Cookies Notification

We use cookies to improve your website experience. To learn about our use of cookies and how you can manage your cookie settings, please see our Cookie Policy.

Unsupervised algorithms to detect single trees in a mixed-species and multilayered Mediterranean forest using LiDAR data

Publication: Canadian Journal of Forest Research
14 June 2021


Accurate measurement of forest growing stock is a prerequisite for implementing climate-smart forestry strategies. This study deals with the use of airborne laser scanning data to assess carbon stock at the tree level. It aims to demonstrate that the combined use of two unsupervised techniques will improve the accuracy of estimation supporting sustainable forest management. Based on the heterogeneity of tree height and point cloud density, we classified 31 forest stands into four complexity categories. The point cloud of each stand was further divided into three horizontal layers, improving the accuracy of tree detection at tree level for which we calculated volume and carbon stock. The average accuracy of tree detection was 0.48. The accuracy was higher for forest stands with lower tree density and higher frequency of large trees, as well as a dense point cloud (0.65). The prediction of carbon stock was higher with a bias ranging from –0.3% to 1.5% and a root mean square error ranging from 0.14% to 1.48%.


La mesure précise du capital forestier en croissance est un prérequis à l’implantation de stratégies forestières intelligentes face au climat. Cette étude porte sur l’utilisation de données de balayage laser aéroporté pour évaluer le stock de carbone à l’échelle de l’arbre. Elle vise à démontrer que l’utilisation combinée de deux techniques non supervisées va améliorer la précision de l’estimation sur laquelle s’appuie un aménagement forestier durable. Sur la base de l’hétérogénéité de la hauteur des arbres et de la densité du nuage de points, nous avons classé 31 peuplements forestiers dans quatre catégories de complexité. Le nuage de points de chaque peuplement a par la suite été divisé en trois couches horizontales, ce qui améliore la précision de la détection de chacun des arbres pour lesquels nous avons calculé le volume et le stock de carbone. La précision moyenne de la détection des arbres était de 0,48. La précision était plus élevée pour les peuplements forestiers qui avaient une plus faible densité et une fréquence plus élevée de gros arbres, ainsi qu’un nuage de points dense (0,65). La prédiction du stock de carbone était plus élevée avec un biais allant de –0,3 à 1,5 % et un écart moyen quadratique (EMQ) entre 0,14 et 1,48 %. [Traduit par la Rédaction]

Get full access to this article

View all available purchase options and get full access to this article.


