A Comparative Assessment of the Performance of Individual Tree Crowns Delineation Algorithms from ALS Data in Tropical Forests
<p>Example of manual segmentation of some crowns. (<b>a</b>) CHM based on the ALS, (<b>b</b>) hyperspectral image, (<b>c</b>) high-resolution photography, and (<b>d</b>) manual segmentation of crowns.</p> "> Figure 2
<p>Hierarchical structure of the allometric model for DBH.</p> "> Figure 3
<p>Histogram of the distance rank of the associated tree for each crown of the reference data.</p> "> Figure 4
<p>Segmentation of one plot (number 11) with the six different methods. (<b>a</b>) Graph-Cut, (<b>b</b>) E-cognition, (<b>c</b>) itcSegment, (<b>d</b>) Profiler, (<b>e</b>) SEGMA, (<b>f</b>) AMS3D.</p> "> Figure 5
<p>Crowns area (m<sup>2</sup>) and crowns height (m) for the crowns segmented with the six different methods, and for the manually segmented crowns from the reference dataset. (<b>a</b>) Graph-Cut, (<b>b</b>) E-cognition, (<b>c</b>) ITCSegment, (<b>d</b>) Profiler, (<b>e</b>) SEGMA, (<b>f</b>) AMS3D, (<b>g</b>) Reference dataset.</p> "> Figure 6
<p>Error of the pairing algorithm: difference between the DBH of the corresponding stem and the tree paired with the pairing algorithm, for the 24% crowns that have not been assigned to the right stem. 1:1 line in red.</p> "> Figure 7
<p>RMSE for the allometric model depends on the tree DBH (in cm). <b>Left</b>: the RMSE is computed for bins of 100 pairs (tree from the inventories—segmented crowns), ordered by increasing DBH. <b>Right</b>: the cumulative RMSE is computed for bins of 100 pairs, ordered by decreasing DBH and plotted against the number of trees. The vertical grey line corresponds to 5000 pairs, the threshold used in <a href="#remotesensing-11-01086-t006" class="html-table">Table 6</a>.</p> "> Figure 8
<p>Density distribution of diameters for all trees with DBH >10 cm in the six plots (red) and only for trees associated with a crown from the reference dataset (blue).</p> "> Figure 9
<p>Segmentation of one crown and the neighboring crowns with the six different methods investigated in this benchmark. (<b>a</b>) Graph-Cut, (<b>b</b>) E-cognition, (<b>c</b>) ITCSegment, (<b>d</b>) Profiler, (<b>e</b>) SEGMA, (<b>f</b>) AMS3D. The neighboring crowns are chosen if a least one point of the crown is less than 10 m far from the central crown mean position on the XY plan. Figure realized with the package lidR [<a href="#B40-remotesensing-11-01086" class="html-bibr">40</a>,<a href="#B46-remotesensing-11-01086" class="html-bibr">46</a>].</p> "> Figure A1
<p>Number of crowns segmented in each plots for each algorithm, total number of stems with DBH ≥ 10 cm from the inventories.</p> "> Figure A2
<p>Segmentation of one crown from an emergent tree with the six different methods. All methods except SEGMA over-segment the crown. For the two methods using the point cloud (AMS3D and Graph-Cut), one polygon was plotted in red and the rest left in black (thin lines) to facilitate the reading of the figure. (<b>a</b>) Graph-Cut, (<b>b</b>) E-cognition, (<b>c</b>) itcSegment, (<b>d</b>) Profiler, (<b>e</b>) SEGMA, (<b>f</b>) AMS3D.</p> "> Figure A3
<p>Segmentation of one crown partially covered by another crown, with the two methods using the point cloud. <b>left</b>: AMS3D, <b>right</b>: Graph-Cut.</p> ">
Abstract
:1. Introduction
2. Materials and Methods
2.1. Study Site and Data
2.1.1. Experimental Site
2.1.2. Remote Sensing Data
2.1.3. Tree Inventory
