Enhanced detection of the coral Acropora cervicornis from satellite imagery using a textural operator

Sam Purkis, Soe W. Myint, Bernhard M. Riegl

Research output: Contribution to journalArticle

43 Citations (Scopus)

Abstract

The strength of a texture-based classification lies in the fact that it detects spatial patterning as a function of spectral variation within a particular facies class, as opposed to spectral consistency which drives standard probability-driven image classifiers. Following this premise, the Moran's I spatial autocorrelation metric was proven to return values which differed significantly for areas characterised by dense interlocking thickets of the coral Acropora cervicornis versus areas populated by a sparse mixed coral assemblage dominated by Montastrea annularis. The different behaviour of the metric was sufficient to facilitate spatial discrimination of the two assemblages using a supervised classifier with accuracies that surpass the level of prediction offered by standard spectral-based methods. Discrimination was optimum when autocorrelation was evaluated within a moving window with side-lengths ranging between circa. 30-70 m. The discrimination ability is postulated to be linked to intrinsic differences in the spatial-patterning of the two assemblages at scales of tens of metres. The observed patterning can be further related to the growth form and architecture of the differing coral assemblages. The study demonstrates the potential of using kernel-based autocorrelation metrics in unison with satellite data and offers a pertinent tool for monitoring ecologically important coral assemblages that are statistically indistinct using traditional spectral methods.

Original languageEnglish (US)
Pages (from-to)82-94
Number of pages13
JournalRemote Sensing of Environment
Volume101
Issue number1
DOIs
StatePublished - Mar 15 2006
Externally publishedYes

Fingerprint

Satellite imagery
Autocorrelation
satellite imagery
corals
coral
autocorrelation
Classifiers
growth form
Textures
Satellites
remote sensing
satellite data
Monitoring
texture
taxonomy
prediction
detection
Acropora cervicornis
monitoring
seeds

Keywords

  • Acropora cervicornis
  • Coral reef
  • IKONOS
  • Spatial autocorrelation
  • Texture

ASJC Scopus subject areas

  • Soil Science
  • Geology
  • Computers in Earth Sciences

Cite this

Enhanced detection of the coral Acropora cervicornis from satellite imagery using a textural operator. / Purkis, Sam; Myint, Soe W.; Riegl, Bernhard M.

In: Remote Sensing of Environment, Vol. 101, No. 1, 15.03.2006, p. 82-94.

Research output: Contribution to journalArticle

@article{c464510db2ba490ea48ef11416ba536e,
title = "Enhanced detection of the coral Acropora cervicornis from satellite imagery using a textural operator",
abstract = "The strength of a texture-based classification lies in the fact that it detects spatial patterning as a function of spectral variation within a particular facies class, as opposed to spectral consistency which drives standard probability-driven image classifiers. Following this premise, the Moran's I spatial autocorrelation metric was proven to return values which differed significantly for areas characterised by dense interlocking thickets of the coral Acropora cervicornis versus areas populated by a sparse mixed coral assemblage dominated by Montastrea annularis. The different behaviour of the metric was sufficient to facilitate spatial discrimination of the two assemblages using a supervised classifier with accuracies that surpass the level of prediction offered by standard spectral-based methods. Discrimination was optimum when autocorrelation was evaluated within a moving window with side-lengths ranging between circa. 30-70 m. The discrimination ability is postulated to be linked to intrinsic differences in the spatial-patterning of the two assemblages at scales of tens of metres. The observed patterning can be further related to the growth form and architecture of the differing coral assemblages. The study demonstrates the potential of using kernel-based autocorrelation metrics in unison with satellite data and offers a pertinent tool for monitoring ecologically important coral assemblages that are statistically indistinct using traditional spectral methods.",
keywords = "Acropora cervicornis, Coral reef, IKONOS, Spatial autocorrelation, Texture",
author = "Sam Purkis and Myint, {Soe W.} and Riegl, {Bernhard M.}",
year = "2006",
month = "3",
day = "15",
doi = "10.1016/j.rse.2005.11.009",
language = "English (US)",
volume = "101",
pages = "82--94",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",
number = "1",

}

TY - JOUR

T1 - Enhanced detection of the coral Acropora cervicornis from satellite imagery using a textural operator

AU - Purkis, Sam

AU - Myint, Soe W.

AU - Riegl, Bernhard M.

PY - 2006/3/15

Y1 - 2006/3/15

N2 - The strength of a texture-based classification lies in the fact that it detects spatial patterning as a function of spectral variation within a particular facies class, as opposed to spectral consistency which drives standard probability-driven image classifiers. Following this premise, the Moran's I spatial autocorrelation metric was proven to return values which differed significantly for areas characterised by dense interlocking thickets of the coral Acropora cervicornis versus areas populated by a sparse mixed coral assemblage dominated by Montastrea annularis. The different behaviour of the metric was sufficient to facilitate spatial discrimination of the two assemblages using a supervised classifier with accuracies that surpass the level of prediction offered by standard spectral-based methods. Discrimination was optimum when autocorrelation was evaluated within a moving window with side-lengths ranging between circa. 30-70 m. The discrimination ability is postulated to be linked to intrinsic differences in the spatial-patterning of the two assemblages at scales of tens of metres. The observed patterning can be further related to the growth form and architecture of the differing coral assemblages. The study demonstrates the potential of using kernel-based autocorrelation metrics in unison with satellite data and offers a pertinent tool for monitoring ecologically important coral assemblages that are statistically indistinct using traditional spectral methods.

AB - The strength of a texture-based classification lies in the fact that it detects spatial patterning as a function of spectral variation within a particular facies class, as opposed to spectral consistency which drives standard probability-driven image classifiers. Following this premise, the Moran's I spatial autocorrelation metric was proven to return values which differed significantly for areas characterised by dense interlocking thickets of the coral Acropora cervicornis versus areas populated by a sparse mixed coral assemblage dominated by Montastrea annularis. The different behaviour of the metric was sufficient to facilitate spatial discrimination of the two assemblages using a supervised classifier with accuracies that surpass the level of prediction offered by standard spectral-based methods. Discrimination was optimum when autocorrelation was evaluated within a moving window with side-lengths ranging between circa. 30-70 m. The discrimination ability is postulated to be linked to intrinsic differences in the spatial-patterning of the two assemblages at scales of tens of metres. The observed patterning can be further related to the growth form and architecture of the differing coral assemblages. The study demonstrates the potential of using kernel-based autocorrelation metrics in unison with satellite data and offers a pertinent tool for monitoring ecologically important coral assemblages that are statistically indistinct using traditional spectral methods.

KW - Acropora cervicornis

KW - Coral reef

KW - IKONOS

KW - Spatial autocorrelation

KW - Texture

UR - http://www.scopus.com/inward/record.url?scp=33344458841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33344458841&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2005.11.009

DO - 10.1016/j.rse.2005.11.009

M3 - Article

AN - SCOPUS:33344458841

VL - 101

SP - 82

EP - 94

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

IS - 1

ER -