Spatial location and ecological content of support vectors in an SVM classification of tropical vegetation

The Support Vector Machines (SVM) are increasingly far-reaching in remotely sensed data classification. As supervised classifiers, the SVM output depends on the input pixels, pointing out that training is potentially an important stage for optimizing classification accuracy. The SVM consist in proje...

Full description

Saved in:
Bibliographic Details
Published in:Remote Sensing Letters Vol. 4; no. 7; pp. 686 - 695
Main Authors: Pouteau, Robin, Collin, Antoine
Format: Journal Article
Language:English
Published: Abingdon Taylor & Francis 01.07.2013
Informa UK Limited
Taylor & Francis Ltd
Taylor and Francis
Subjects:
[INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM]
[INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation
[INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE]
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
[INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing
[SDE.BE]Environmental Sciences/Biodiversity and Ecology
[SDE.ES]Environmental Sciences/Environment and Society
[SDE.IE]Environmental Sciences/Environmental Engineering
[SDE.MCG]Environmental Sciences/Global Changes
[SDV.EE.ECO]Life Sciences [q-bio]/Ecology, environment/Ecosystems
[SHS.GEO]Humanities and Social Sciences/Geography
[SPI.ACOU]Engineering Sciences [physics]/Acoustics [physics.class-ph]
[SPI.ELEC]Engineering Sciences [physics]/Electromagnetism
[SPI.OPTI]Engineering Sciences [physics]/Optics / Photonic
[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processing
[STAT.ME]Statistics [stat]/Methodology [stat.ME]
[STAT.ML]Statistics [stat]/Machine Learning [stat.ML]
Acoustics
Animal and plant ecology
Animal, plant and microbial ecology
Applied geophysics
Biodiversity and Ecology
Bioinformatics
Biological and medical sciences
Classification
Computer Science
Earth sciences
Earth, ocean, space
ecology
Ecology, environment
Ecosystems
ecotones
Electromagnetism
Engineering Sciences
Environment and Society
Environmental Engineering
Environmental Sciences
Exact sciences and technology
Fundamental and applied biological sciences. Psychology
Geography
Global Changes
Humanities and Social Sciences
Hyperplanes
Image Processing
Internal geophysics
Life Sciences
Machine Learning
Mathematical analysis
Methodology
Modeling and Simulation
Neural and Evolutionary Computing
Optics
Photonic
Pixels
Polynesia
Remote sensing
Signal and Image Processing
Statistics
Support vector machines
surveys
SVM
Synecology
Terrestrial ecosystems
Vectors (mathematics)
Vegetation
vegetation types
iterative methods
accuracy
remote sensing
vegetation
classification
Pixel
ecology
Polynesia
SVM
ISSN:2150-7058, 2150-704X, 2150-7058
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The Support Vector Machines (SVM) are increasingly far-reaching in remotely sensed data classification. As supervised classifiers, the SVM output depends on the input pixels, pointing out that training is potentially an important stage for optimizing classification accuracy. The SVM consist in projecting pixels into a high-dimensional feature space and then fitting in a hyperplane, maximizing the distance between the closest vectors and the hyperplane itself. This study aims to locate the pixels acting as support vectors and identify the ecological features they contain in a tropical vegetation context. The analyses focused on a Quickbird-2 image where two vegetation types occur. The physical boundary between classes was delineated in the field, and we used an iterative method to mark and localize the pixels acting as support vectors on the image. Our results highlight that vegetation sampling should focus on ecotones (the transition area between two different and adjacent vegetation classes) in order to minimize the field survey effort and maximize the mapping accuracy.
Bibliography:http://dx.doi.org/10.1080/2150704X.2013.784848
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:2150-7058
2150-704X
2150-7058
DOI:10.1080/2150704x.2013.784848