Paper Info
Title
Weighted Least Squares Pan-Sharpening of Very High Resolution Multispectral Images
Abstract
This paper presents a solution to the problem of enhancing the spatial resolution of multispectral images with high-resolution panchromatic observations. The proposed method exploits a Weighted Least Squares estimator to calculate injection parameters in the fusion model. For each pixel of the image a weight is calculated by a classification map. The classifier used in the experiments is a Support Vector Machine in order to obtain high accuracy on each land-cover type. Results are presented and discussed on very-high resolution images acquired by Quickbird and Ikonos satellite systems. Fusion simulations on spatially degraded data and fusion tests at full scale reveal that an accurate and reliable PAN-sharpening is achieved by the proposed method.
Year
DOI
Venue
2008
10.1109/IGARSS.2008.4780028
Geoscience and Remote Sensing Symposium, 2008. IGARSS 2008. IEEE International
Keywords
Field
DocType
geophysics computing,image enhancement,image fusion,least squares approximations,support vector machines,terrain mapping,Ikonos satellite system,Quickbird satellite system,Support Vector Machine,Weighted Least Squares estimator,classification map,fusion model,fusion simulation,fusion tests,high-resolution panchromatic observations,image acquisition,land-cover type,multiresolution analysis,multispectral image enhancement,spatially degraded data,very high resolution multispectral images,Data Fusion,Pan-sharpening,Support Vector machine,Weighted Least Square Estimator
Least squares,Sharpening,Image fusion,Computer science,Remote sensing,Artificial intelligence,Computer vision,Pattern recognition,Panchromatic film,Multispectral image,Sensor fusion,Pixel,Image resolution
Conference
Volume
ISBN
Citations 
5
978-1-4244-2808-3
2
PageRank 
References 
Authors
0.41
6
3
Name
Order
Citations
PageRank
Filippo Nencini153130.47
Luca Capobianco2906.20
A. Garzelli361.04