Ahmad P.H. and Dang S. 2015. Performance evaluation of clustering algorithm using different datasets. Int. J. Adv. Res. Comput. Sci. Manage. Stud. 8: 167–173. Available from [accessed 28 March 2021].
Allouis T., Durrieu S., Véga C., and Couteron P. 2013. Stem volume and above-ground biomass estimation of individual pine trees from LiDAR data: contribution of full-waveform signals. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 6(2): 924–934.
Antos, J. 2009. Understory plants in temperate forests. In Forests and forest plants. Department of Biology, University of Victoria, Victoria, BC. pp. 262–279.
Alberti G., Boscutti F., Pirotti F., Bertacco C., De Simon G., Sigura M., et al. 2013. A LiDAR-based approach for a multi-purpose characterization of Alpine forests: an Italian case study. iForest, 6(3): 156–168.
Balsi M., Esposito S., Fallavollita P., and Nardinocchi C. 2018. Single-tree detection in high-density LiDAR data from UAV-based survey. Eur. J. Remote Sens. 51(1): 679–692.
Barabesi L., Franceschi S., and Marcheselli M. 2012. Properties of design-based estimation under stratified spatial sampling with application to canopy coverage estimation. Ann. Appl. Stat. 6(1): 210–228.
Barbati A., Marchetti M., Chirici G., and Corona P. 2014. European Forest Types and Forest Europe SFM indicators: tools for monitoring progress on forest biodiversity conservation. For. Ecol. Manage. 321: 145–157.
Belgiu M. and Drăguţ L. 2016. Random forest in remote sensing: a review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 114: 24–31.
Biondi, E., Blasi, C., Burrascano, S., Casavecchia, S., Copiz, R., Del Vico, E., et al. 2010. Manuale italiano di interpretazione de- gli habitat (Direttiva 92/43/CEE) [Italian guidelines for habitat interpretation (Directive 92/43/CEE)]. MATTM. Available from [accessed 15 March 2021].
Bivand, R., and Rowlingson, B., 2016. Package ‘rgdal’. R Package. Available from [accessed 15 January 2019].
Bowditch E., Santopuoli G., Binder F., del Río M., La Porta N., Kluvankova T., et al. 2020. What is Climate-Smart Forestry? A definition from a multinational collaborative process focused on mountain regions of Europe. Ecosyst. Serv. 43(1): 101113–101113.
Breiman L. 2001. Random forests. Machine Learning, 45: 5–32.
Chirici G., Barbati A., Corona P., Marchetti M., Travaglini D., Maselli F., and Bertini R. 2008. Non-parametric and parametric methods using satellite images for estimating growing stock volume in alpine and Mediterranean forest ecosystems. Remote Sens. Environ. 112(5): 2686–2700.
Chirici G., McRoberts R.E., Fattorini L., Mura M., and Marchetti M. 2016. Comparing echo-based and canopy height model-based metrics for enhancing estimation of forest aboveground biomass in a model-assisted framework. Remote Sen. Environ. 174: 1–9.
Dalponte M., Reyes F., Kandare K., and Gianelle D. 2015. Delineation of individual tree crowns from ALS and hyperspectral data: a comparison among four methods. Eur. J. Remote Sens. 48(1): 365–382.
Duncanson L.I., Cook B.D., Hurtt G.C., and Dubayah R.O. 2014. An efficient, multi-layered crown delineation algorithm for mapping individual tree structure across multiple ecosystems. Remote Sens. Environ. 154: 378–386.
Ester M., Kriegel H.P., Sander J., and Xu X. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. KDD-96 Proc. 96(34): 226–231.
Federici S., Vitullo M., Tulipano S., De Lauretis R., and Seufert G. 2008. An approach to estimate carbon stocks change in forest carbon pools under the UNFCCC: the Italian case. iForest, 1(2): 86–95.
Ferrara R., Virdis S.G., Ventura A., Ghisu T., Duce P., and Pellizzaro G. 2018. An automated approach for wood-leaf separation from terrestrial LIDAR point clouds using the density based clustering algorithm DBSCAN. Agric. For. Meteorol. 262: 434–444.
Hahsler M., Piekenbrock M., and Doran D. 2019. dbscan: Fast density-based clustering with R. J. Stat. Soft. 91(1): 1–30.
Hamraz H., Contreras M.A., and Zhang J. 2017a. Forest understory trees can be segmented accurately using sufficiently dense airborne laser scanning point clouds. Sci. Rep. 7(1): 1–9.
Hamraz H., Contreras M.A., and Zhang J. 2017b. Vertical stratification of forest canopy for segmentation of understory trees within small-footprint airborne LiDAR point clouds. ISPRS J. Photogram. Remote Sens. 130: 385–392.
Hartigan J.A. and Wong M.A. 1979. Algorithm AS 136: a k-means clustering algorithm. J. R. Stat. Soc. Series C (Appl. Stat), 28(1): 100–108.
Jules M.J., Sawyer J.O., and Jules E.S. 2008. Assessing the relationships between stand development and understory vegetation using a 420-year chronosequence. For. Ecol. Manage. 255(7): 2384–2393.
Kandare, K., Dalponte, M., Gianelle, D., and Chan, J.C.W. 2014. A new procedure for identifying single trees in understory layer using discrete LiDAR data. In Proceedings of the 2014 IEEE Geoscience and Remote Sensing Symposium, Quebec City, Que., 13–18 July 2014. IEEE. pp. 1357–1360.
Kandare K., Ørka H.O., Chan J.C.W., and Dalponte M. 2016. Effects of forest structure and airborne laser scanning point cloud density on 3D delineation of individual tree crowns. Eur. J. Remote Sens. 49(1): 337–359.
Kwak, J. 2014. Akmeans: adaptive K-means algorithm based on threshold. R package version 1.1. Available from [accessed 15 October 2019].
Liang X., Hyyppä J., Kaartinen H., Lehtomäki M., Pyörälä J., Pfeifer N., et al. 2018. International benchmarking of terrestrial laser scanning approaches for forest inventories. ISPRS J. Photogram. Remote Sens. 144: 137–179.