2.1.4. Validation Dataset
2.2. ITC Delineation Algorithms
2.2.1. AMS3D
2.2.2. itcSegment
2.2.3. Graph-Cut
2.2.4. Profiler
2.2.5. SEGMA: Therefore, Computree Version
2.2.6. E-Cognition
2.3. Congruence Analysis
2.4. Paired-Trees Analysis
3. Results
3.1. Segmentation Results
3.2. Congruence Analysis
3.3. Paired Tree Validation
4. Discussion
5. Conclusions
Author Contributions
Funding
Conflicts of Interest
Abbreviations
ALS | Airborne Laser Scanning |
TLS | Terrestrial Laser Scanning |
ITC | Individual Tree Crown |
CHM | Canopy Height Model |
AGB | aboveground biomass |
Appendix A. Number of Crowns Segmented
Appendix B. Segmentation Examples
References
- Larjavaara, M.; Muller-Landau, H.C. Measuring tree height: A quantitative comparison of two common field methods in a moist tropical forest. Methods Ecol. Evol. 2013, 4, 793–801. [Google Scholar] [CrossRef]
- Coomes, D.A.; Dalponte, M.; Jucker, T.; Asner, G.P.; Banin, L.F.; Burslem, D.F.; Lewis, S.L.; Nilus, R.; Phillips, O.L.; Phua, M.H.; et al. Area-based vs tree-centric approaches to mapping forest carbon in Southeast Asian forests from airborne laser scanning data. Remote Sens. Environ. 2017, 194, 77–88. [Google Scholar] [CrossRef] [Green Version]
- Ferraz, A.; Saatchi, S.; Mallet, C.; Meyer, V. Lidar detection of individual tree size in tropical forests. Remote Sens. Environ. 2016, 183, 318–333. [Google Scholar] [CrossRef]
- Dalponte, M.; Coomes, D.A. Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data. Methods Ecol. Evol. 2016, 7, 1236–1245. [Google Scholar] [CrossRef] [PubMed]
- Wagner, F.H.; Ferreira, M.P.; Sanchez, A.; Hirye, M.C.; Zortea, M.; Gloor, E.; Phillips, O.L.; de Souza Filho, C.R.; Shimabukuro, Y.E.; Aragão, L.E. Individual tree crown delineation in a highly diverse tropical forest using very high resolution satellite images. ISPRS J. Photogramm. Remote Sens. 2018, 145, 362–377. [Google Scholar] [CrossRef]
- Popescu, S.C.; Wynne, R.H.; Nelson, R.F. Estimating plot-level tree heights with lidar: Local filtering with a canopy-height based variable window size. Comput. Electron. Agric. 2002, 37, 71–95. [Google Scholar] [CrossRef]
- Reitberger, J.; Schnörr, C.; Krzystek, P.; Stilla, U. 3D segmentation of single trees exploiting full waveform LIDAR data. ISPRS J. Photogramm. Remote Sens. 2009, 64, 561–574. [Google Scholar] [CrossRef]
- Falkowski, M.J.; Smith, A.M.; Hudak, A.T.; Gessler, P.E.; Vierling, L.A.; Crookston, N.L. Automated estimation of individual conifer tree height and crown diameter via two-dimensional spatial wavelet analysis of lidar data. Can. J. Remote Sens. 2006, 32, 153–161. [Google Scholar] [CrossRef]
- Vega, C.; Hamrouni, A.; El Mokhtari, A.; Morel, M.; Bock, J.; Renaud, J.P.; Bouvier, M.; Durrieue, S. PTrees: A point-based approach to forest tree extractionfrom lidar data. Int. J. Appl. Earth Obs. Geoinf. 2014, 33, 98–108. [Google Scholar] [CrossRef]
- Mongus, D.; Žalik, B. An efficient approach to 3D single tree-crown delineation in LiDAR data. ISPRS J. Photogramm. Remote Sens. 2015, 108, 219–233. [Google Scholar] [CrossRef]
- Holmgren, J.; Lindberg, E. Tree crown segmentation based on a geometric tree crown model for prediction of forest variables. Can. J. Remote Sens. 2013, 39, 86–98. [Google Scholar] [CrossRef]
- Morsdorf, F.; Meier, E.; Kötz, B.; Itten, K.I.; Dobbertin, M.; Allgöwer, B. LIDAR-based geometric reconstruction of boreal type forest stands at single tree level for forest and wildland fire management. Remote Sens. Environ. 2004, 92, 353–362. [Google Scholar] [CrossRef]
