High-resolution SAR and high-resolution optical data integration for sub-urban land-cover classification
Rusmini, Marco ; Candiani, Gabriele ; Frassy, Federico ; ...Dini, Luigi ; et al.
Jul - 2012
DOI: 10.1109/IGARSS.2012.6352492
ISSN : 2153-6996 ;
ISBN : 978-1-4673-1159-5
Event Title :
Published in:
Publisher:
type: Conference Proceedings
Abstract
This study shows a comparison between pixel-based and object-based approaches in data fusion of high-resolution multispectral GeoEye-1 imagery and high-resolution COSMO-SkyMed SAR data for land-cover/land-use classification. The per-pixel method consisted of a maximum likelihood classification of fused data based on discrete wavelet transform and a classification from optical images alone. Optical and SAR data were then integrated into an object-oriented environment with the addition of texture measurements from SAR and classified with a nearest neighbor approach. Results were compared with the classification of the GeoEye-1 data alone and the outcomes pointed out that per-pixel data fusion did not improve the classification accuracy, while the object-based data integration increased the overall accuracy from 73\% to 89\%. According to results, an object-based approach with the introduction of adjunctive information layers proved to be more performing than standard pixel-based methods in landcover/ land-use classification.
keywords : Adaptive optics,COSMO-SkyMed,Data integration,GeoEye-1,Integrated optics,Land-cover/land-use,OBIA,Optical imaging,Optical sensors,Remote sensing,SAR data,Synthetic aperture radar,data fusion,discrete wavelet transform,fused data,geophysical image processing,geophysical techniques,high-resolution COSMO-SkyMed SAR data,high-resolution SAR data,high-resolution multispectral GeoEye-1 imagery,high-resolution optical data,image fusion,land-use classification,maximum likelihood classification,object-based approach,object-oriented environment,optical data,optical images,per-pixel method,pixel-based approach,standard pixel-based methods,sub-urban land-cover classification,vegetation mapping