|
Multiple Classifiers for Multisource Remote Sensing Data
======================================================
CISP Seminar
Tuesday Sep. 2, 10:00-11:00, Room 053, IMM-B321, DTU
======================================================
Multiple Classifiers for Multisource Remote Sensing Data
Prof. Jon Atli Benediktsson
Department of Electrical and Computer Engineering
University of Iceland -- benedikt (a) hi. is
Abstract
The combined use of multisource remote sensing and geographic data is
believed to offer improved accuracies in land cover classification. For
such classification, the conventional parametric statistical classifiers,
which have been applied successfully in remote sensing for more than the
last two decades, are not appropriate, since a convenient multivariate
statistical model does in general not exist for such data. In the talk,
several single and multiple classifiers, which are appropriate for the
classification of multisource remote sensing and geographic data, are
considered. The focus is on multiple classifiers: bagging algorithms,
boosting algorithms and consensus theoretic classifiers. These multiple
classifiers have different characteristics. The performance of the
algorithms in terms of accuracies is compared for two multisource remote
sensing and geographic data sets. In the experiments, the multiple
classifiers are shown to outperform the single classifiers in terms of
overall accuracies.
Host: Lars Kai Hansen, IMM
Slides
- Jon Atli Benediktsson, Johannes R. Sveinsson and Gunnar J. Briem.
Multiple Classifiers for Multisource Remote Sensing Data.
[ PDF ]
|