Centre dedocumentation
scientifique

Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification / Divyesh Varade in Geocarto international, Vol 36 n° 15 ([10/08/2021])  

Public [article]  inGeocarto international > Vol 36 n° 15 [10/08/2021] . - pp 1709 - 1731 Titre : Unsupervised band selection of hyperspectral data based on mutual information derived from weighted cluster entropy for snow classification Type de document : Article/Communication Auteurs : Divyesh Varade, Auteur ; Ajay K. Maurya, Auteur ; Onkar Dikshit, Auteur Année de publication : 2021 Article en page(s) : pp 1709 - 1731 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] bande spectrale [Termes IGN] classification floue [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par nuées dynamiques [Termes IGN] distribution spatiale [Termes IGN] entropie [Termes IGN] image EO1-Hyperion [Termes IGN] image hyperspectrale [Termes IGN] Inde [Termes IGN] manteau neigeux [Termes IGN] neige [Termes IGN] réflectance spectrale Résumé : (auteur) Information on the spatial and temporal extent of snow cover distribution is a significant input in hydrological processes and climate models. Although hyperspectral remote sensing provides significant opportunities in the assessment of land cover, the applications of such data are limited in the snow-covered alpine regions. A major issue with hyperspectral data is the larger dimensionality. Feature selection methods are often used to derive the most informative subset of bands from the hyperspectral data. In this study, a band selection technique is proposed which utilizes the mutual information (MI) between hyperspectral bands and a reference band. The first principal component of the hyperspectral data is selected as the reference band. Two variants of this approach are proposed involving preclustering of bands using: (1) the k-means and (2) the fuzzy k-means algorithms. The MI is derived from weighted entropy of the hyperspectral band and the reference band. The weights are computed from the cluster distance ratio and the cluster membership function for the k-means and fuzzy k-means algorithm, respectively. The selected bands were classified using random forest classifier. The proposed methods are evaluated with four datasets, two Hyperion datasets corresponding to the geographical locations of Dhundi and Solang in India, corresponding to snow covered terrain and two benchmark AVIRIS datasets of Indian Pines and Salinas. The average classification accuracy (0.995 and 0.721 for Dhundi and Solang datasets, respectively) for the proposed approach were observed to be better as compared with those from other state of the art techniques. Numéro de notice : A2021-568 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2019.1665717 Date de publication en ligne : 18/09/2019 En ligne : https://doi.org/10.1080/10106049.2019.1665717 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98183 [article]

Assessment of winter season land surface temperature in the Himalayan regions around the Kullu area in India using Landsat-8 data / Divyesh Varade in Geocarto international, vol 35 n° 6 ([01/05/2020])  

Public [article]  inGeocarto international > vol 35 n° 6 [01/05/2020] . - pp 641 - 662 Titre : Assessment of winter season land surface temperature in the Himalayan regions around the Kullu area in India using Landsat-8 data Type de document : Article/Communication Auteurs : Divyesh Varade, Auteur ; Onkar Dikshit, Auteur Année de publication : 2020 Article en page(s) : pp 641 - 662 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] emissivité [Termes IGN] Himalaya [Termes IGN] hiver [Termes IGN] image Landsat-8 [Termes IGN] image multibande [Termes IGN] image Sentinel-3 [Termes IGN] Inde [Termes IGN] manteau neigeux [Termes IGN] Normalized Difference Vegetation Index [Termes IGN] précision de détermination de surface [Termes IGN] seuillage [Termes IGN] température au sol Résumé : (auteur) In this study, we propose a modified thresholds method for the determination of land surface emissivity (LSE) for snow covered mountainous areas. The conventional Normalized Differenced Vegetation Index (NDVI) thresholds method (NDVITHM) does not discriminate the snow covered pixels with soil pixels in assigning the LSE based on NDVI thresholds. In the proposed approach, we incorporate different thresholding rules based on the Normalized Differenced Snow Index and the S3 index for incorporating separability in the LSE for the snow covered pixels. The LSE thus derived is used to determine the land surface temperature using the Single Channel Method. The approach was evaluated for a study area around the Kullu Valley in the lower Indian Himalayas for a dataset of the winter season of Landsat-8 multispectral data. The observed coefficient of determination values indicated that the proposed method yielded better results with respect to the conventional NDVITHM approach. Numéro de notice : A2020-203 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1520928 Date de publication en ligne : 26/12/2018 En ligne : https://doi.org/10.1080/10106049.2018.1520928 Format de la ressource électronique : url article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94878 [article]

Potential of Landsat-8 and Sentinel-2A composite for land use land cover analysis / Divyesh Varade in Geocarto international, vol 34 n° 14 ([30/10/2019])  

Public [article]  inGeocarto international > vol 34 n° 14 [30/10/2019] . - pp 1552 - 1567 Titre : Potential of Landsat-8 and Sentinel-2A composite for land use land cover analysis Type de document : Article/Communication Auteurs : Divyesh Varade, Auteur ; Anudeep Sure, Auteur ; Onkar Dikshit, Auteur Année de publication : 2019 Article en page(s) : pp 1552 - 1567 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse linéaire des mélanges spectraux [Termes IGN] classification dirigée [Termes IGN] image EO1-Hyperion [Termes IGN] image hyperspectrale [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel-MSI [Termes IGN] Inde [Termes IGN] occupation du sol [Termes IGN] réflectance spectrale [Termes IGN] utilisation du sol Résumé : (auteur) This study proposes the development of a multi-sensor, multi-spectral composite from Landsat-8 and Sentinel-2A imagery referred to as ‘LSC’ for land use land cover (LULC) characterisation and compared with respect to the hyperspectral imagery of the EO1: Hyperion sensor. A three-stage evaluation was implemented based on the similarity observed in the spectral response, supervised classification results and endmember abundance information obtained using linear spectral unmixing. The study was conducted for two areas located around Dhundi and Rohtak in Himachal Pradesh and Haryana, respectively. According to the analysis of the spectral reflectance curves, the spectral response of the LSC is capable of identifying major LULC classes. The kappa accuracy of 0.85 and 0.66 was observed for the classification results from LSC and Hyperion data for Dhundi and Rohtak datasets, respectively. The coefficient of determination was found to be above 0.9 for the LULC classes in both the datasets as compared to Hyperion, indicating a good agreement. Thus, these three-stage results indicated the significant potential of a composite derived from freely available multi-sensor multi-spectral imagery as an alternative to hyperspectral imagery for LULC studies. Numéro de notice : A2019-527 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2018.1497096 Date de publication en ligne : 07/09/2018 En ligne : https://doi.org/10.1080/10106049.2018.1497096 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94101 [article]

Evaluation of global geopotential models: a case study for India / Ropesh Goyal in Survey review, vol 51 n° 368 (September 2019)  

Public [article]  inSurvey review > vol 51 n° 368 (September 2019) . - pp 402 - 412 Titre : Evaluation of global geopotential models: a case study for India Type de document : Article/Communication Auteurs : Ropesh Goyal, Auteur ; Onkar Dikshit, Auteur ; Nagarajan Balasubramania, Auteur Année de publication : 2019 Article en page(s) : pp 402 - 412 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géodésie physique [Termes IGN] analyse multicritère [Termes IGN] Inde [Termes IGN] Matlab [Termes IGN] modèle de géopotentiel [Termes IGN] modèle de géopotentiel local [Termes IGN] réseau altimétrique national Résumé : (Auteur) This paper aims to identify most suitable global geopotential model (GGM) for India, by comparing 15 GGMs developed through 1996 to 2017. The GGM derived geoid undulation values are compared with the geometrical undulation values obtained from GNSS/levelling data on Indian vertical datum. A correction term is added to the computed GGM derived geoid undulation value after fitting three-, four-, five- and seven-parameter models to account for bias and tilt between local geometric Indian vertical datum and global gravimetric vertical datum. The results indicate that EGM2008 model is the best GGM available for India with root-mean-square error (RMSE) of 0.28 m, without model fitting. However, after considering the systematic errors in the two datums with seven-parameter model, GECO GGM has shown significantly better results with RMSE of 0.19 m for India. Numéro de notice : A2019-366 Affiliation des auteurs : non IGN Thématique : POSITIONNEMENT Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/00396265.2018.1468537 Date de publication en ligne : 11/05/2018 En ligne : https://doi.org/10.1080/00396265.2018.1468537 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=93472 [article]

Identifying geospatial services across heterogeneous taxonomies / Anand Mehta in Geocarto international, Vol 31 n° 9 - 10 (October - November 2016)  

Public [article]  inGeocarto international > Vol 31 n° 9 - 10 (October - November 2016) . - pp 1058 - 1077 Titre : Identifying geospatial services across heterogeneous taxonomies Type de document : Article/Communication Auteurs : Anand Mehta, Auteur ; Akash Ashapure, Auteur ; Onkar Dikshit, Auteur Année de publication : 2016 Article en page(s) : pp 1058 - 1077 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Géomatique web [Termes IGN] données localisées [Termes IGN] identification automatique [Termes IGN] informatique [Termes IGN] service fondé sur la position [Termes IGN] taxinomie Résumé : (auteur) Geospatial services with different functions are assembled together to solve complex problems. Different taxonomies are developed to categorize these services into classes. As differences in granularity and semantics exist among these taxonomies, the identification of services across different taxonomies has become a challenge. In this paper, an approach to identify geospatial services across heterogeneous taxonomies is proposed. Using formal concept analysis, existing heterogeneous taxonomies are decomposed into semantic factors and their various combinations. With these semantic factors, a super taxonomy is established to integrate the original heterogeneous taxonomies. Finally, with the super taxonomy as a cross-referencing system, geospatial services with classes in original taxonomies are identifiable across taxonomies. Experiments in service registries and a social media-based spatial-temporal analysis project are presented to illustrate the effectiveness of this approach. Numéro de notice : A2016-674 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1080/10106049.2015.1110208 Date de publication en ligne : 02/12/2015 En ligne : http://dx.doi.org/10.1080/10106049.2015.1110208 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81924 [article]

Réservation

Réserver ce document

Exemplaires (1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
059-2016051	SL	Revue	Centre de documentation	Revues en salle	Disponible

Comparative study on projected clustering methods for hyperspectral imagery classification / Anand Mehta in Geocarto international, vol 31 n° 3 - 4 (March - April 2016)  

Permalink