- Heurich, M. Automatic recognition and measurement of single trees based on data from airborne laser scanning over the richly structured natural forests of the Bavarian Forest National Park. For. Ecol. Manag. 2008, 255, 2416–2433. [Google Scholar] [CrossRef]
- Koch, B.; Heyder, U.; Weinacker, H. Detection of Individual Tree Crowns in Airborne Lidar Data. Photogramm. Eng. Remote Sens. 2006, 72, 357–363. [Google Scholar] [CrossRef]
- Clark, M.L.; Roberts, D.A.; Clark, D.B. Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales. Remote Sens. Environ. 2005, 96, 375–398. [Google Scholar] [CrossRef]
- Feret, J.B.; Asner, G.P. Tree species discrimination in tropical forests using airborne imaging spectroscopy. IEEE Trans. Geosci. Remote Sens. 2013, 51, 73–84. [Google Scholar] [CrossRef]
- Fassnacht, F.E.; Latifi, H.; Stereńczak, K.; Modzelewska, A.; Lefsky, M.; Waser, L.T.; Straub, C.; Ghosh, A. Review of studies on tree species classification from remotely sensed data. Remote Sens. Environ. 2016, 186, 64–87. [Google Scholar] [CrossRef]
- Ferreira, M.P.; Zortea, M.; Zanotta, D.C.; Shimabukuro, Y.E.; de Souza Filho, C.R. Mapping tree species in tropical seasonal semi-deciduous forests with hyperspectral and multispectral data. Remote Sens. Environ. 2016, 179, 66–78. [Google Scholar] [CrossRef]
- Laybros, A.; Schläpfer, D.; Féret, J.B.; Descroix, L.; Bedeau, C.; Lefevre, M.J.; Vincent, G. Across Date Species Detection Using Airborne Imaging Spectroscopy. Remote Sens. 2019, 11, 789. [Google Scholar] [CrossRef]
- Paris, C.; Valduga, D.; Bruzzone, L. A Hierarchical Approach to Three-Dimensional Segmentation of LiDAR Data at Single-Tree Level in a Multilayered Forest. IEEE Trans. Geosci. Remote Sensing 2016, 54, 4190–4203. [Google Scholar] [CrossRef]
- Duncanson, L.I.; Cook, B.D.; Hurtt, G.C.; Dubayah, R.O. An efficient, multi-layered crown delineation algorithm for mapping individual tree structure across multiple ecosystems. Remote Sens. Environ. 2014, 154, 378–386. [Google Scholar] [CrossRef]
- Kaartinen, H.; Hyyppä, J.; Yu, X.; Vastaranta, M.; Hyyppä, H.; Kukko, A.; Holopainen, M.; Heipke, C.; Hirschmugl, M.; Morsdorf, F.; et al. An international comparison of individual tree detection and extraction using airborne laser scanning. Remote Sens. 2012, 4, 950–974. [Google Scholar] [CrossRef]
- Eysn, L.; Hollaus, M.; Lindberg, E.; Berger, F.; Monnet, J.M.; Dalponte, M.; Kobal, M.; Pellegrini, M.; Lingua, E.; Mongus, D.; et al. A benchmark of lidar-based single tree detection methods using heterogeneous forest data from the Alpine Space. Forests 2015, 6, 1721–1747. [Google Scholar] [CrossRef]
- Larsen, M.; Eriksson, M.; Descombes, X.; Perrin, G.; Brandtberg, T.; Gougeon, F.A. Comparison of six individual tree crown detection algorithms evaluated under varying forest conditions. Int. J. Remote Sens. 2011, 32, 5827–5852. [Google Scholar] [CrossRef]
- Vauhkonen, J.; Ene, L.; Gupta, S.; Heinzel, J.; Holmgren, J.; Pitkänen, J.; Solberg, S.; Wang, Y.; Weinacker, H.; Hauglin, K.M.; et al. Comparative testing of single-tree detection algorithms under different types of forest. Forestry 2012, 85, 27–40. [Google Scholar] [CrossRef]
- Gourlet-Fleury, S.; Guehl, J.; Laroussinie, O. Ecology and Management of a Neotropical Rainforest: Lessons Drawn from Paracou, a Long-Term Experimental Research Site in French Guiana; Elsevier: Amsterdam, The Netherlands, 2004; Volume 380. [Google Scholar]
