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

Allan Aasbjerg Nielsen; Rasmus Larsen

doi:10.1007/978-3-319-59129-2_13

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

Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review

931 Downloads (Orbit)

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 language	English
Title of host publication	Image Analysis
Volume	10270
Publisher	IEEE
Publication date	2017
Pages	147-158
ISBN (Print)	9783319591285
DOIs	https://doi.org/10.1007/978-3-319-59129-2_13
Publication status	Published - 2017
Event	20th Scandinavian Conference on Image Analysis - Tromsø, Norway Duration: 12 Jun 2017 → 14 Jun 2017 Conference number: 20 https://link.springer.com/book/10.1007/978-3-319-59126-1

Conference

Conference	20th Scandinavian Conference on Image Analysis
Number	20
Country/Territory	Norway
City	Tromsø
Period	12/06/2017 → 14/06/2017
Internet address	https://link.springer.com/book/10.1007/978-3-319-59126-1

Series	Lecture Notes in Computer Science
Volume	10270
ISSN	0302-9743

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

Access to Document

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

SCIA2017Accepted author manuscript, 13.4 MB

OpenUrl availability

Check availability in DTU Findit

Cite this

@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",

series = "Lecture Notes in Computer Science",

publisher = "IEEE",

pages = "147--158",

booktitle = "Image Analysis",

address = "United States",

note = "20th Scandinavian Conference on Image Analysis, SCIA 2017 ; Conference date: 12-06-2017 Through 14-06-2017",

url = "https://link.springer.com/book/10.1007/978-3-319-59126-1",

}

TY - GEN

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

AU - Nielsen, Allan Aasbjerg

AU - Larsen, Rasmus

N1 - Conference code: 20

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

T3 - Lecture Notes in Computer Science

SP - 147

EP - 158

BT - Image Analysis

PB - IEEE

T2 - 20th Scandinavian Conference on Image Analysis

Y2 - 12 June 2017 through 14 June 2017

ER -

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

Abstract

Conference

Keywords

Access to Document

OpenUrl availability

Fingerprint

Cite this