Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Comparison of algorithms for classifying Swedish landcover using Landsat TM and ERS-1 SAR data

Michelson, Daniel B. ; Liljeberg, B. Marcus and Pilesjö, Petter LU (2000) In Remote Sensing of Environment 71(1). p.1-15
Abstract

Sixteen landcover classes in a representative Swedish environment were analyzed and classified using one Landsat TM scene and seven ERS-1 SAR.PRI images acquired during 1993. Spectral and backscattering signature separabilities are analyzed using the Jeffries-Matusita distance measure to determine which combinations of channels/images contained the most information. Maximum likelihood, sequential maximum a posteriori (SMAP, a Bayesian image segmentation algorithm), and back propagation neural network classification algorithms were applied and their performances evaluated. Results of the separability analyses indicated that the multitemporal SAR data contained more separable landcover information than did the multispectral TM data; the... (More)

Sixteen landcover classes in a representative Swedish environment were analyzed and classified using one Landsat TM scene and seven ERS-1 SAR.PRI images acquired during 1993. Spectral and backscattering signature separabilities are analyzed using the Jeffries-Matusita distance measure to determine which combinations of channels/images contained the most information. Maximum likelihood, sequential maximum a posteriori (SMAP, a Bayesian image segmentation algorithm), and back propagation neural network classification algorithms were applied and their performances evaluated. Results of the separability analyses indicated that the multitemporal SAR data contained more separable landcover information than did the multispectral TM data; the highest separabilities were achieved when the TM and SAR data were combined. Classification accuracy evaluation results indicate that the SMAP algorithm outperformed the maximum likelihood algorithm which, in turn, outperformed the neural network algorithm. The best KAPPA values, using combined data, were 0.495 for SMAP, 0.445 for maximum likelihood, and 0.432 for neural network. Corresponding overall accuracy values were 57.1%, 52.4%, and 51.2%, respectively. A comparison between lumped crop area statistics with areal sums calculated from the classified satellite data gave the highest correspondence where the SMAP algorithm was used, followed by the maximum likelihood and neural network algorithms. Based on our application, we can therefore confirm the value of a multisource optical/SAR approach for analyzing landcover and the improvements to classification achieved using the SMAP algorithm.

(Less)
Please use this url to cite or link to this publication:
author
; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Remote Sensing of Environment
volume
71
issue
1
pages
15 pages
publisher
Elsevier
external identifiers
  • scopus:0033987880
ISSN
0034-4257
DOI
10.1016/S0034-4257(99)00024-3
language
English
LU publication?
yes
additional info
Funding Information: The Swedish National Space Board is gratefully acknowledged for financing this study. Support from the Swedish Water Management Research Program (VASTRA), which is financed by the Swedish Foundation for Strategic Research (MISTRA), is also gratefully acknowledged.
id
5ad5155b-63c4-45b1-bf4b-bb3c2ffae0fd
date added to LUP
2022-03-25 13:06:34
date last changed
2022-04-10 07:00:24
@article{5ad5155b-63c4-45b1-bf4b-bb3c2ffae0fd,
  abstract     = {{<p>Sixteen landcover classes in a representative Swedish environment were analyzed and classified using one Landsat TM scene and seven ERS-1 SAR.PRI images acquired during 1993. Spectral and backscattering signature separabilities are analyzed using the Jeffries-Matusita distance measure to determine which combinations of channels/images contained the most information. Maximum likelihood, sequential maximum a posteriori (SMAP, a Bayesian image segmentation algorithm), and back propagation neural network classification algorithms were applied and their performances evaluated. Results of the separability analyses indicated that the multitemporal SAR data contained more separable landcover information than did the multispectral TM data; the highest separabilities were achieved when the TM and SAR data were combined. Classification accuracy evaluation results indicate that the SMAP algorithm outperformed the maximum likelihood algorithm which, in turn, outperformed the neural network algorithm. The best KAPPA values, using combined data, were 0.495 for SMAP, 0.445 for maximum likelihood, and 0.432 for neural network. Corresponding overall accuracy values were 57.1%, 52.4%, and 51.2%, respectively. A comparison between lumped crop area statistics with areal sums calculated from the classified satellite data gave the highest correspondence where the SMAP algorithm was used, followed by the maximum likelihood and neural network algorithms. Based on our application, we can therefore confirm the value of a multisource optical/SAR approach for analyzing landcover and the improvements to classification achieved using the SMAP algorithm.</p>}},
  author       = {{Michelson, Daniel B. and Liljeberg, B. Marcus and Pilesjö, Petter}},
  issn         = {{0034-4257}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{1--15}},
  publisher    = {{Elsevier}},
  series       = {{Remote Sensing of Environment}},
  title        = {{Comparison of algorithms for classifying Swedish landcover using Landsat TM and ERS-1 SAR data}},
  url          = {{http://dx.doi.org/10.1016/S0034-4257(99)00024-3}},
  doi          = {{10.1016/S0034-4257(99)00024-3}},
  volume       = {{71}},
  year         = {{2000}},
}