Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data

Wan Shafrina Wan Mohd Jaafar, Iain Hector Woodhouse, Carlos Alberto Silva, Hamdan Omar, Khairul Nizam Abdul Maulud, Andrew Thomas Hudak, Carine Klauberg, Adrián Cardil, Midhun Mohan

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Individual tree crown (ITC) segmentation is an approach to isolate individual tree from the background vegetation and delineate precisely the crown boundaries for forest management and inventory purposes. ITC detection and delineation have been commonly generated from canopy height model (CHM) derived from light detection and ranging (LiDAR) data. Existing ITC segmentation methods, however, are limited in their efficiency for characterizing closed canopies, especially in tropical forests, due to the overlapping structure and irregular shape of tree crowns. Furthermore, the potential of 3-dimensional (3D) LiDAR data is not fully realized by existing CHM-based methods. Thus, the aim of this study was to develop an efficient framework for ITC segmentation in tropical forests using LiDAR-derived CHM and 3D point cloud data in order to accurately estimate tree attributes such as the tree height, mean crown width and aboveground biomass (AGB). The proposed framework entails five major steps: (1) automatically identifying dominant tree crowns by implementing semi-variogram statistics and morphological analysis; (2) generating initial tree segments using a watershed algorithm based on mathematical morphology; (3) identifying "problematic" segments based on predetermined set of rules; (4) tuning the problematic segments using a modified distance-based algorithm (DBA); and (5) segmenting and counting the number of individual trees based on the 3D LiDAR point clouds within each of the identified segment. This approach was developed in a way such that the 3D LiDAR points were only examined on problematic segments identified for further evaluations. 209 reference trees with diameter at breast height (DBH) ≥ 10 cm were selected in the field in two study areas in order to validate ITC detection and delineation results of the proposed framework. We computed tree crown metrics (e.g., maximum crown height and mean crown width) to estimate aboveground biomass (AGB) at tree level using previously published allometric equations. Accuracy assessment was performed to calculate percentage of correctly detected trees, omission and commission errors. Our method correctly identified individual tree crowns with detection accuracy exceeding 80 percent at both forest sites. Also, our results showed high agreement (R2 > 0.64) in terms of AGB estimates using 3D LiDAR metrics and variables measured in the field, for both sites. The findings from our study demonstrate the efficacy of the proposed framework in delineating tree crowns, even in high canopy density areas such as tropical rainforests, where, usually the traditional algorithms are limited in their performances. Moreover, the high tree delineation accuracy in the two study areas emphasizes the potential robustness and transferability of our approach to other densely forested areas across the globe.

Original languageEnglish
Article number759
JournalForests
Volume9
Issue number12
DOIs
Publication statusPublished - 5 Dec 2018

Fingerprint

lidar
tropical forests
tropical forest
tree crown
canopy
aboveground biomass
segmentation
attribute
detection
forest inventory
tropical rain forests
tree and stand measurements
accuracy assessment
forest management

Keywords

  • 3D LiDAR point cloud
  • Aboveground biomass (AGB)
  • Canopy height model (CHM)
  • Individual tree crown (ITC)
  • LiDAR
  • Mathematical morphology
  • Tropical forest
  • Watershed

ASJC Scopus subject areas

  • Forestry

Cite this

Jaafar, W. S. W. M., Woodhouse, I. H., Silva, C. A., Omar, H., Abdul Maulud, K. N., Hudak, A. T., ... Mohan, M. (2018). Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data. Forests, 9(12), [759]. https://doi.org/10.3390/f9120759

Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data. / Jaafar, Wan Shafrina Wan Mohd; Woodhouse, Iain Hector; Silva, Carlos Alberto; Omar, Hamdan; Abdul Maulud, Khairul Nizam; Hudak, Andrew Thomas; Klauberg, Carine; Cardil, Adrián; Mohan, Midhun.

In: Forests, Vol. 9, No. 12, 759, 05.12.2018.