Liang X., Wang Y., Pyörälä J., Lehtomäki M., Yu X., Kaartinen H., et al. 2019. Forest in situ observations using unmanned aerial vehicle as an alternative of terrestrial measurements. For. Ecosyst. 6(1): 1–16.
Liaw A. and Wiener M. 2002. Classification and regression by randomForest. R News, 2(3): 18–22. Available from [accessed 18 October 2020].
Lindner M. and Karjalainen T. 2007. Carbon inventory methods and carbon mitigation potentials of forests in Europe: a short review of recent progress. Eur. J. For. Res. 126(2): 149–156.
MacQueen, J. 1967. Some methods for classification and analysis of multivariate observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Statistical Laboratory University of California, Davis, Calif., 21 June – 18 July 1965, and 27 December 1965 – 7 January 1966. University of California Press, Berkeley, Calif. pp. 281–297.
Mongus D. and Žalik B. 2015. An efficient approach to 3D single tree-crown delineation in LiDAR data. ISPRS J. Photogram. Remote Sens. 108: 219–233.
Nabuurs, G.J., Verkerk, P.J., Schelhaas, M., González-Olabarria, J.R., Trasobares, A., and Cienciala, E. 2018. Climate-Smart Forestry: mitigation impact in three European regions. From Science to Policy 6. European Forest Institute, Joensuu, Finland. pp. 1–32.
Naimi, B., 2017. R package usdm: uncertainty analysis for species distribution models. Available from [accessed 18 October 2020].
Næsset E. 1997. Determination of mean tree height of forest stands using airborne laser scanner data. ISPRS J. Photogram. Remote Sens. 52(2): 49–56.
Popescu S.C. 2007. Estimating biomass of individual pine trees using airborne lidar. Biomass Bioenergy, 31(9): 646–655.
Sačkov I., Santopuoli G., Bucha T., Lasserre B., and Marchetti M. 2016. Forest inventory attribute prediction using lightweight aerial scanner data in a selected type of multilayered deciduous forest. Forests, 7(12): 307.
Sačkov I., Kulla L., and Bucha T. 2019. A comparison of two tree detection methods for estimation of forest stand and ecological variables from airborne LiDAR data in central European forests. Remote Sens. 11(12): 1431.
Santopuoli G., di Cristofaro M., Kraus D., Schuck A., Lasserre B., and Marchetti M. 2019. Biodiversity conservation and wood production in a Natura 2000 Mediterranean forest. A trade-off evaluation focused on the occurrence of microhabitats. iForest, 12(1): 76–84.
Santopuoli G., Di Febbraro M., Maesano M., Balsi M., Marchetti M., and Lasserre B. 2020. Machine learning algorithms to predict tree-related microhabitats using airborne laser scanning. Remote Sens. 12: 2142.
Santopuoli G., Temperli C., Alberdi I., Barbeito I., Bosela M., Bottero A., et al. 2021. Pan-European sustainable forest management indicators for assessing Climate-Smart Forestry in Europe. Can. J. For. Res. [This issue.].
Shao G., Shao G., and Fei S. 2019. Delineation of individual deciduous trees in plantations with low-density LiDAR data. Int. J. Remote Sens. 40(1): 346–363.
Shi Y., Wang T., Skidmore A.K., and Heurich M. 2018. Important LiDAR metrics for discriminating forest tree species in Central Europe. ISPRS J. Photogram. Remote Sens. 137: 163–174.
Silva, C.A., Crookston, N.L., Hudak, A.T., and Vierling, L.A., 2015. rLiDAR: an R package for reading, processing and visualizing LiDAR (Light Detection and Ranging) data. Available from [accessed 15 January 2019].
Smits I., Prieditis G., Dagis S., and Dubrovskis D. 2012. Individual tree identification using different LIDAR and optical imagery data processing methods. Biosyst. Inf. Technol. 1: 19–24.
SoEF. 2020. Summary for Policy Markers: State of Europe’s Forest 2020 (SoEF 2020). Vol. 4. Ministerial Conference on the Protection of Forests in Europe – FOREST EUROPE Liaison Unit Bratislava, Zvolen, Slovak Republic. pp. 64–75.
Tabacchi G., Di Cosmo L., and Gasparini P. 2011. Aboveground tree volume and phytomass prediction equations for forest species in Italy. Eur. J. For. Res. 130(6): 911–934.
Torresan C., Carotenuto F., Chiavetta U., Miglietta F., Zaldei A., and Gioli B. 2020. Individual tree crown segmentation in two-layered dense mixed forests from UAV LiDAR data. Drones, 4(2): 10.
Torresan C., Benito Garzón M., O’Grady M., Robson T.M., Picchi G., Panzacchi P., et al. 2021. A new generation of sensors and monitoring tools to support climate-smart forestry practices. Can. J. For. Res. [This issue.].
Wang Y., Lehtomäki M., Liang X., Pyörälä J., Kukko A., Jaakkola A., et al. 2019a. Is field-measured tree height as reliable as believed – A comparison study of tree height estimates from field measurement, airborne laser scanning and terrestrial laser scanning in a boreal forest. ISPRS J. Photogram. Remote Sens. 147: 132–145.
Wang Y., Pyörälä J., Liang X., Lehtomäki M., Kukko A., Yu X., et al. 2019b. In situ biomass estimation at tree and plot levels: What did data record and what did algorithms derive from terrestrial and aerial point clouds in boreal forest. Remote Sens. Environ. 232: 111309–111315.
White J.C., Wulder M.A., and Buckmaster G. 2014. Validating estimates of merchantable volume from airborne laser scanning (ALS) data using weight scale data. For. Chron. 90(3): 378–385.
Williams J., Schönlieb C.B., Swinfield T., Lee J., Cai X., Qie L., and Coomes D.A. 2020. Three-dimensional segmentation of trees through a flexible Multi-Class Graph Cut algorithm (MCGC). IEEE Trans. Geosci. Remote Sens. 58: 754–776.
Yu X., Hyyppä J., Holopainen M., and Vastaranta M. 2010. Comparison of area-based and individual tree-based methods for predicting plot-level forest attributes. Remote Sens. 2(6): 1481–1495.

