Automated tree recognition in old growth conifer stands with high resolution digital imagery

Donald G. Leckie, François A. Gougeon, Sally Tinis, Trisalyn Nelson, Charles N. Burnett, Dennis Paradine

Research output: Contribution to journalArticle

135 Citations (Scopus)

Abstract

Automated individual tree isolation and species determination with high resolution multispectral imagery is becoming a viable forest survey tool. Application to old growth conifer forests offer unique technical issues including high variability in tree size and dominance, strong tree shading and obscuration, and varying ages and states of health. The capabilities of individual tree analysis are examined with two acquisitions of 70-cm resolution CASI imagery over a hemlock, amabilis fir, and cedar dominated old growth site on the west coast of Canada. Trees were delineated using the valley following approach of the Individual Tree Crown (ITC) software suite, classified according to species (hemlock, amabilis fir, and cedar) using object-based spectral classification and tested on a tree-for-tree basis against data derived from ground plots. Tree-for-tree isolation and species classification accuracy assessment, although often sobering, is important for portraying the overall effectiveness of species composition mapping using single tree approaches. This accuracy considers not only how well each tree is classified, but how well each automated isolation represents a true tree and its species. Omissions and commissions need to be included in overall species accuracy assessment. A structure of rules for defining isolation accuracy is developed and used. An example is given of a new approach to accuracy analysis incorporating both isolation and classification results (automated tree recognition) and the issues this presents. The automated tree isolation performed well on those trees that could be visually identified on the imagery using ground measured stem maps (approximately 50-60% of trees had a good match between manual and automated delineations). There were few omissions. Commission errors, i.e., automated isolations not associated with a delineated ground reference tree, were a problem (25%) usually associated with spurious higher intensity areas within shaded regions, which get confused in the process of trying to isolate shaded trees. Difficulty in classifying species was caused by: variability of the spectral signatures of the old growth trees within the same species, tree health, and trees partly or fully shaded by other trees. To accommodate this variability, several signatures were used to represent each species including shaded trees. Species could not be determined for the shaded cases or for the unhealthy trees and therefore two combined classes, a shaded class and unhealthy class with all species included, were used for further analysis. Species classification accuracy of the trees for which there was a good automated isolation match was 72%, 60%, and 40% for the non-shaded healthy hemlock, balsam, and cedar trees for the 1996 data. Equivalent accuracy for the 1998 imagery was 59% for hemlock, 80% for balsam, with only a few cedar trees being well isolated. If all other matches were considered an error in classification, species classification was poor (approximately 45% for balsam and hemlock, 25% for cedar). However, species classification accuracies incorporating the good isolation matches and trees for which there was a match of an isolations and reference tree but the match was not considered good were moderate (60%, 57%, and 38% for hemlock, balsam, and cedar from the 1996 data; 62%, 61%, and 89%, respectively, for the 1998 imagery). Automated tree isolation and species classification of old growth forests is difficult, but nevertheless in this example useful results were obtained. Crown

Original languageEnglish (US)
Pages (from-to)311-326
Number of pages16
JournalRemote Sensing of Environment
Volume94
Issue number3
DOIs
StatePublished - Feb 15 2005
Externally publishedYes

Fingerprint

conifers
coniferous tree
imagery
Health
Coastal zones
old-growth forests
accuracy assessment
Abies
taxonomy
tree crown
Chemical analysis
multispectral imagery
forest surveys

Keywords

  • Accuracy assessment
  • Forest inventory
  • Individual tree crown
  • Species classification
  • Tree isolation

ASJC Scopus subject areas

  • Computers in Earth Sciences
  • Earth-Surface Processes
  • Environmental Science(all)
  • Management, Monitoring, Policy and Law

Cite this

Automated tree recognition in old growth conifer stands with high resolution digital imagery. / Leckie, Donald G.; Gougeon, François A.; Tinis, Sally; Nelson, Trisalyn; Burnett, Charles N.; Paradine, Dennis.

In: Remote Sensing of Environment, Vol. 94, No. 3, 15.02.2005, p. 311-326.

