Multisource data and knowledge fusion for intelligent SAR sea ice classification

Leen-Kiat Soh, Costas Tsatsoulis

Research output: Contribution to conferencePaper

10 Citations (Scopus)

Abstract

In this paper we describe the fusion of various data and knowledge sources for intelligent SAR sea ice classification, thereby addressing the weaknesses of each information source while improving the overall reasoning power of the classifier. We equip our ice classification system, ARKTOS, with the capability of analyzing and classifying images unsupervised by emulating how a human geophysicist or photo-interpreter classifies SAR images. To imitate human visual inspection of raw images, we have designed and implemented a data mining application that first categorizes pixels into regions, and then extracts for each region a complex feature set of more than 30 attributes. In addition, we have incorporated other sea ice data and knowledge products such as ice concentration maps, operational ice charts, and land masks. Finally, we solicited human sea ice expertise as classification rules through interviews, and collaborative refinements during the early-stage evaluations. Using a Dempster-Shafer belief system, we are able to perform multisource data and knowledge fusion in ARKTOS' rule-based classification. ARKTOS has been installed at the National Ice Center and Canadian Ice Service.

Original languageEnglish (US)
Pages68-70
Number of pages3
StatePublished - Dec 1 1999
EventProceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' - Hamburg, Ger
Duration: Jun 28 1999Jul 2 1999

Other

OtherProceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century'
CityHamburg, Ger
Period6/28/997/2/99

Fingerprint

Sea ice
Ice
sea ice
synthetic aperture radar
Fusion reactions
ice
data mining
Data mining
Masks
pixel
Classifiers
Inspection
Pixels

ASJC Scopus subject areas

  • Software
  • Geology

Cite this

Soh, L-K., & Tsatsoulis, C. (1999). Multisource data and knowledge fusion for intelligent SAR sea ice classification. 68-70. Paper presented at Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger, .

Multisource data and knowledge fusion for intelligent SAR sea ice classification. / Soh, Leen-Kiat; Tsatsoulis, Costas.

1999. 68-70 Paper presented at Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger, .

Research output: Contribution to conferencePaper

Soh, L-K & Tsatsoulis, C 1999, 'Multisource data and knowledge fusion for intelligent SAR sea ice classification' Paper presented at Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger, 6/28/99 - 7/2/99, pp. 68-70.
Soh L-K, Tsatsoulis C. Multisource data and knowledge fusion for intelligent SAR sea ice classification. 1999. Paper presented at Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger, .
Soh, Leen-Kiat ; Tsatsoulis, Costas. / Multisource data and knowledge fusion for intelligent SAR sea ice classification. Paper presented at Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century', Hamburg, Ger, .3 p.
@conference{60d563c4f0904a4ea0f847388cbfbbff,
title = "Multisource data and knowledge fusion for intelligent SAR sea ice classification",
abstract = "In this paper we describe the fusion of various data and knowledge sources for intelligent SAR sea ice classification, thereby addressing the weaknesses of each information source while improving the overall reasoning power of the classifier. We equip our ice classification system, ARKTOS, with the capability of analyzing and classifying images unsupervised by emulating how a human geophysicist or photo-interpreter classifies SAR images. To imitate human visual inspection of raw images, we have designed and implemented a data mining application that first categorizes pixels into regions, and then extracts for each region a complex feature set of more than 30 attributes. In addition, we have incorporated other sea ice data and knowledge products such as ice concentration maps, operational ice charts, and land masks. Finally, we solicited human sea ice expertise as classification rules through interviews, and collaborative refinements during the early-stage evaluations. Using a Dempster-Shafer belief system, we are able to perform multisource data and knowledge fusion in ARKTOS' rule-based classification. ARKTOS has been installed at the National Ice Center and Canadian Ice Service.",
author = "Leen-Kiat Soh and Costas Tsatsoulis",
year = "1999",
month = "12",
day = "1",
language = "English (US)",
pages = "68--70",
note = "Proceedings of the 1999 IEEE International Geoscience and Remote Sensing Symposium (IGARSS'99) 'Remote Sensing of the Systems Earth - A Challenge for the 21st Century' ; Conference date: 28-06-1999 Through 02-07-1999",

}

TY - CONF

T1 - Multisource data and knowledge fusion for intelligent SAR sea ice classification

AU - Soh, Leen-Kiat

AU - Tsatsoulis, Costas

PY - 1999/12/1

Y1 - 1999/12/1

N2 - In this paper we describe the fusion of various data and knowledge sources for intelligent SAR sea ice classification, thereby addressing the weaknesses of each information source while improving the overall reasoning power of the classifier. We equip our ice classification system, ARKTOS, with the capability of analyzing and classifying images unsupervised by emulating how a human geophysicist or photo-interpreter classifies SAR images. To imitate human visual inspection of raw images, we have designed and implemented a data mining application that first categorizes pixels into regions, and then extracts for each region a complex feature set of more than 30 attributes. In addition, we have incorporated other sea ice data and knowledge products such as ice concentration maps, operational ice charts, and land masks. Finally, we solicited human sea ice expertise as classification rules through interviews, and collaborative refinements during the early-stage evaluations. Using a Dempster-Shafer belief system, we are able to perform multisource data and knowledge fusion in ARKTOS' rule-based classification. ARKTOS has been installed at the National Ice Center and Canadian Ice Service.

AB - In this paper we describe the fusion of various data and knowledge sources for intelligent SAR sea ice classification, thereby addressing the weaknesses of each information source while improving the overall reasoning power of the classifier. We equip our ice classification system, ARKTOS, with the capability of analyzing and classifying images unsupervised by emulating how a human geophysicist or photo-interpreter classifies SAR images. To imitate human visual inspection of raw images, we have designed and implemented a data mining application that first categorizes pixels into regions, and then extracts for each region a complex feature set of more than 30 attributes. In addition, we have incorporated other sea ice data and knowledge products such as ice concentration maps, operational ice charts, and land masks. Finally, we solicited human sea ice expertise as classification rules through interviews, and collaborative refinements during the early-stage evaluations. Using a Dempster-Shafer belief system, we are able to perform multisource data and knowledge fusion in ARKTOS' rule-based classification. ARKTOS has been installed at the National Ice Center and Canadian Ice Service.

UR - http://www.scopus.com/inward/record.url?scp=0033318935&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033318935&partnerID=8YFLogxK

M3 - Paper

SP - 68

EP - 70

ER -