Research output: Contribution to journalArticle

Jaafar, WSWM, Woodhouse, IH, Silva, CA, Omar, H, Abdul Maulud, KN, Hudak, AT, Klauberg, C, Cardil, A & Mohan, M 2018, 'Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data', Forests, vol. 9, no. 12, 759. https://doi.org/10.3390/f9120759
Jaafar, Wan Shafrina Wan Mohd ; Woodhouse, Iain Hector ; Silva, Carlos Alberto ; Omar, Hamdan ; Abdul Maulud, Khairul Nizam ; Hudak, Andrew Thomas ; Klauberg, Carine ; Cardil, Adrián ; Mohan, Midhun. / Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data. In: Forests. 2018 ; Vol. 9, No. 12.
@article{bf7c3fca10444526b8c41ff0cc12c5c4,
title = "Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data",
abstract = "Individual tree crown (ITC) segmentation is an approach to isolate individual tree from the background vegetation and delineate precisely the crown boundaries for forest management and inventory purposes. ITC detection and delineation have been commonly generated from canopy height model (CHM) derived from light detection and ranging (LiDAR) data. Existing ITC segmentation methods, however, are limited in their efficiency for characterizing closed canopies, especially in tropical forests, due to the overlapping structure and irregular shape of tree crowns. Furthermore, the potential of 3-dimensional (3D) LiDAR data is not fully realized by existing CHM-based methods. Thus, the aim of this study was to develop an efficient framework for ITC segmentation in tropical forests using LiDAR-derived CHM and 3D point cloud data in order to accurately estimate tree attributes such as the tree height, mean crown width and aboveground biomass (AGB). The proposed framework entails five major steps: (1) automatically identifying dominant tree crowns by implementing semi-variogram statistics and morphological analysis; (2) generating initial tree segments using a watershed algorithm based on mathematical morphology; (3) identifying {"}problematic{"} segments based on predetermined set of rules; (4) tuning the problematic segments using a modified distance-based algorithm (DBA); and (5) segmenting and counting the number of individual trees based on the 3D LiDAR point clouds within each of the identified segment. This approach was developed in a way such that the 3D LiDAR points were only examined on problematic segments identified for further evaluations. 209 reference trees with diameter at breast height (DBH) ≥ 10 cm were selected in the field in two study areas in order to validate ITC detection and delineation results of the proposed framework. We computed tree crown metrics (e.g., maximum crown height and mean crown width) to estimate aboveground biomass (AGB) at tree level using previously published allometric equations. Accuracy assessment was performed to calculate percentage of correctly detected trees, omission and commission errors. Our method correctly identified individual tree crowns with detection accuracy exceeding 80 percent at both forest sites. Also, our results showed high agreement (R2 > 0.64) in terms of AGB estimates using 3D LiDAR metrics and variables measured in the field, for both sites. The findings from our study demonstrate the efficacy of the proposed framework in delineating tree crowns, even in high canopy density areas such as tropical rainforests, where, usually the traditional algorithms are limited in their performances. Moreover, the high tree delineation accuracy in the two study areas emphasizes the potential robustness and transferability of our approach to other densely forested areas across the globe.",
keywords = "3D LiDAR point cloud, Aboveground biomass (AGB), Canopy height model (CHM), Individual tree crown (ITC), LiDAR, Mathematical morphology, Tropical forest, Watershed",
author = "Jaafar, {Wan Shafrina Wan Mohd} and Woodhouse, {Iain Hector} and Silva, {Carlos Alberto} and Hamdan Omar and {Abdul Maulud}, {Khairul Nizam} and Hudak, {Andrew Thomas} and Carine Klauberg and Adri{\'a}n Cardil and Midhun Mohan",
year = "2018",
month = "12",
day = "5",
doi = "10.3390/f9120759",
language = "English",
volume = "9",
journal = "Forests",
issn = "1999-4907",
publisher = "MDPI AG",
number = "12",

}

TY - JOUR

T1 - Improving individual tree crown delineation and attributes estimation of tropical forests using airborne LiDAR data

