Fiche du document
5 juillet 2016
- handle: 10670/1.r2vaki
- hal: hal-01352525
Sujets proches
Natural science Sciences Science of science Tropes Speech, Figures of English language--Figures of speech Imagery Knowledge, Classification of Orchestras and bandsCiter ce document
Sébastien Gadal et al., « Urban objects recognition feasibilities by airborne hyperspectral and multispectral remote sensing », HAL-SHS : géographie, ID : 10670/1.r2vaki
Métriques
Partage / Export
Résumé
This paper explores the recognition uncertainty of urban objects by multiband imagery. Thepurpose is to recognize the urban objects by their spectral signature, using an external spectrallibrary. Two Vis-NIR images were used for the study: a four bands Kompsat-2 multispectralimage and a 16 bands Ricola‘s airborne hyperspectral image, two supervised classifiers weretested; a spectral based classifier, called the Spectral Angle Mapper (SAM), coupled to an externalspectral library and a machine learning based classifier called the Support Vector Machine(SVM), in a second step the classification results obtained by the two classifiers were merged, thegoal was to take advantage of both techniques, to optimize the classification result. The classifiersperformance and the objects recognition feasibility were discussed for both images.