Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery

Leen Kiat Soh, Costas Tsatsoulis

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

In this paper we present a feature extraction technique that extracts ice floes for Synthetic Aperture Radar (SAR) sea ice imagery. We investigate two types of ice floes: 1) independent ice floes that collide and meet, and 2) component ice floes that melt and consolidate to form an independent ice floe. To detect independent ice floes, we consider two kinds of edges: 1) clear edges, and 2) blurred edges. We use a spatial enhancement technique combined with thresholding to obtain the clear edges. To detect the blurred edges, we make use of `corners' which are pixels where a considerable change in direction of a floe boundary occurs. To connect the corners appropriately, we incorporate both their geometric and semantic properties into heuristics that choose which pair of corners to connect. To investigate component ice floes, we have developed a technique that combines thresholding, correlation, morphological cleaning, and structural growing. Our technique has been tested successfully on a large number of SAR images, including data from ERS-1.

Original languageEnglish (US)
Title of host publicationBetter Understanding of Earth Environment
EditorsSadao Fujimura
PublisherPubl by IEEE
Pages632-634
Number of pages3
ISBN (Print)0780312406
StatePublished - Dec 1 1993
EventProceedings of the 13th Annual International Geoscience and Remote Sensing Symposium - Tokyo, Jpn
Duration: Aug 18 1993Aug 21 1993

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2

Other

OtherProceedings of the 13th Annual International Geoscience and Remote Sensing Symposium
CityTokyo, Jpn
Period8/18/938/21/93

Fingerprint

Sea ice
Synthetic aperture radar
Ice
sea ice
Feature extraction
synthetic aperture radar
imagery
ice
heuristics
Cleaning
pixel
Pixels
Semantics
melt

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Soh, L. K., & Tsatsoulis, C. (1993). Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery. In S. Fujimura (Ed.), Better Understanding of Earth Environment (pp. 632-634). (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2). Publ by IEEE.

Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery. / Soh, Leen Kiat; Tsatsoulis, Costas.

Better Understanding of Earth Environment. ed. / Sadao Fujimura. Publ by IEEE, 1993. p. 632-634 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Soh, LK & Tsatsoulis, C 1993, Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery. in S Fujimura (ed.), Better Understanding of Earth Environment. International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2, Publ by IEEE, pp. 632-634, Proceedings of the 13th Annual International Geoscience and Remote Sensing Symposium, Tokyo, Jpn, 8/18/93.
Soh LK, Tsatsoulis C. Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery. In Fujimura S, editor, Better Understanding of Earth Environment. Publ by IEEE. 1993. p. 632-634. (International Geoscience and Remote Sensing Symposium (IGARSS)).
Soh, Leen Kiat ; Tsatsoulis, Costas. / Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery. Better Understanding of Earth Environment. editor / Sadao Fujimura. Publ by IEEE, 1993. pp. 632-634 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{3586fea6ed9b464a8141c11a28ff8950,
title = "Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery",
abstract = "In this paper we present a feature extraction technique that extracts ice floes for Synthetic Aperture Radar (SAR) sea ice imagery. We investigate two types of ice floes: 1) independent ice floes that collide and meet, and 2) component ice floes that melt and consolidate to form an independent ice floe. To detect independent ice floes, we consider two kinds of edges: 1) clear edges, and 2) blurred edges. We use a spatial enhancement technique combined with thresholding to obtain the clear edges. To detect the blurred edges, we make use of `corners' which are pixels where a considerable change in direction of a floe boundary occurs. To connect the corners appropriately, we incorporate both their geometric and semantic properties into heuristics that choose which pair of corners to connect. To investigate component ice floes, we have developed a technique that combines thresholding, correlation, morphological cleaning, and structural growing. Our technique has been tested successfully on a large number of SAR images, including data from ERS-1.",
author = "Soh, {Leen Kiat} and Costas Tsatsoulis",
year = "1993",
month = "12",
day = "1",
language = "English (US)",
isbn = "0780312406",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Publ by IEEE",
pages = "632--634",
editor = "Sadao Fujimura",
booktitle = "Better Understanding of Earth Environment",

}

TY - GEN

T1 - Feature extraction technique for synthetic aperture radar (SAR) sea ice imagery

AU - Soh, Leen Kiat

AU - Tsatsoulis, Costas

PY - 1993/12/1

Y1 - 1993/12/1

N2 - In this paper we present a feature extraction technique that extracts ice floes for Synthetic Aperture Radar (SAR) sea ice imagery. We investigate two types of ice floes: 1) independent ice floes that collide and meet, and 2) component ice floes that melt and consolidate to form an independent ice floe. To detect independent ice floes, we consider two kinds of edges: 1) clear edges, and 2) blurred edges. We use a spatial enhancement technique combined with thresholding to obtain the clear edges. To detect the blurred edges, we make use of `corners' which are pixels where a considerable change in direction of a floe boundary occurs. To connect the corners appropriately, we incorporate both their geometric and semantic properties into heuristics that choose which pair of corners to connect. To investigate component ice floes, we have developed a technique that combines thresholding, correlation, morphological cleaning, and structural growing. Our technique has been tested successfully on a large number of SAR images, including data from ERS-1.

AB - In this paper we present a feature extraction technique that extracts ice floes for Synthetic Aperture Radar (SAR) sea ice imagery. We investigate two types of ice floes: 1) independent ice floes that collide and meet, and 2) component ice floes that melt and consolidate to form an independent ice floe. To detect independent ice floes, we consider two kinds of edges: 1) clear edges, and 2) blurred edges. We use a spatial enhancement technique combined with thresholding to obtain the clear edges. To detect the blurred edges, we make use of `corners' which are pixels where a considerable change in direction of a floe boundary occurs. To connect the corners appropriately, we incorporate both their geometric and semantic properties into heuristics that choose which pair of corners to connect. To investigate component ice floes, we have developed a technique that combines thresholding, correlation, morphological cleaning, and structural growing. Our technique has been tested successfully on a large number of SAR images, including data from ERS-1.

UR - http://www.scopus.com/inward/record.url?scp=0027801868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027801868&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0027801868

SN - 0780312406

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 632

EP - 634

BT - Better Understanding of Earth Environment

A2 - Fujimura, Sadao

PB - Publ by IEEE

ER -