Research output: Contribution to journalArticle

Leckie, Donald G. ; Gougeon, François A. ; Tinis, Sally ; Nelson, Trisalyn ; Burnett, Charles N. ; Paradine, Dennis. / Automated tree recognition in old growth conifer stands with high resolution digital imagery. In: Remote Sensing of Environment. 2005 ; Vol. 94, No. 3. pp. 311-326.
@article{2ba3961066d54178b3e57c70a3d973a7,
title = "Automated tree recognition in old growth conifer stands with high resolution digital imagery",
abstract = "Automated individual tree isolation and species determination with high resolution multispectral imagery is becoming a viable forest survey tool. Application to old growth conifer forests offer unique technical issues including high variability in tree size and dominance, strong tree shading and obscuration, and varying ages and states of health. The capabilities of individual tree analysis are examined with two acquisitions of 70-cm resolution CASI imagery over a hemlock, amabilis fir, and cedar dominated old growth site on the west coast of Canada. Trees were delineated using the valley following approach of the Individual Tree Crown (ITC) software suite, classified according to species (hemlock, amabilis fir, and cedar) using object-based spectral classification and tested on a tree-for-tree basis against data derived from ground plots. Tree-for-tree isolation and species classification accuracy assessment, although often sobering, is important for portraying the overall effectiveness of species composition mapping using single tree approaches. This accuracy considers not only how well each tree is classified, but how well each automated isolation represents a true tree and its species. Omissions and commissions need to be included in overall species accuracy assessment. A structure of rules for defining isolation accuracy is developed and used. An example is given of a new approach to accuracy analysis incorporating both isolation and classification results (automated tree recognition) and the issues this presents. The automated tree isolation performed well on those trees that could be visually identified on the imagery using ground measured stem maps (approximately 50-60{\%} of trees had a good match between manual and automated delineations). There were few omissions. Commission errors, i.e., automated isolations not associated with a delineated ground reference tree, were a problem (25{\%}) usually associated with spurious higher intensity areas within shaded regions, which get confused in the process of trying to isolate shaded trees. Difficulty in classifying species was caused by: variability of the spectral signatures of the old growth trees within the same species, tree health, and trees partly or fully shaded by other trees. To accommodate this variability, several signatures were used to represent each species including shaded trees. Species could not be determined for the shaded cases or for the unhealthy trees and therefore two combined classes, a shaded class and unhealthy class with all species included, were used for further analysis. Species classification accuracy of the trees for which there was a good automated isolation match was 72{\%}, 60{\%}, and 40{\%} for the non-shaded healthy hemlock, balsam, and cedar trees for the 1996 data. Equivalent accuracy for the 1998 imagery was 59{\%} for hemlock, 80{\%} for balsam, with only a few cedar trees being well isolated. If all other matches were considered an error in classification, species classification was poor (approximately 45{\%} for balsam and hemlock, 25{\%} for cedar). However, species classification accuracies incorporating the good isolation matches and trees for which there was a match of an isolations and reference tree but the match was not considered good were moderate (60{\%}, 57{\%}, and 38{\%} for hemlock, balsam, and cedar from the 1996 data; 62{\%}, 61{\%}, and 89{\%}, respectively, for the 1998 imagery). Automated tree isolation and species classification of old growth forests is difficult, but nevertheless in this example useful results were obtained. Crown",
keywords = "Accuracy assessment, Forest inventory, Individual tree crown, Species classification, Tree isolation",
author = "Leckie, {Donald G.} and Gougeon, {Fran{\cc}ois A.} and Sally Tinis and Trisalyn Nelson and Burnett, {Charles N.} and Dennis Paradine",
year = "2005",
month = "2",
day = "15",
doi = "10.1016/j.rse.2004.10.011",
language = "English (US)",
volume = "94",
pages = "311--326",
journal = "Remote Sensing of Environment",
issn = "0034-4257",
publisher = "Elsevier Inc.",
number = "3",

}

TY - JOUR

T1 - Automated tree recognition in old growth conifer stands with high resolution digital imagery

AU - Leckie, Donald G.

AU - Gougeon, François A.

AU - Tinis, Sally

AU - Nelson, Trisalyn

AU - Burnett, Charles N.

