Techniques for accuracy assessment of tree locations extracted from remotely sensed imagery

Trisalyn Nelson, Barry Boots, Michael A. Wulder

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Remotely sensed imagery is becoming a common source of environmental data. Consequently, there is an increasing need for tools to assess the accuracy and information content of such data. Particularly when the spatial resolution of imagery is fine, the accuracy of image processing is determined by comparisons with field data. However, the nature of error is more difficult to assess. In this paper we describe a set of tools intended for such an assessment when tree objects are extracted and field data are available for comparison. These techniques are demonstrated on individual tree locations extracted from an IKONOS image via local maximum filtering. The locations of the extracted trees are compared with field data to determine the number of found and missed trees. Aspatial and spatial (Voronoi) analysis methods are used to examine the nature of errors by searching for trends in characteristics of found and missed trees. As well, analysis is conducted to assess the information content of found trees.

Original languageEnglish (US)
Pages (from-to)265-271
Number of pages7
JournalJournal of Environmental Management
Volume74
Issue number3
DOIs
StatePublished - Feb 2005
Externally publishedYes

Fingerprint

accuracy assessment
imagery
Image processing
IKONOS
spatial analysis
image processing
spatial resolution

Keywords

  • Accuracy assessment
  • Feature extraction
  • Spatial autocorrelation
  • Voronoi polygon

ASJC Scopus subject areas

  • Environmental Science(all)
  • Management, Monitoring, Policy and Law

Cite this

Techniques for accuracy assessment of tree locations extracted from remotely sensed imagery. / Nelson, Trisalyn; Boots, Barry; Wulder, Michael A.

In: Journal of Environmental Management, Vol. 74, No. 3, 02.2005, p. 265-271.

Research output: Contribution to journalArticle

@article{16cf0f12fa9940fba2ee89d1861d05f7,
title = "Techniques for accuracy assessment of tree locations extracted from remotely sensed imagery",
abstract = "Remotely sensed imagery is becoming a common source of environmental data. Consequently, there is an increasing need for tools to assess the accuracy and information content of such data. Particularly when the spatial resolution of imagery is fine, the accuracy of image processing is determined by comparisons with field data. However, the nature of error is more difficult to assess. In this paper we describe a set of tools intended for such an assessment when tree objects are extracted and field data are available for comparison. These techniques are demonstrated on individual tree locations extracted from an IKONOS image via local maximum filtering. The locations of the extracted trees are compared with field data to determine the number of found and missed trees. Aspatial and spatial (Voronoi) analysis methods are used to examine the nature of errors by searching for trends in characteristics of found and missed trees. As well, analysis is conducted to assess the information content of found trees.",
keywords = "Accuracy assessment, Feature extraction, Spatial autocorrelation, Voronoi polygon",
author = "Trisalyn Nelson and Barry Boots and Wulder, {Michael A.}",
year = "2005",
month = "2",
doi = "10.1016/j.jenvman.2004.10.002",
language = "English (US)",
volume = "74",
pages = "265--271",
journal = "Journal of Environmental Management",
issn = "0301-4797",
publisher = "Academic Press Inc.",
number = "3",

}

TY - JOUR

T1 - Techniques for accuracy assessment of tree locations extracted from remotely sensed imagery

AU - Nelson, Trisalyn

AU - Boots, Barry

AU - Wulder, Michael A.

PY - 2005/2

Y1 - 2005/2

N2 - Remotely sensed imagery is becoming a common source of environmental data. Consequently, there is an increasing need for tools to assess the accuracy and information content of such data. Particularly when the spatial resolution of imagery is fine, the accuracy of image processing is determined by comparisons with field data. However, the nature of error is more difficult to assess. In this paper we describe a set of tools intended for such an assessment when tree objects are extracted and field data are available for comparison. These techniques are demonstrated on individual tree locations extracted from an IKONOS image via local maximum filtering. The locations of the extracted trees are compared with field data to determine the number of found and missed trees. Aspatial and spatial (Voronoi) analysis methods are used to examine the nature of errors by searching for trends in characteristics of found and missed trees. As well, analysis is conducted to assess the information content of found trees.

AB - Remotely sensed imagery is becoming a common source of environmental data. Consequently, there is an increasing need for tools to assess the accuracy and information content of such data. Particularly when the spatial resolution of imagery is fine, the accuracy of image processing is determined by comparisons with field data. However, the nature of error is more difficult to assess. In this paper we describe a set of tools intended for such an assessment when tree objects are extracted and field data are available for comparison. These techniques are demonstrated on individual tree locations extracted from an IKONOS image via local maximum filtering. The locations of the extracted trees are compared with field data to determine the number of found and missed trees. Aspatial and spatial (Voronoi) analysis methods are used to examine the nature of errors by searching for trends in characteristics of found and missed trees. As well, analysis is conducted to assess the information content of found trees.

KW - Accuracy assessment

KW - Feature extraction

KW - Spatial autocorrelation

KW - Voronoi polygon

UR - http://www.scopus.com/inward/record.url?scp=12144251069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12144251069&partnerID=8YFLogxK

U2 - 10.1016/j.jenvman.2004.10.002

DO - 10.1016/j.jenvman.2004.10.002

M3 - Article

C2 - 15644266

AN - SCOPUS:12144251069

VL - 74

SP - 265

EP - 271

JO - Journal of Environmental Management

JF - Journal of Environmental Management

SN - 0301-4797

IS - 3

ER -