Share Email Print

Proceedings Paper

Comparison of MIVIS and IKONOS data for high-resolution land-cover classification in a rural/mountainous area
Author(s): Tiziana Simoniello; Stefano Pignatti; Maria Lanfredi; Maria Macchiato
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Land cover classification is one of the main applications of remotely sensed data and the capability of airborne hyperspectral data for such a purpose is known. The recent availability of high spatial resolution multispectral data, such as IKONOS and QuickBird, puts the question about advantages and disadvantages of these data in comparison with the hyperspectral ones. We evaluated the cost and accuracy of using IKONOS imagery to perform a land cover classification at high spatial resolution and compared them with results obtained from MIVIS airborne hyper-spectral scanner data (102 bands from VIS to TIR). The study was performed in a rural area (25 km2) of Basilicata region (Southern Italy) characterized by complex topography (altitude ranges from 600 to 1400m) and different land cover patterns (forests, lakes, cultivated areas, and small urban areas). Evaluations were made taking into account time-processing, feature extraction, accuracy for different classification levels, and costs as a function of the extension of the area to be classified. Quite high accuracies were obtained for the first classification level, whereas increasing the class number IKONOS was less accurate than MIVIS. Multispectral classification well identified the different forest species, but had some problems in distinguishing between gravel road and some plowed lands. The obtained results showed that IKONOS data are cost-effective for updating thematic maps to support planning and decision-making processes at local government scale.

Paper Details

Date Published: 13 February 2004
PDF: 8 pages
Proc. SPIE 5239, Remote Sensing for Environmental Monitoring, GIS Applications, and Geology III, (13 February 2004); doi: 10.1117/12.511359
Show Author Affiliations
Tiziana Simoniello, Istituto di Metodologie per l'Analisi Ambientale, CNR (Italy)
Stefano Pignatti, Istituto di Metodologie per l'Analisi Ambientale, CNR (Italy)
Maria Lanfredi, Istituto di Metodologie per l'Analisi Ambientale, CNR (Italy)
INFM (Italy)
Maria Macchiato, INFM (Italy)
Univ. degli Studi di Napoli Federico II (Italy)

Published in SPIE Proceedings Vol. 5239:
Remote Sensing for Environmental Monitoring, GIS Applications, and Geology III
Manfred Ehlers; Hermann J. Kaufmann; Ulrich Michel, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?