AU - Paradine, Dennis

PY - 2005/2/15

Y1 - 2005/2/15

N2 - Automated individual tree isolation and species determination with high resolution multispectral imagery is becoming a viable forest survey tool. Application to old growth conifer forests offer unique technical issues including high variability in tree size and dominance, strong tree shading and obscuration, and varying ages and states of health. The capabilities of individual tree analysis are examined with two acquisitions of 70-cm resolution CASI imagery over a hemlock, amabilis fir, and cedar dominated old growth site on the west coast of Canada. Trees were delineated using the valley following approach of the Individual Tree Crown (ITC) software suite, classified according to species (hemlock, amabilis fir, and cedar) using object-based spectral classification and tested on a tree-for-tree basis against data derived from ground plots. Tree-for-tree isolation and species classification accuracy assessment, although often sobering, is important for portraying the overall effectiveness of species composition mapping using single tree approaches. This accuracy considers not only how well each tree is classified, but how well each automated isolation represents a true tree and its species. Omissions and commissions need to be included in overall species accuracy assessment. A structure of rules for defining isolation accuracy is developed and used. An example is given of a new approach to accuracy analysis incorporating both isolation and classification results (automated tree recognition) and the issues this presents. The automated tree isolation performed well on those trees that could be visually identified on the imagery using ground measured stem maps (approximately 50-60% of trees had a good match between manual and automated delineations). There were few omissions. Commission errors, i.e., automated isolations not associated with a delineated ground reference tree, were a problem (25%) usually associated with spurious higher intensity areas within shaded regions, which get confused in the process of trying to isolate shaded trees. Difficulty in classifying species was caused by: variability of the spectral signatures of the old growth trees within the same species, tree health, and trees partly or fully shaded by other trees. To accommodate this variability, several signatures were used to represent each species including shaded trees. Species could not be determined for the shaded cases or for the unhealthy trees and therefore two combined classes, a shaded class and unhealthy class with all species included, were used for further analysis. Species classification accuracy of the trees for which there was a good automated isolation match was 72%, 60%, and 40% for the non-shaded healthy hemlock, balsam, and cedar trees for the 1996 data. Equivalent accuracy for the 1998 imagery was 59% for hemlock, 80% for balsam, with only a few cedar trees being well isolated. If all other matches were considered an error in classification, species classification was poor (approximately 45% for balsam and hemlock, 25% for cedar). However, species classification accuracies incorporating the good isolation matches and trees for which there was a match of an isolations and reference tree but the match was not considered good were moderate (60%, 57%, and 38% for hemlock, balsam, and cedar from the 1996 data; 62%, 61%, and 89%, respectively, for the 1998 imagery). Automated tree isolation and species classification of old growth forests is difficult, but nevertheless in this example useful results were obtained. Crown

AB - Automated individual tree isolation and species determination with high resolution multispectral imagery is becoming a viable forest survey tool. Application to old growth conifer forests offer unique technical issues including high variability in tree size and dominance, strong tree shading and obscuration, and varying ages and states of health. The capabilities of individual tree analysis are examined with two acquisitions of 70-cm resolution CASI imagery over a hemlock, amabilis fir, and cedar dominated old growth site on the west coast of Canada. Trees were delineated using the valley following approach of the Individual Tree Crown (ITC) software suite, classified according to species (hemlock, amabilis fir, and cedar) using object-based spectral classification and tested on a tree-for-tree basis against data derived from ground plots. Tree-for-tree isolation and species classification accuracy assessment, although often sobering, is important for portraying the overall effectiveness of species composition mapping using single tree approaches. This accuracy considers not only how well each tree is classified, but how well each automated isolation represents a true tree and its species. Omissions and commissions need to be included in overall species accuracy assessment. A structure of rules for defining isolation accuracy is developed and used. An example is given of a new approach to accuracy analysis incorporating both isolation and classification results (automated tree recognition) and the issues this presents. The automated tree isolation performed well on those trees that could be visually identified on the imagery using ground measured stem maps (approximately 50-60% of trees had a good match between manual and automated delineations). There were few omissions. Commission errors, i.e., automated isolations not associated with a delineated ground reference tree, were a problem (25%) usually associated with spurious higher intensity areas within shaded regions, which get confused in the process of trying to isolate shaded trees. Difficulty in classifying species was caused by: variability of the spectral signatures of the old growth trees within the same species, tree health, and trees partly or fully shaded by other trees. To accommodate this variability, several signatures were used to represent each species including shaded trees. Species could not be determined for the shaded cases or for the unhealthy trees and therefore two combined classes, a shaded class and unhealthy class with all species included, were used for further analysis. Species classification accuracy of the trees for which there was a good automated isolation match was 72%, 60%, and 40% for the non-shaded healthy hemlock, balsam, and cedar trees for the 1996 data. Equivalent accuracy for the 1998 imagery was 59% for hemlock, 80% for balsam, with only a few cedar trees being well isolated. If all other matches were considered an error in classification, species classification was poor (approximately 45% for balsam and hemlock, 25% for cedar). However, species classification accuracies incorporating the good isolation matches and trees for which there was a match of an isolations and reference tree but the match was not considered good were moderate (60%, 57%, and 38% for hemlock, balsam, and cedar from the 1996 data; 62%, 61%, and 89%, respectively, for the 1998 imagery). Automated tree isolation and species classification of old growth forests is difficult, but nevertheless in this example useful results were obtained. Crown

KW - Accuracy assessment

KW - Forest inventory

KW - Individual tree crown

KW - Species classification

KW - Tree isolation

UR - http://www.scopus.com/inward/record.url?scp=12344295841&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=12344295841&partnerID=8YFLogxK

U2 - 10.1016/j.rse.2004.10.011

DO - 10.1016/j.rse.2004.10.011

M3 - Article

AN - SCOPUS:12344295841

VL - 94

SP - 311

EP - 326

JO - Remote Sensing of Environment

JF - Remote Sensing of Environment

SN - 0034-4257

IS - 3

ER -