Centre de documentation
scientifique

Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points / Y. Shao in ISPRS Journal of photogrammetry and remote sensing, vol 70 (June 2012)  

Public [article]  inISPRS Journal of photogrammetry and remote sensing > vol 70 (June 2012) . - pp 78 - 87 Titre : Comparison of support vector machine, neural network, and CART algorithms for the land-cover classification using limited training data points Type de document : Article/Communication Auteurs : Y. Shao, Auteur ; R. Lunetta, Auteur Année de publication : 2012 Article en page(s) : pp 78 - 87 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse comparative [Termes IGN] analyse diachronique [Termes IGN] classification dirigée [Termes IGN] classification et arbre de régression [Termes IGN] classification par réseau neuronal [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Terra-MODIS [Termes IGN] occupation du sol [Termes IGN] Perceptron multicouche [Termes IGN] série temporelle Résumé : (Auteur) Support vector machine (SVM) was applied for land-cover characterization using MODIS time-series data. Classification performance was examined with respect to training sample size, sample variability, and landscape homogeneity (purity). The results were compared to two conventional nonparametric image classification algorithms: multilayer perceptron neural networks (NN) and classification and regression trees (CART). For 2001 MODIS time-series data, SVM generated overall accuracies ranging from 77% to 80% for training sample sizes from 20 to 800 pixels per class, compared to 67–76% and 62–73% for NN and CART, respectively. These results indicated that SVM’s had superior generalization capability, particularly with respect to small training sample sizes. There was also less variability of SVM performance when classification trials were repeated using different training sets. Additionally, classification accuracies were directly related to sample homogeneity/heterogeneity. The overall accuracies for the SVM algorithm were 91% (Kappa = 0.77) and 64% (Kappa = 0.34) for homogeneous and heterogeneous pixels, respectively. The inclusion of heterogeneous pixels in the training sample did not increase overall accuracies. Also, the SVM performance was examined for the classification of multiple year MODIS time-series data at annual intervals. Finally, using only the SVM output values, a method was developed to directly classify pixel purity. Approximately 65% of pixels within the Albemarle–Pamlico Basin study area were labeled as “functionally homogeneous” with an overall classification accuracy of 91% (Kappa = 0.79). The results indicated a high potential for regional scale operational land-cover characterization applications. Numéro de notice : A2012-290 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2012.04.001 En ligne : https://doi.org/10.1016/j.isprsjprs.2012.04.001 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31736 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
081-2012041	SL	Revue	Centre de documentation	Revues en salle	Disponible

The Sichuan earthquake (2) : space-borne SAR in earthquake response / Y. Shao in GIM international, vol 22 n° 11 (November 2008)

Public [article]  inGIM international > vol 22 n° 11 (November 2008) . - pp 24 - 27 Titre : The Sichuan earthquake (2) : space-borne SAR in earthquake response Type de document : Article/Communication Auteurs : Y. Shao, Auteur Année de publication : 2008 Article en page(s) : pp 24 - 27 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] cartographie d'urgence [Termes IGN] extraction de données [Termes IGN] image radar moirée [Termes IGN] image satellite [Termes IGN] risque naturel [Termes IGN] séisme [Termes IGN] Setchouan (Chine) [Termes IGN] traitement d'image Résumé : (Auteur) In may 2008 an earthquake struck chinese province of Sichuan. Geo information experts were able to support emergency response through the immediate provision and analysis of satellite imagery. Infoterra and IRSACAS used SAR satellite imagery extract accurate information. Both institutions independently chose a very similar approach : visual interpretation of the data and pre-earthquake remote-sensing data for reference. Numéro de notice : A2008-415 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29407 [article]

Voir aussi

• The Sichuan earthquake (3): satellite-based global flood response / F. Koudogbo in GIM international, vol 22 n° 12 (December 2008)
• The Sichuan earthquake (1): satellite imagery for rapid response / Timo Balz in GIM international, vol 22 n° 10 (October 2008)

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
061-08111	RAB	Revue	Centre de documentation	En réserve L003	Disponible

Integration of Hyperion satellite data and a household social survey to caracterize the causes and consequences of reforestation patterns in the Northern Ecuadorian Amazon / S.J. Walsh in Photogrammetric Engineering & Remote Sensing, PERS, vol 74 n° 6 (June 2008)  

Public [article]  inPhotogrammetric Engineering & Remote Sensing, PERS > vol 74 n° 6 (June 2008) . - pp 725 - 735 Titre : Integration of Hyperion satellite data and a household social survey to caracterize the causes and consequences of reforestation patterns in the Northern Ecuadorian Amazon Type de document : Article/Communication Auteurs : S.J. Walsh, Auteur ; Y. Shao, Auteur ; C.F. Mena, Auteur ; A.L. Mccleary, Auteur Année de publication : 2008 Article en page(s) : pp 725 - 735 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] Amazonie [Termes IGN] analyse en composantes principales [Termes IGN] analyse linéaire des mélanges spectraux [Termes IGN] classification dirigée [Termes IGN] classification non dirigée [Termes IGN] Equateur (état) [Termes IGN] forêt équatoriale [Termes IGN] image EO1-Hyperion [Termes IGN] image hyperspectrale [Termes IGN] image Ikonos [Termes IGN] intégration de données [Termes IGN] occupation du sol Résumé : (Auteur) The integration of Hyperion and Ikonos imagery are used to differentiate the subtle spectral differences of landuse/ land-cover types on household farms in the Northern Ecuadorian Amazon (NEA) with an emphasis on secondary and successional forests. Approaches are examined that include the use of Principal Components Analysis to compress the Hyperion hyperspectral data to its most vital spectral channels; linear mixture modeling to derive subpixel fractions of land-use/land-cover types through the generation of spectral endmembers; and supervised and unsupervised classifications to map forest regrowth, agricultural crops and pasture, and other land-uses on 18 survey farms that are spatially coincident with the imagery. A longitudinal socio-economic and demographic survey (1990 and 1999) is used to characterize household farms; a community survey (2000) is used to assess nearby market towns and service centers; GIS is used to represent the resource endowments of farms and their geographic accessibility. Statistical relationships are examined using Spearman rank correlation coefficients to assess the linkages among a number of selected social, geographical, and biophysical variables and secondary and successional forest on household farms. Relationships suggest the importance of household characteristics, farm resources, and geographic access of secondary forests on surveyed household farms that were previously deforested and converted to agriculture through extensification processes. Results support the integrated use of hyperspectral and hyperspatial data for characterizing forest regrowth on household farms, and the use of multi-dimensional social survey data and GIS to assess plausible causes and consequences of land-use/land-cover dynamics in the NEA. Copyright ASPRS Numéro de notice : A2008-199 Affiliation des auteurs : non IGN Thématique : FORET/IMAGERIE Nature : Article DOI : 10.14358/PERS.74.6.725 En ligne : https://doi.org/10.14358/PERS.74.6.725 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=29194 [article]