- Valbuena, R.; Mauro, F.; Arjonilla, F.J.; Manzanera, J.A. Comparing airborne laser scanning-imagery fusion methods based on geometric accuracy in forested areas. Remote Sens. Environ. 2011, 115, 1942–1954. [Google Scholar] [CrossRef]
- Blaschke, T. Object based image analysis for remote sensing. ISPRS J. Photogramm. Remote Sens. 2010, 65, 2–16. [Google Scholar] [CrossRef] [Green Version]
- Ferraz, A.; Bretar, F.; Jacquemoud, S.; Gonçalves, G.; Pereira, L.; Tomé, M.; Soares, P. 3-D mapping of a multi-layered Mediterranean forest using ALS data. Remote Sens. Environ. 2012, 121, 210–223. [Google Scholar] [CrossRef]
- Williams, J.; Schönlieb, C.B.; Swinfield, T.; Lee, J.; Cai, X.; Qie, L.; Coomes, D.A. Three-dimensional Segmentation of Trees Through a Flexible Multi-Class Graph Cut Algorithm (MCGC). arXiv 2019, arXiv:1903.08481. [Google Scholar]
- Hamraz, H.; Contreras, M.A.; Zhang, J. A robust approach for tree segmentation in deciduous forests using small-footprint airborne LiDAR data. Int. J. Appl. Earth Obs. Geoinf. 2016, 52, 532–541. [Google Scholar] [CrossRef] [Green Version]
- Hamraz, H.; Contreras, M.A.; Zhang, J. Vertical stratification of forest canopy for segmentation of understory trees within small-footprint airborne LiDAR point clouds. ISPRS J. Photogramm. Remote Sens. 2017, 130, 385–392. [Google Scholar] [CrossRef] [Green Version]
- St-Onge, B.; Audet, F.A.; Bégin, J. Characterizing the height structure and composition of a boreal forest using an individual tree crown approach applied to photogrammetric point clouds. Forests 2015, 6, 3899–3922. [Google Scholar] [CrossRef]
- Dalponte, M. itcSegment: Individual Tree Crowns Segmentation. R Package Version 0.8. 2018. Available online: https://rdrr.io/cran/itcSegment/ (accessed on 6 May 2019).
- Baatz, M.; Schape, A. Multiresolution Segmentation: An Optimization Approach for High Quality Multi-Scale Image Segmentation; Angewandte Geographische Informations-Verarbeitung, Wichmann-Verlag: Heidelberg, Germany, 2000; pp. 12–23. [Google Scholar]
- Jucker, T.; Caspersen, J.; Chave, J.; Antin, C.; Barbier, N.; Bongers, F.; Dalponte, M.; van Ewijk, K.Y.; Forrester, D.I.; Haeni, M.; et al. Allometric equations for integrating remote sensing imagery into forest monitoring programmes. Glob. Chang. Biol. 2017, 23, 177–190. [Google Scholar] [CrossRef]
- Dalponte, M.; Frizzera, L.; Ørka, H.O.; Gobakken, T.; Næsset, E.; Gianelle, D. Predicting stem diameters and aboveground biomass of individual trees using remote sensing data. Ecol. Indic. 2018, 85, 367–376. [Google Scholar] [CrossRef]
- Spiegelhalter, D.J.; Best, N.G.; Carlin, B.P.; van der Line, A. The deviance information criterion: 12 years on. J. R. Stat. Soc. Ser. B Stat. Methodol. 2014, 76, 485–493. [Google Scholar] [CrossRef]
- Su, Y.S.; Yajima, M. R2jags: Using R to Run ‘JAGS’. R package version 0.5-7. 2015. Available online: https://cran.r-project.org/web/packages/R2jags/R2jags.pdf (accessed on 6 May 2019).
- R Core Team. R: A Language and Environment for Statistical Computing; R Foundation for Statistical Computing: Vienna, Austria, 2018. [Google Scholar]
- Hijmans, R.J. Raster: Geographic Data Analysis and Modeling. R Package Version 2.8-4. 2018. Available online: https://rdrr.io/cran/raster/ (accessed on 6 May 2019).
- Bivand, R.; Keitt, T.; Rowlingson, B. Rgdal: Bindings for the ‘Geospatial’ Data Abstraction Library. R Package Version 1.3-6. 2018. Available online: https://rdrr.io/cran/rgdal/ (accessed on 6 May 2019).
