Sustainable management of natural resources requires constant and detailed monitoring of various aspects of the environment. Land use/cover mapping is considered a key element for planning protection, management and monitoring of semi-natural areas in urban ecosystems. Hence the importance of the information acquired through Remote Sensing, airplane and satellite, has been recognized for decades. The Remote Sensing data offers notable advantages for territorial monitoring, particularly of the vegetated areas, in comparison with data collected on the ground. The study of the spectral response of vegetation gained from airplanes or satellites makes it possible to obtain useful information about plant species and their conditions (density, vegetative state, etc.) in repetitive synoptic images. The research was carried out over an area of study in southern Italy (Basilicata, Metaponto area) near the mouth of the Basento River. For this area, synchronous and geometrically corecorded aerial photographs and Landsat TM image covering the period May 2004, were developed. Firstly a preliminary analysis was carried out using unsupervised means of classification with the aim of grouping together clusters of multi-band spectral responses that are statistically distinctive. Following this and after having properly defined the levels of segmentation of Landsat images using aerial photographs as a reference, a supervised classification procedure was applied, first pixel-oriented and then object-oriented, obtaining a marked improvement both in accuracy and in the reduction of the “salt&papper” effect of the map obtained by the Maximum Likelihood classifier.

Object-Oriented Techniques for Land Use/Cover Classification:Application of Metaponto Area (Basilicata, Southern Italy)

SOLE, Aurelia;TELESCA, Vito
2012

Abstract

Sustainable management of natural resources requires constant and detailed monitoring of various aspects of the environment. Land use/cover mapping is considered a key element for planning protection, management and monitoring of semi-natural areas in urban ecosystems. Hence the importance of the information acquired through Remote Sensing, airplane and satellite, has been recognized for decades. The Remote Sensing data offers notable advantages for territorial monitoring, particularly of the vegetated areas, in comparison with data collected on the ground. The study of the spectral response of vegetation gained from airplanes or satellites makes it possible to obtain useful information about plant species and their conditions (density, vegetative state, etc.) in repetitive synoptic images. The research was carried out over an area of study in southern Italy (Basilicata, Metaponto area) near the mouth of the Basento River. For this area, synchronous and geometrically corecorded aerial photographs and Landsat TM image covering the period May 2004, were developed. Firstly a preliminary analysis was carried out using unsupervised means of classification with the aim of grouping together clusters of multi-band spectral responses that are statistically distinctive. Following this and after having properly defined the levels of segmentation of Landsat images using aerial photographs as a reference, a supervised classification procedure was applied, first pixel-oriented and then object-oriented, obtaining a marked improvement both in accuracy and in the reduction of the “salt&papper” effect of the map obtained by the Maximum Likelihood classifier.
File in questo prodotto:
File Dimensione Formato  
ARTICOLO_OB_format_2.pdf

accesso aperto

Tipologia: Documento in Pre-print
Licenza: DRM non definito
Dimensione 700.32 kB
Formato Adobe PDF
700.32 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11563/36733
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact