Segmentation of satellite imagery of natural scenes using data mining

Leen Kiat Soh, Costas Tsatsoulis

Research output: Contribution to journalArticle

48 Citations (Scopus)

Abstract

In this paper we describe a segmentation technique that integrates traditional image processing algorithms with techniques adapted from knowledge discovery in databases (KDD) and data mining to analyze and segment unstructured satellite images of natural scenes. We have divided our segmentation task into three major steps. First an initial segmentation is achieved using dynamic local thresholding producing a set of regions. Then spectral spatial and textural features for each region are generated from the thresholded image. Finally given these features as attributes an unsupervised machine learning methodology called conceptual clustering is used to cluster the regions found in the image into N classes-thus determining the number of classes in the image automatically. We have applied the technique successfully to ERS-1 synthetic aperture radar (SAR) Landsat thematic mapper (TM) and NOAA advanced very high resolution radiometer (AVHRR) data of natural scenes.

Original languageEnglish (US)
Pages (from-to)1086-1099
Number of pages14
JournalIEEE Transactions on Geoscience and Remote Sensing
Volume37
Issue number2 II
DOIs
StatePublished - Dec 1 1999

Fingerprint

satellite imagery
data mining
Satellite imagery
segmentation
Data mining
Advanced very high resolution radiometers (AVHRR)
Synthetic aperture radar
Learning systems
Image processing
Satellites
thematic mappers (LANDSAT)
ERS-1 (ESA satellite)
AVHRR
image processing
Landsat thematic mapper
Advanced Very High Resolution Radiometer
machine learning
synthetic aperture radar
methodology

Keywords

  • Clustering methods
  • Image segmentation
  • Natural scene analysis

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Earth and Planetary Sciences(all)

Cite this

Segmentation of satellite imagery of natural scenes using data mining. / Soh, Leen Kiat; Tsatsoulis, Costas.

In: IEEE Transactions on Geoscience and Remote Sensing, Vol. 37, No. 2 II, 01.12.1999, p. 1086-1099.

Research output: Contribution to journalArticle

@article{443e23efa5d54d07be9cd8eb3cc7ef53,
title = "Segmentation of satellite imagery of natural scenes using data mining",
abstract = "In this paper we describe a segmentation technique that integrates traditional image processing algorithms with techniques adapted from knowledge discovery in databases (KDD) and data mining to analyze and segment unstructured satellite images of natural scenes. We have divided our segmentation task into three major steps. First an initial segmentation is achieved using dynamic local thresholding producing a set of regions. Then spectral spatial and textural features for each region are generated from the thresholded image. Finally given these features as attributes an unsupervised machine learning methodology called conceptual clustering is used to cluster the regions found in the image into N classes-thus determining the number of classes in the image automatically. We have applied the technique successfully to ERS-1 synthetic aperture radar (SAR) Landsat thematic mapper (TM) and NOAA advanced very high resolution radiometer (AVHRR) data of natural scenes.",
keywords = "Clustering methods, Image segmentation, Natural scene analysis",
author = "Soh, {Leen Kiat} and Costas Tsatsoulis",
year = "1999",
month = "12",
day = "1",
doi = "10.1109/36.752227",
language = "English (US)",
volume = "37",
pages = "1086--1099",
journal = "IEEE Transactions on Geoscience and Remote Sensing",
issn = "0196-2892",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2 II",

}

TY - JOUR

T1 - Segmentation of satellite imagery of natural scenes using data mining

AU - Soh, Leen Kiat

AU - Tsatsoulis, Costas

PY - 1999/12/1

Y1 - 1999/12/1

N2 - In this paper we describe a segmentation technique that integrates traditional image processing algorithms with techniques adapted from knowledge discovery in databases (KDD) and data mining to analyze and segment unstructured satellite images of natural scenes. We have divided our segmentation task into three major steps. First an initial segmentation is achieved using dynamic local thresholding producing a set of regions. Then spectral spatial and textural features for each region are generated from the thresholded image. Finally given these features as attributes an unsupervised machine learning methodology called conceptual clustering is used to cluster the regions found in the image into N classes-thus determining the number of classes in the image automatically. We have applied the technique successfully to ERS-1 synthetic aperture radar (SAR) Landsat thematic mapper (TM) and NOAA advanced very high resolution radiometer (AVHRR) data of natural scenes.

AB - In this paper we describe a segmentation technique that integrates traditional image processing algorithms with techniques adapted from knowledge discovery in databases (KDD) and data mining to analyze and segment unstructured satellite images of natural scenes. We have divided our segmentation task into three major steps. First an initial segmentation is achieved using dynamic local thresholding producing a set of regions. Then spectral spatial and textural features for each region are generated from the thresholded image. Finally given these features as attributes an unsupervised machine learning methodology called conceptual clustering is used to cluster the regions found in the image into N classes-thus determining the number of classes in the image automatically. We have applied the technique successfully to ERS-1 synthetic aperture radar (SAR) Landsat thematic mapper (TM) and NOAA advanced very high resolution radiometer (AVHRR) data of natural scenes.

KW - Clustering methods

KW - Image segmentation

KW - Natural scene analysis

UR - http://www.scopus.com/inward/record.url?scp=0033098902&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0033098902&partnerID=8YFLogxK

U2 - 10.1109/36.752227

DO - 10.1109/36.752227

M3 - Article

AN - SCOPUS:0033098902

VL - 37

SP - 1086

EP - 1099

JO - IEEE Transactions on Geoscience and Remote Sensing

JF - IEEE Transactions on Geoscience and Remote Sensing

SN - 0196-2892

IS - 2 II

ER -