the native and exotic species difficult. This study investigated the potential of remote sensing in identifying native, non-native and hybrid Tamarix species recorded in South Africa. Leaf- and canopy-level classifications of the species were conducted using field spectroradiometer data that provided two inputs: original hyperspectral data and bands simulated according to Landsat-8, Sentinel-2, SPOT-6 and WorldView-3. The original hyperspectral data yielded high accuracies for leaf- and plot-level discriminations (>90%), while promising accuracies were also obtained using Landsat-8, Sentinel-2 and Worldview-3 simulations (>75%). These findings encourage for investigating the performance of actual space-borne multispectral data in classifying the species. Numéro de notice : A2022-928 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1080/10106049.2021.1983033 Date de publication en ligne : 27/09/2021 En ligne : https://doi.org/10.1080/10106049.2021.1983033 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102661
in Geocarto international > vol 37 n° 25 [01/12/2022] . - pp 7733 - 7752[article]Establishing a GIS-based evaluation method considering spatial heterogeneity for debris flow susceptibility mapping at the regional scale / Shengwu Qin in Natural Hazards, vol 114 n° 3 (December 2022)
![]()
[article]
Titre : Establishing a GIS-based evaluation method considering spatial heterogeneity for debris flow susceptibility mapping at the regional scale Type de document : Article/Communication Auteurs : Shengwu Qin, Auteur ; Shuangshuang Qiao, Auteur ; Jingyu Yao, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 2709 - 2738 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications SIG
[Termes IGN] aléa
[Termes IGN] analyse de sensibilité
[Termes IGN] cartographie des risques
[Termes IGN] Chine
[Termes IGN] classification par réseau neuronal convolutif
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] éboulement
[Termes IGN] hétérogénéité spatiale
[Termes IGN] prévention des risquesRésumé : (auteur) Susceptibility mapping is an effective means of preventing debris flow disasters. However, previous studies have failed to solve spatial heterogeneity well, especially at the regional scale. The main objective of this study is to solve the spatial heterogeneity of regional-scale debris flow susceptibility (DFS) mapping by establishing a geographic information system (GIS)-based processing framework. The framework was realized by integrating the determination factor (DFactor) model with machine learning models. The DFactor model established different combinations of evaluation factors in each local region and clarified the differing contributions of influencing factors to DFS. To test the feasibility of the framework, the support vector machine (SVM) and two-dimensional convolutional neural network (CNN) were integrated with the DFactor model (DFactor-SVM and DFactor-CNN) to evaluate DFS in Jilin Province, China. The individual models (SVM and CNN) were also used to map the DFS for comparison with the integrated models. For debris flow modeling, 868 debris flow samples were collected and randomly divided into two datasets: 70% of the samples were used for training and the result was used for verification. The results of the receiver operating characteristic curve showed that the integrated models performed better. The DFactor-CNN model had the highest predictive accuracy, followed by the DFactor-SVM, CNN and SVM models. In general, the GIS-based processing framework maximizes the contribution of the influencing factors to debris flows and enhances the prediction ability of models. Furthermore, it provides a reliable means to predict debris flows at the regional scale. Numéro de notice : A2022-854 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE Nature : Article DOI : 10.1007/s11069-022-05487-5 Date de publication en ligne : 06/08/2022 En ligne : https://doi.org/10.1007/s11069-022-05487-5 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102101
in Natural Hazards > vol 114 n° 3 (December 2022) . - pp 2709 - 2738[article]Integration of radar and optical Sentinel images for land use mapping in a complex landscape (case study: Arasbaran Protected Area) / Vahid Nasiri in Arabian Journal of Geosciences, vol 15 n° 24 (December 2022)
![]()
[article]
Titre : Integration of radar and optical Sentinel images for land use mapping in a complex landscape (case study: Arasbaran Protected Area) Type de document : Article/Communication Auteurs : Vahid Nasiri, Auteur ; Arnaud Le Bris , Auteur ; Ali Asghar Darvishsefat, Auteur ; Fardin Moradi, Auteur
Année de publication : 2022 Projets : 1-Pas de projet / Article en page(s) : n° 1759 Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image mixte
[Termes IGN] aire protégée
[Termes IGN] carte d'occupation du sol
[Termes IGN] classification par forêts d'arbres décisionnels
[Termes IGN] classification par maximum de vraisemblance
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] image Sentinel-MSI
