Multisource Clustering of Remote Sensing Images With Entropy-Based Dempster-Shafer Fusion
Details
State: Public
Version: author
Serval ID
serval:BIB_97A0622EA0C3
Type
Inproceedings: an article in a conference proceedings.
Publication sub-type
Abstract (Abstract): shot summary in a article that contain essentials elements presented during a scientific conference, lecture or from a poster.
Collection
Publications
Institution
Title
Multisource Clustering of Remote Sensing Images With Entropy-Based Dempster-Shafer Fusion
Title of the conference
EUSIPCO 2013, European Signal Processing Conference
Address
Marrakech, Morocco, September 9-13, 2013
Publication state
Published
Issued date
2013
Language
english
Abstract
In this paper, we propose a strategy for fusing
clustering maps obtained with different remote sensing
sources. Dempster- Shafer (DS) Theory is a powerful
fusion method that allows to combine classifications from
different sources and handles ignorance, imprecision and
conflict between them. To do so, it attributes evidences
(weights) to different hypothesis representing single or
unions of classes. We introduce a fully unsupervised
evidence assignment strategy exploiting the entropy among
cluster memberships. Ambiguous pixels get stronger
evidences for union of classes to better represent the
uncertainty among them. On two multisource experiments,
the proposed Entropy-based Dempster-Shafer (EDS) performs
best along the different fusion methods with VHR images,
when the single class accuracies from each source are
complementary and one of the sources shows low overall
accuracy.
clustering maps obtained with different remote sensing
sources. Dempster- Shafer (DS) Theory is a powerful
fusion method that allows to combine classifications from
different sources and handles ignorance, imprecision and
conflict between them. To do so, it attributes evidences
(weights) to different hypothesis representing single or
unions of classes. We introduce a fully unsupervised
evidence assignment strategy exploiting the entropy among
cluster memberships. Ambiguous pixels get stronger
evidences for union of classes to better represent the
uncertainty among them. On two multisource experiments,
the proposed Entropy-based Dempster-Shafer (EDS) performs
best along the different fusion methods with VHR images,
when the single class accuracies from each source are
complementary and one of the sources shows low overall
accuracy.
Keywords
Dempster-Shafer, Multi-sensor, multisource fusion, unsupervised, entropy, fuzzy c-means, remote sensing, LTS5
Create date
06/01/2014 21:46
Last modification date
20/08/2019 15:59
Usage data
