Abstract

Reliable land cover mapping of agricultural areas require high resolution remotesensing and robust classification techniques. In this paper, we propose the integration of spectralinformation with spatial information using the traditional statistical supervised classifier “MaximumLikelihood” and a geostatistical tool, “Indicator Kriging” algorithm, for the developmentof land cover maps by supervised classification from remotely sensed data at medium and highspatial resolution. The proposed method showed better results in classes’ discrimination withsmoother resulting maps than the ones produced using only spectral information. Two differentsatellites imagery were analyzed: a Landsat TM5 image at medium spatial resolution acquiredduring 2006 and an Ikonos II image at higher spatial resolution acquired during 2008. The betterperformance of the “combined” approach compared to the traditional Maximum Likelihoodtechnique was confirmed by confusion matrix. The overall accuracy increases from 76.16%to 85.96% for LandsatTM image and from 71.56% to 80.25% for the IKONOS image.

Autore Pugliese

• Pasquariello Guido

Tutti gli autori

• C. Fiorentino;C. Tarantino; G. Pasquariello; B. Basso

Titolo volume/Rivista

Journal of applied remote sensing

Anno di pubblicazione

2011

ISSN

1931-3195

ISBN

Non Disponibile

Numero di citazioni Wos

Nessuna citazione

Ultimo Aggiornamento Citazioni

Non Disponibile

Numero di citazioni Scopus

Non Disponibile

Ultimo Aggiornamento Citazioni

Non Disponibile

Settori ERC

Non Disponibile

Codici ASJC

Non Disponibile