Centre de documentation
scientifique

Aboveground biomass estimation of an agro-pastoral ecology in semi-arid Bundelkhand region of India from Landsat data: a comparison of support vector machine and traditional regression models / Dibyendu Deb in Geocarto international, vol 37 n° 4 ([15/02/2022])  

Public [article]  inGeocarto international > vol 37 n° 4 [15/02/2022] . - pp 1043 - 1058 Titre : Aboveground biomass estimation of an agro-pastoral ecology in semi-arid Bundelkhand region of India from Landsat data: a comparison of support vector machine and traditional regression models Type de document : Article/Communication Auteurs : Dibyendu Deb, Auteur ; Shovik Deb, Auteur ; Debasis Chakraborty, Auteur ; et al., Auteur Année de publication : 2022 Article en page(s) : pp 1043 - 1058 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] biomasse aérienne [Termes IGN] distribution spatiale [Termes IGN] image Landsat-8 [Termes IGN] Inde [Termes IGN] indice de végétation [Termes IGN] modèle de régression [Termes IGN] point d'appui [Termes IGN] régression linéaire [Termes IGN] régression multiple [Termes IGN] séparateur à vaste marge [Termes IGN] zone semi-aride Résumé : (auteur) This study compared the traditional regression models and support vector machine (SVM) for estimation of aboveground biomass (ABG) of an agro-pastoral ecology using vegetation indices derived from Landsat 8 satellite data as explanatory variables . The area falls in the Shivpuri Tehsil of Madhya Pradesh, India, which is predominantly a semi-arid tract of the Bundelkhand region. The Enhanced Vegetation Index-1 (EVI-1) was identified as the most suitable input variable for the regression models, although the collective effect of a number of the vegetation indices was evident. The EVI-1 was also the most suitable input variable to SVM, due to its capacity to distinctly differentiate diverse vegetation classes. The performance of SVM was better over regression models for estimation of the AGB. Based on the SVM-derived and the ground observations, the AGB of the area was precisely mapped for croplands, grassland and rangelands over the entire region. Numéro de notice : A2022-394 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2020.1756461 Date de publication en ligne : 29/04/2020 En ligne : https://doi.org/10.1080/10106049.2020.1756461 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=100688 [article]

Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery / Ujjwal Maulik in ISPRS Journal of photogrammetry and remote sensing, vol 77 (March 2013)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 77 (March 2013) . - pp 66 - 78 Titre : Learning with transductive SVM for semisupervised pixel classification of remote sensing imagery Type de document : Article/Communication Auteurs : Ujjwal Maulik, Auteur ; Debasis Chakraborty, Auteur Année de publication : 2013 Article en page(s) : pp 66 - 78 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] Bombay [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] classification pixellaire [Termes IGN] classification semi-dirigée [Termes IGN] image infrarouge couleur [Termes IGN] image SPOT [Termes IGN] Inde [Termes IGN] ville Résumé : (Auteur) Land cover classification using remotely sensed data requires robust classification methods for the accurate mapping of complex land cover area of different categories. In this regard, support vector machines (SVMs) have recently received increasing attention. However, small number of training samples remains a bottleneck to design suitable supervised classifiers. On the other hand, adequate number of unlabeled data is available in remote sensing images which can be employed as additional source of information about margins. To fully leverage all of the precious unlabeled data, integration of filtering in a transductive SVM is proposed. Using two labeled image datasets of small size and two large unlabeled image datasets, the effectiveness of the proposed method is explored. Experimental results show that the proposed technique achieves average overall accuracies of around 4.5–7.8%, 0.8–2.6% and 0.9–2.2% more than the standard inductive SVM (ISVM), progressive transductive SVM (PTSVM) and low density separation (LDS) classifiers, respectively on larger domains in case of labeled datasets. Using image datasets, visual interpretation from the classified images as well as the segmentation quality reveal that the proposed method can efficiently filter informative data from the unlabeled samples. Numéro de notice : A2013-116 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2012.12.003 En ligne : https://doi.org/10.1016/j.isprsjprs.2012.12.003 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32254 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2013031	RAB	Revue	Centre de documentation	En réserve L003	Disponible