DocumentCode :
1186714
Title :
Toward the Automatic Updating of Land-Cover Maps by a Domain-Adaptation SVM Classifier and a Circular Validation Strategy
Author :
Bruzzone, Lorenzo ; Marconcini, Mattia
Author_Institution :
Dept. of Inf. Eng. & Comput. Sci., Univ. of Trento, Trento
Volume :
47
Issue :
4
fYear :
2009
fDate :
4/1/2009 12:00:00 AM
Firstpage :
1108
Lastpage :
1122
Abstract :
In this paper, we address automatic updating of land-cover maps by using remote-sensing images periodically acquired over the same investigated area under the hypothesis that a reliable ground truth is not available for all the considered acquisitions. The problem is modeled in the domain-adaptation framework by introducing a novel method designed for land-cover map updating, which is based on a domain-adaptation support vector machine technique. In addition, a novel circular accuracy assessment strategy is proposed for the validation of the results obtained by domain-adaptation classifiers when no ground-truth labels for the considered image are available. Experimental results obtained on a multitemporal and multispectral data set confirmed the effectiveness and the reliability of the proposed system.
Keywords :
geophysical signal processing; support vector machines; vegetation mapping; automatic updating; circular validation strategy; domain adaptation SVM classifier; domain adaptation classifiers; domain adaptation support vector machine; land cover maps; remote sensing images; Domain adaptation; kernel methods; partially unsupervised classification; semisupervised classification; support vector machines (SVMs); transfer learning; updating land-cover maps; validation strategy;
fLanguage :
English
Journal_Title :
Geoscience and Remote Sensing, IEEE Transactions on
Publisher :
ieee
ISSN :
0196-2892
Type :
jour
DOI :
10.1109/TGRS.2008.2007741
Filename :
4798216
Link To Document :
بازگشت