- Bivand, R.; Rundel, C. Rgeos: Interface to Geometry Engine—Open Source (‘GEOS’). R Package Version 0.4-2. 2018. Available online: https://rdrr.io/cran/rgeos/ (accessed on 6 May 2019).
- Kwak, D.A.; Lee, W.K.; Lee, J.H.; Biging, G.S.; Gong, P. Detection of individual trees and estimation of tree height using LiDAR data. J. For. Res. 2007, 12, 425–434. [Google Scholar] [CrossRef]
- Rahman, M.Z.A.; Grote, B.G.H. Tree Crown Delineation from High Resolution Airborne Lidar Based on Densities of High Points. In Proceedings of the ISPRS Workshop Laserscanning 2009, Paris, France, 1–2 September 2009; pp. 123–128. [Google Scholar]
- Roussel, J.R.; Auty, D. lidR: Airborne LiDAR Data Manipulation and Visualization for Forestry Applications. R Package Version 1.6.1. 2018. Available online: https://rdrr.io/cran/lidR/ (accessed on 6 May 2019).
- Wang, Y.; Hyyppä, J.; Liang, X.; Kaartinen, H.; Yu, X.; Lindberg, E.; Holmgren, J.; Qin, Y.; Mallet, C.; Ferraz, A.; et al. International Benchmarking of the Individual Tree Detection Methods for Modeling 3-D Canopy Structure for Silviculture and Forest Ecology Using Airborne Laser Scanning. IEEE Trans. Geosci. Remote Sens. 2016, 54, 5011–5027. [Google Scholar] [CrossRef]
- Burt, A.; Disney, M.; Calders, K. Extracting individual trees from lidar point clouds using treeseg. Methods Ecol. Evol. 2017, 10, 438–445. [Google Scholar] [CrossRef]
- Bastin, J.F.; Barbier, N.; Réjou-Méchain, M.; Fayolle, A.; Gourlet-Fleury, S.; Maniatis, D.; De Haulleville, T.; Baya, F.; Beeckman, H.; Beina, D.; et al. Seeing Central African forests through their largest trees. Sci. Rep. 2015, 5, 13156. [Google Scholar] [CrossRef] [Green Version]
- Dai, W.; Yang, B.; Dong, Z.; Shaker, A. A new method for 3D individual tree extraction using multispectral airborne LiDAR point clouds. ISPRS J. Photogramm. Remote Sens. 2018, 144, 400–411. [Google Scholar] [CrossRef]
- McRoberts, R.E.; Næsset, E.; Gobakken, T.; Bollandsås, O.M. Indirect and direct estimation of forest biomass change using forest inventory and airborne laser scanning data. Remote Sens. Environ. 2015, 164, 36–42. [Google Scholar] [CrossRef]
- Shendryk, I.; Broich, M.; Tulbure, M.G.; Alexandrov, S.V. Bottom-up delineation of individual trees from full-waveform airborne laser scans in a structurally complex eucalypt forest. Remote Sens. Environ. 2016, 173, 69–83. [Google Scholar] [CrossRef]
- Tusa, E.; Laybros, A.; Monnet, J.M.; Dalla, M. Fusion of Hyperspectral Imaging and LiDAR for Forest Monitoring. 2018. Available online: https://bit.ly/2LrEm8X (accessed on 6 May 2019).
