Structured Output SVM for Remote Sensing Image Classification

Details

Ressource 1Download: serval:BIB_20E02910FB08.P001 (998.45 [Ko])
State: Public
Version: author
License: Not specified
It was possible to publish this article open access thanks to a Swiss National Licence with the publisher.
Serval ID
serval:BIB_20E02910FB08
Type
Article: article from journal or magazin.
Collection
Publications
Institution
Title
Structured Output SVM for Remote Sensing Image Classification
Journal
Journal of Signal Processing Systems
Author(s)
Tuia D., Muñoz-Marí J., Kanevski M., Camps-Valls G.
ISSN
1939-8018
ISSN-L
1939-8115
Publication state
Published
Issued date
2010
Peer-reviewed
Oui
Volume
65
Pages
301-310
Language
english
Abstract
Traditional kernel classifiers assume independence among the classification outputs. As a consequence, each misclassification receives the same weight in the loss function. Moreover, the kernel function only takes into account the similarity between input values and ignores possible relationships between the classes to be predicted. These assumptions are not consistent for most of real-life problems. In the particular case of remote sensing data, this is not a good assumption either. Segmentation of images acquired by airborne or satellite sensors is a very active field of research in which one tries to classify a pixel into a predefined set of classes of interest (e.g. water, grass, trees, etc.). In this situation, the classes share strong relationships, e.g. a tree is naturally (and spectrally) more similar to grass than to water. In this paper, we propose a first approach to remote sensing image classification using structured output learning. In our approach, the output space structure is encoded using a hierarchical tree, and these relations are added to the model in both the kernel and the loss function. The methodology gives rise to a set of new tools for structured classification, and generalizes the traditional non-structured classification methods. Comparison to standard SVM is done numerically, statistically and by visual inspection of the obtained classification maps. Good results are obtained in the challenging case of a multispectral image of very high spatial resolution acquired with QuickBird over a urban area.
Keywords
Structured output learning, Support vector machines, Kernel methods, Land use classification
Web of science
Publisher's website
Open Access
Yes
Create date
16/07/2018 15:58
Last modification date
01/10/2019 7:17
Usage data