Canonical analysis of sentinel-1 radar and sentinel-2 optical data

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

197 Downloads (Pure)

Abstract

This paper gives results from joint analyses of dual polarimety synthetic aperture radar data from the Sentinel-1 mission and optical data from the Sentinel-2 mission. The analyses are carried out by means of traditional canonical correlation analysis (CCA) and canonical information analysis (CIA). Where CCA is based on maximising correlation between linear combinations of the two data sets, CIA maximises mutual information between the two. CIA is a conceptually more pleasing method for the analysis of data with very different modalities such as radar and optical data. Although a little inconclusive as far as the change detection aspect is concerned, results show that CIA analysis gives conspicuously less noisy appearing images of canonical variates (CVs) than CCA. Also, the 2D histogram of the mutual information based leading CVs clearly reveals much more structure than the correlation based one. This gives promise for potentially better change detection results with CIA than can be obtained by means of CCA.
Original languageEnglish
Title of host publicationImage Analysis
Volume10270
PublisherIEEE
Publication date2017
Pages147-158
ISBN (Print)9783319591285
DOIs
Publication statusPublished - 2017
Event20th Scandinavian Conference on Image Analysis - Tromsø, Norway
Duration: 12 Jun 201714 Jun 2017

Conference

Conference20th Scandinavian Conference on Image Analysis
CountryNorway
CityTromsø
Period12/06/201714/06/2017
SeriesLecture Notes in Computer Science
Volume10270
ISSN0302-9743

Keywords

  • Theoretical Computer Science
  • Computer Science (all)
  • Canonical correlation analysis
  • Canonical information analysis
  • Correlation methods
  • Information analysis
  • Radar
  • Synthetic aperture radar
  • 2-D histograms
  • Analysis of data
  • Canonical analysis
  • Change detection
  • Joint analysis
  • Linear combinations
  • Mutual informations
  • Image analysis

Cite this

Nielsen, A. A., & Larsen, R. (2017). Canonical analysis of sentinel-1 radar and sentinel-2 optical data. In Image Analysis (Vol. 10270, pp. 147-158). IEEE. Lecture Notes in Computer Science, Vol.. 10270 https://doi.org/10.1007/978-3-319-59129-2_13
Nielsen, Allan Aasbjerg ; Larsen, Rasmus. / Canonical analysis of sentinel-1 radar and sentinel-2 optical data. Image Analysis. Vol. 10270 IEEE, 2017. pp. 147-158 (Lecture Notes in Computer Science, Vol. 10270).
@inproceedings{2d6243b924e340ab9302deb06dd4240d,
title = "Canonical analysis of sentinel-1 radar and sentinel-2 optical data",
abstract = "This paper gives results from joint analyses of dual polarimety synthetic aperture radar data from the Sentinel-1 mission and optical data from the Sentinel-2 mission. The analyses are carried out by means of traditional canonical correlation analysis (CCA) and canonical information analysis (CIA). Where CCA is based on maximising correlation between linear combinations of the two data sets, CIA maximises mutual information between the two. CIA is a conceptually more pleasing method for the analysis of data with very different modalities such as radar and optical data. Although a little inconclusive as far as the change detection aspect is concerned, results show that CIA analysis gives conspicuously less noisy appearing images of canonical variates (CVs) than CCA. Also, the 2D histogram of the mutual information based leading CVs clearly reveals much more structure than the correlation based one. This gives promise for potentially better change detection results with CIA than can be obtained by means of CCA.",
keywords = "Theoretical Computer Science, Computer Science (all), Canonical correlation analysis, Canonical information analysis, Correlation methods, Information analysis, Radar, Synthetic aperture radar, 2-D histograms, Analysis of data, Canonical analysis, Change detection, Joint analysis, Linear combinations, Mutual informations, Image analysis",
author = "Nielsen, {Allan Aasbjerg} and Rasmus Larsen",
year = "2017",
doi = "10.1007/978-3-319-59129-2_13",
language = "English",
isbn = "9783319591285",
volume = "10270",
pages = "147--158",
booktitle = "Image Analysis",
publisher = "IEEE",
address = "United States",

}

Nielsen, AA & Larsen, R 2017, Canonical analysis of sentinel-1 radar and sentinel-2 optical data. in Image Analysis. vol. 10270, IEEE, Lecture Notes in Computer Science, vol. 10270, pp. 147-158, 20th Scandinavian Conference on Image Analysis, Tromsø, Norway, 12/06/2017. https://doi.org/10.1007/978-3-319-59129-2_13

Canonical analysis of sentinel-1 radar and sentinel-2 optical data. / Nielsen, Allan Aasbjerg; Larsen, Rasmus.

Image Analysis. Vol. 10270 IEEE, 2017. p. 147-158 (Lecture Notes in Computer Science, Vol. 10270).

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Canonical analysis of sentinel-1 radar and sentinel-2 optical data

AU - Nielsen, Allan Aasbjerg

AU - Larsen, Rasmus

PY - 2017

Y1 - 2017

N2 - This paper gives results from joint analyses of dual polarimety synthetic aperture radar data from the Sentinel-1 mission and optical data from the Sentinel-2 mission. The analyses are carried out by means of traditional canonical correlation analysis (CCA) and canonical information analysis (CIA). Where CCA is based on maximising correlation between linear combinations of the two data sets, CIA maximises mutual information between the two. CIA is a conceptually more pleasing method for the analysis of data with very different modalities such as radar and optical data. Although a little inconclusive as far as the change detection aspect is concerned, results show that CIA analysis gives conspicuously less noisy appearing images of canonical variates (CVs) than CCA. Also, the 2D histogram of the mutual information based leading CVs clearly reveals much more structure than the correlation based one. This gives promise for potentially better change detection results with CIA than can be obtained by means of CCA.

AB - This paper gives results from joint analyses of dual polarimety synthetic aperture radar data from the Sentinel-1 mission and optical data from the Sentinel-2 mission. The analyses are carried out by means of traditional canonical correlation analysis (CCA) and canonical information analysis (CIA). Where CCA is based on maximising correlation between linear combinations of the two data sets, CIA maximises mutual information between the two. CIA is a conceptually more pleasing method for the analysis of data with very different modalities such as radar and optical data. Although a little inconclusive as far as the change detection aspect is concerned, results show that CIA analysis gives conspicuously less noisy appearing images of canonical variates (CVs) than CCA. Also, the 2D histogram of the mutual information based leading CVs clearly reveals much more structure than the correlation based one. This gives promise for potentially better change detection results with CIA than can be obtained by means of CCA.

KW - Theoretical Computer Science

KW - Computer Science (all)

KW - Canonical correlation analysis

KW - Canonical information analysis

KW - Correlation methods

KW - Information analysis

KW - Radar

KW - Synthetic aperture radar

KW - 2-D histograms

KW - Analysis of data

KW - Canonical analysis

KW - Change detection

KW - Joint analysis

KW - Linear combinations

KW - Mutual informations

KW - Image analysis

U2 - 10.1007/978-3-319-59129-2_13

DO - 10.1007/978-3-319-59129-2_13

M3 - Article in proceedings

SN - 9783319591285

VL - 10270

SP - 147

EP - 158

BT - Image Analysis

PB - IEEE

ER -

Nielsen AA, Larsen R. Canonical analysis of sentinel-1 radar and sentinel-2 optical data. In Image Analysis. Vol. 10270. IEEE. 2017. p. 147-158. (Lecture Notes in Computer Science, Vol. 10270). https://doi.org/10.1007/978-3-319-59129-2_13