AU - Jaafar, Wan Shafrina Wan Mohd

AU - Woodhouse, Iain Hector

AU - Silva, Carlos Alberto

AU - Omar, Hamdan

AU - Abdul Maulud, Khairul Nizam

AU - Hudak, Andrew Thomas

AU - Klauberg, Carine

AU - Cardil, Adrián

AU - Mohan, Midhun

PY - 2018/12/5

Y1 - 2018/12/5

N2 - Individual tree crown (ITC) segmentation is an approach to isolate individual tree from the background vegetation and delineate precisely the crown boundaries for forest management and inventory purposes. ITC detection and delineation have been commonly generated from canopy height model (CHM) derived from light detection and ranging (LiDAR) data. Existing ITC segmentation methods, however, are limited in their efficiency for characterizing closed canopies, especially in tropical forests, due to the overlapping structure and irregular shape of tree crowns. Furthermore, the potential of 3-dimensional (3D) LiDAR data is not fully realized by existing CHM-based methods. Thus, the aim of this study was to develop an efficient framework for ITC segmentation in tropical forests using LiDAR-derived CHM and 3D point cloud data in order to accurately estimate tree attributes such as the tree height, mean crown width and aboveground biomass (AGB). The proposed framework entails five major steps: (1) automatically identifying dominant tree crowns by implementing semi-variogram statistics and morphological analysis; (2) generating initial tree segments using a watershed algorithm based on mathematical morphology; (3) identifying "problematic" segments based on predetermined set of rules; (4) tuning the problematic segments using a modified distance-based algorithm (DBA); and (5) segmenting and counting the number of individual trees based on the 3D LiDAR point clouds within each of the identified segment. This approach was developed in a way such that the 3D LiDAR points were only examined on problematic segments identified for further evaluations. 209 reference trees with diameter at breast height (DBH) ≥ 10 cm were selected in the field in two study areas in order to validate ITC detection and delineation results of the proposed framework. We computed tree crown metrics (e.g., maximum crown height and mean crown width) to estimate aboveground biomass (AGB) at tree level using previously published allometric equations. Accuracy assessment was performed to calculate percentage of correctly detected trees, omission and commission errors. Our method correctly identified individual tree crowns with detection accuracy exceeding 80 percent at both forest sites. Also, our results showed high agreement (R2 > 0.64) in terms of AGB estimates using 3D LiDAR metrics and variables measured in the field, for both sites. The findings from our study demonstrate the efficacy of the proposed framework in delineating tree crowns, even in high canopy density areas such as tropical rainforests, where, usually the traditional algorithms are limited in their performances. Moreover, the high tree delineation accuracy in the two study areas emphasizes the potential robustness and transferability of our approach to other densely forested areas across the globe.

AB - Individual tree crown (ITC) segmentation is an approach to isolate individual tree from the background vegetation and delineate precisely the crown boundaries for forest management and inventory purposes. ITC detection and delineation have been commonly generated from canopy height model (CHM) derived from light detection and ranging (LiDAR) data. Existing ITC segmentation methods, however, are limited in their efficiency for characterizing closed canopies, especially in tropical forests, due to the overlapping structure and irregular shape of tree crowns. Furthermore, the potential of 3-dimensional (3D) LiDAR data is not fully realized by existing CHM-based methods. Thus, the aim of this study was to develop an efficient framework for ITC segmentation in tropical forests using LiDAR-derived CHM and 3D point cloud data in order to accurately estimate tree attributes such as the tree height, mean crown width and aboveground biomass (AGB). The proposed framework entails five major steps: (1) automatically identifying dominant tree crowns by implementing semi-variogram statistics and morphological analysis; (2) generating initial tree segments using a watershed algorithm based on mathematical morphology; (3) identifying "problematic" segments based on predetermined set of rules; (4) tuning the problematic segments using a modified distance-based algorithm (DBA); and (5) segmenting and counting the number of individual trees based on the 3D LiDAR point clouds within each of the identified segment. This approach was developed in a way such that the 3D LiDAR points were only examined on problematic segments identified for further evaluations. 209 reference trees with diameter at breast height (DBH) ≥ 10 cm were selected in the field in two study areas in order to validate ITC detection and delineation results of the proposed framework. We computed tree crown metrics (e.g., maximum crown height and mean crown width) to estimate aboveground biomass (AGB) at tree level using previously published allometric equations. Accuracy assessment was performed to calculate percentage of correctly detected trees, omission and commission errors. Our method correctly identified individual tree crowns with detection accuracy exceeding 80 percent at both forest sites. Also, our results showed high agreement (R2 > 0.64) in terms of AGB estimates using 3D LiDAR metrics and variables measured in the field, for both sites. The findings from our study demonstrate the efficacy of the proposed framework in delineating tree crowns, even in high canopy density areas such as tropical rainforests, where, usually the traditional algorithms are limited in their performances. Moreover, the high tree delineation accuracy in the two study areas emphasizes the potential robustness and transferability of our approach to other densely forested areas across the globe.

KW - 3D LiDAR point cloud

KW - Aboveground biomass (AGB)

KW - Canopy height model (CHM)

KW - Individual tree crown (ITC)

KW - LiDAR

KW - Mathematical morphology

KW - Tropical forest

KW - Watershed

UR - http://www.scopus.com/inward/record.url?scp=85058144186&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058144186&partnerID=8YFLogxK

U2 - 10.3390/f9120759

DO - 10.3390/f9120759

M3 - Article

AN - SCOPUS:85058144186

VL - 9

JO - Forests

JF - Forests

SN - 1999-4907

IS - 12

M1 - 759

ER -