National Research Council of Italy

Institute of Biosciences and BioResources

DISBA logo CNR logo
IBBR publication #1738

Multi-modal knowledge base generation from very high resolution satellite imagery for habitat mapping

Manakos I, Technitou E, Petrou Z, Karydas C, Tomaselli V, Veronico G, Mountrakis G

European Journal of Remote Sensing 49: 1033-1060. (2016)
doi: 10.5721/EuJRS20164953

Monitoring of ecosystems entails the evaluation of contributing factors by the expert ecologist. The aim of this study is to examine to what extent the quantitative variables, calculated solely by the spectral and textural information of the space-borne image, may reproduce verified habitat maps. 555 spectral and texture attributes are extracted and calculated from the image. Results reached an overall accuracy of 65% per object, 76% per pixel, and 77% in reproducing the original objects with segmentation. Taking into consideration the large number of different habitats queried and the lack of any ancillary information the results suggest the discriminatory power of the finally selected attributes. Potential and limitations are discussed.

Actions
Select by Year
Select by Type
Select by Author
*
*
*
*
Istituto di Bioscienze e Biorisorse (IBBR/CNR)
Via G. Amendola 165/A, I-70126 Bari (Italy)
Copyright © 2012-2024. All Rights Reserved.