- Torabzadeh, H.; Morsdorf, F.; Schaepman, M.E. Fusion of imaging spectroscopy and airborne laser scanning data for characterization of forest ecosystems—A review. ISPRS J. Photogramm. Remote Sens. 2014, 97, 25–35. [Google Scholar] [CrossRef]
- Asner, G.P.; Mascaro, J. Mapping tropical forest carbon: Calibrating plot estimates to a simple LiDAR metric. Remote Sens. Environ. 2014, 140, 614–624. [Google Scholar] [CrossRef]
Plot Number | Number of Trees | DBH Median (cm) | DBH 95% (cm) | DBH 99% (cm) | Canopy Cover | Management | Mean Point Density (point·m−2) |
---|---|---|---|---|---|---|---|
4 | 4502 | 16.5 | 39.6 | 51.2 | 98.5% | treatment 2 | 55 |
7 | 3757 | 17.7 | 49 | 66.5 | 98.2% | treatment 1 | 59 |
8 | 4347 | 16.5 | 39.1 | 50.9 | 98.5% | treatment 2 | 57 |
9 | 4005 | 17.2 | 44.1 | 57.9 | 98% | treatment 1 | 64 |
11 | 3986 | 17.3 | 47.4 | 65.6 | 97.7% | control | 72 |
15 | 4091 | 17 | 48.2 | 65.4 | 98.3% | control | 112 |
Name | Description | Team | References |
---|---|---|---|
AMS3D | Adaptative mean-shift on the point cloud | A.F. | [3,29] |
itcSegment | Maxima finding and region growing on the CHM | J.W. & D.A.C. | [4] |
Graph-Cut | Graph cut on the point cloud | J.W. & D.A.C. | [30] |
Profiler | Maxima finding and watershed on the point cloud | H.H. | [31,32] |
SEGMA | Maxima finding and watershed on the CHM | A.P. | [33] |
Level of Taxonomic Information | No Information | Family | Genus | Species |
---|---|---|---|---|
DIC | 16,264 | 15,924 | 15,573 | 15,502 |
Algorithm | Mean Number of Crowns per Plot | Mean Area of a Crown (m2) | Area of Plots Segmented | % of Crowns Segmented Paired with a Stem |
---|---|---|---|---|
AMS3D | 2564 | 32.46 | 91% | 37% |
SEGMA | 837 | 53.12 | 65% | 87% |
E-cognition | 1435 | 40.40 | 86% | 61% |
Graph-Cut | 1832 | 34.38 | 66% | 82% |
itcSegment | 1353 | 43.86 | 88% | 86% |
Profiler | 936 | 71.17 | 97% | 88% |
Algorithm | Crowns with a Match (Jaccard Index ) | Mean Jaccard Index | Crowns with a Match, Under-Segmentation | Crowns with a Match, Over-Segmentation |
---|---|---|---|---|
AMS3D | 73.8% | 71.4% | 76.0% | 93.7% |
E-cognition | 59.1% | 67.1% | 63.6 % | 74.0% |
SEGMA | 55.4% | 67.5% | 68.4% | 61.4% |
Graph-Cut | 54.3% | 69.1% | 56.3% | 71.0% |
itcSegment | 43.8% | 64.9% | 46.8% | 67.3% |
Profiler | 30.5% | 60.3% | 38.1% | 39.4% |
AMS3D | SEGMA | Graph-Cut | itcSegment | E-Cognition | Profiler | |
---|---|---|---|---|---|---|
RMSE | 7.67 | 9.02 | 7.64 | 7.75 | 10.91 | 9.47 |
RMSE 40% | 3.58 | 4.70 | 3.58 | 3.97 | 5.33 | 4.24 |
RMSE ref | 8.92 (63%) | 8.86 (60%) | 9.33 (67%) | 8.67 (63%) | 12.92 (42%) | 8.41 (62%) |
© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
Share and Cite
Aubry-Kientz, M.; Dutrieux, R.; Ferraz, A.; Saatchi, S.; Hamraz, H.; Williams, J.; Coomes, D.; Piboule, A.; Vincent, G. A Comparative Assessment of the Performance of Individual Tree Crowns Delineation Algorithms from ALS Data in Tropical Forests. Remote Sens. 2019, 11, 1086. https://doi.org/10.3390/rs11091086
Aubry-Kientz M, Dutrieux R, Ferraz A, Saatchi S, Hamraz H, Williams J, Coomes D, Piboule A, Vincent G. A Comparative Assessment of the Performance of Individual Tree Crowns Delineation Algorithms from ALS Data in Tropical Forests. Remote Sensing. 2019; 11(9):1086. https://doi.org/10.3390/rs11091086
Chicago/Turabian StyleAubry-Kientz, Mélaine, Raphaël Dutrieux, Antonio Ferraz, Sassan Saatchi, Hamid Hamraz, Jonathan Williams, David Coomes, Alexandre Piboule, and Grégoire Vincent. 2019. "A Comparative Assessment of the Performance of Individual Tree Crowns Delineation Algorithms from ALS Data in Tropical Forests" Remote Sensing 11, no. 9: 1086. https://doi.org/10.3390/rs11091086