Paper Info
Title
Supervised classification of remote sensing images with unknown classes
Abstract
This paper addresses the problem of classifying multispectral images when the a priori knowledge about classes is not complete: the true number of classes is not known, or it is not possible to obtain ground truth data for some of the classes in the image. We propose a method to perform image classification taking into account all the classes, "known" and "unknown", based on accurate estimates of the prior probabilities and of the joint probability density functions (pdfs). To this end, we propose the application of the dependence tree approximation to mitigate the problem of few available samples. Finally, we investigate the suitability of the application of a biased cross-validation criterion for the optimization of 2-dimensional pdf estimations.
Year
DOI
Venue
2002
10.1109/IGARSS.2002.1027224
IGARSS
Keywords
Field
DocType
geophysical signal processing,image classification,learning (artificial intelligence),terrain mapping,2-dimensional pdf estimations,biased cross-validation criterion,dependence tree approximation,joint probability density functions,multispectral images,optimization,prior probabilities,remote sensing images,supervised classification,labeling,bandwidth,a priori knowledge,learning artificial intelligence,joint probability density function,2 dimensional,pixel,ground truth,probability density function,kernel,multispectral imaging,remote sensing,cross validation
Computer science,Remote sensing,A priori and a posteriori,Multispectral pattern recognition,Artificial intelligence,Contextual image classification,Geophysical signal processing,Terrain mapping,Computer vision,Joint probability distribution,Pattern recognition,Multispectral image,Ground truth
Conference
Volume
ISBN
Citations 
6
0-7803-7536-X
2
PageRank 
References 
Authors
0.54
5
4
Name
Order
Citations
PageRank
Guerrero-Curieses, A.120.54
Biasiotto, A.220.54
Serpico, S.B.356048.52
Gabriele Moser491976.92