[Termes IGN] image Sentinel-SARRésumé : (auteur) Considering the importance of accurate and up-to-date land use/cover (LULC) maps and in a situation of fast LULC changes, an accurate mapping of complex landscapes requires real-time high-resolution remote sensed data and powerful classification algorithms. The new ESA Copernicus satellites Sentinel-1 (S-1) and Sentinel-2 (S-2) have contributed to the effective monitoring of the Earth’s surface. This paper aims at assessing the potential of mono-temporal S-1 and S-2 satellite images and three common classification algorithms including maximum likelihood (ML), support vector machine (SVM), and random forest (RF) for LULC classification. The research methodology consists of a sequence of tasks including data collection and preprocessing, the extraction of texture and spectral features, the definition of several feature set configurations, classification, and accuracy assessment. Based on the results, using S-1 data alone leads to quite poor results, even though dual polarimetric C-band and texture features increased the classification accuracy. The S-2 data outperformed the S-1 data in terms of overall and class level accuracies. A combined use of S-1 and S-2 satellite images involving extracted features from both sources led to the best result for identifying all classes. This emphasizes the critical importance of using multi-modal datasets and different features in the LULC classification. Among classification algorithms, the SVM led to the highest accuracies irrespective of the dataset. To sum it up, according to the applied methodology and results, S-1 and S-2 data can provide optimal and up-to-date information for LULC mapping using non-parametric classifiers as SVM or RF. Numéro de notice : A2022-699 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Thématique : IMAGERIE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1007/s12517-022-11035-z Date de publication en ligne : 07/12/2022 En ligne : https://doi.org/10.1007/s12517-022-11035-z Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102253
in Arabian Journal of Geosciences > vol 15 n° 24 (December 2022) . - n° 1759[article]Urban wetland fragmentation and ecosystem service assessment using integrated machine learning algorithm and spatial landscape analysis / Das Subhasis in Geocarto international, vol 37 n° 25 ([01/12/2022])
![]()
[article]
Titre : Urban wetland fragmentation and ecosystem service assessment using integrated machine learning algorithm and spatial landscape analysis Type de document : Article/Communication Auteurs : Das Subhasis, Auteur ; Partha Pratim Adhikary, Auteur ; Pravat Kumar Shit, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 7800 - 7818 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Cartographie thématique
[Termes IGN] analyse du paysage
[Termes IGN] analyse spatiale
[Termes IGN] apprentissage automatique
[Termes IGN] Calcutta
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] image Landsat-ETM+
[Termes IGN] image Landsat-OLI
[Termes IGN] image Landsat-TM
[Termes IGN] Inde
[Termes IGN] occupation du sol
[Termes IGN] QGIS
[Termes IGN] régression multiple
[Termes IGN] service écosystémique
[Termes IGN] zone humide
[Termes IGN] zone urbaineRésumé : (auteur) Dynamics of ecosystem service value (ESV) of various wetlands has been assessed by researchers globally. But the impact of spatio-temporal variation of landscape metrics on ESV in the lower Gangetic plains has not been examined, fully. The present work has established linkages between landscape metrics and ESV in Kolkata urban agglomeration using support vector machine and multivariate regression analysis. Result indicates that wetland area has been reduced by 5.26%, 13.67% and 9.03% during the periods 1990–2000, 2000–2010 and 2010–2020, respectively and the ESV contributed by wetlands has been decreased by $131428, $323674 and $184649, respectively during the same period at an annual rate of 0.85%. Number of patches, mean patch area and edge density are the main determinants of wetland fragmentation and decreased by 44.12%, 10.23% and 8.65%, respectively during the last three decades. A wetland restoration strategy based on dynamic restoration, reactive restoration and wetland creation for the study area has been formulated, which can guide for sustainable management of wetland resources in Kolkata urban agglomeration. Numéro de notice : A2022-930 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/IMAGERIE Nature : Article DOI : 10.1080/10106049.2021.1985174 Date de publication en ligne : 03/11/2021 En ligne : https://doi.org/10.1080/10106049.2021.1985174 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102665
in Geocarto international > vol 37 n° 25 [01/12/2022] . - pp 7800 - 7818[article]Exploring the influencing factors in identifying soil texture classes using multitemporal Landsat-8 and Sentinel-2 data / Yanan Zhou in Remote sensing, vol 14 n° 21 (November-1 2022)
PermalinkMeasuring visual walkability perception using panoramic street view images, virtual reality, and deep learning / Yunqin Li in Sustainable Cities and Society, vol 86 (November 2022)
PermalinkLand use/land cover mapping from airborne hyperspectral images with machine learning algorithms and contextual information / Ozlem Akar in Geocarto international, vol 37 n° 22 ([10/10/2022])
PermalinkApplication of a graph convolutional network with visual and semantic features to classify urban scenes / Yongyang Xu in International journal of geographical information science IJGIS, vol 36 n° 10 (October 2022)
PermalinkInvestigation of recognition and classification of forest fires based on fusion color and textural features of images / Cong Li in Forests, vol 13 n° 10 (October 2022)
PermalinkModelling and prediction of GNSS time series using GBDT, LSTM and SVM machine learning approaches / Wenzong Gao in Journal of geodesy, vol 96 n° 10 (October 2022)
PermalinkA comparative assessment of modeling groundwater vulnerability using DRASTIC method from GIS and a novel classification method using machine learning classifiers / Qasim Khan in Geocarto international, vol 37 n° 20 ([20/09/2022])
PermalinkForest tree species classification based on Sentinel-2 images and auxiliary data / Haotian You in Forests, vol 13 n° 9 (september 2022)
PermalinkMapping annual urban evolution process (2001–2018) at 250 m: A normalized multi-objective deep learning regression / Haoyu Wang in Remote sensing of environment, vol 278 (September 2022)
PermalinkIncorporation of digital elevation model, normalized difference vegetation index, and Landsat-8 data for land use land cover mapping / Jwan Al-Doski in Photogrammetric Engineering & Remote Sensing, PERS, vol 88 n° 8 (August 2022)
Permalink