Information & Authors


Published In

cover image Canadian Journal of Forest Research
Canadian Journal of Forest Research
Volume 51Number 12December 2021
Pages: 1766 - 1780


Received: 1 December 2020
Accepted: 5 June 2021
Accepted manuscript online: 14 June 2021
Version of record online: 14 June 2021


Request permissions for this article.

Key Words

  1. tree detection
  2. airborne laser scanning (ALS)
  3. forest structure
  4. carbon stock
  5. climate-smart forestry


  1. détection des arbres
  2. balayage laser aéroporté (BLA)
  3. structure de la forêt
  4. stock de carbone
  5. foresterie intelligente face au climat



Cesar Alvites [email protected]
Dipartimento di Bioscienze e Territorio, Università degli Studi del Molise, Cda Fonte Lappone snc, Pesche (IS) 86090, Italy.
Giovanni Santopuoli
Dipartimento di Agricoltura, Ambiente e Alimenti, Università degli Studi del Molise, Via De Sanctis snc, Campobasso 86100, Italy.
Centro di Ricerca per le Aree Interne e gli Appennini (ArIA), Università degli Studi del Molise, Via De Sanctis snc, Campobasso 86100, Italy.
Mauro Maesano
Department of Innovation in Biological, Agro-food and Forest Systems, University of Tuscia, Viterbo 01100, Italy.
Gherardo Chirici
Dipartimento di Scienze e Tecnologie Agrarie, Alimentari, Ambientali e Forestali, Università degli Studi di Firenze, Via San Bonaventura 13, Firenze 50145, Italy.
Federico Valerio Moresi
Department of Innovation in Biological, Agro-food and Forest Systems, University of Tuscia, Viterbo 01100, Italy.
Roberto Tognetti
Dipartimento di Agricoltura, Ambiente e Alimenti, Università degli Studi del Molise, Via De Sanctis snc, Campobasso 86100, Italy.
Centro di Ricerca per le Aree Interne e gli Appennini (ArIA), Università degli Studi del Molise, Via De Sanctis snc, Campobasso 86100, Italy.
Marco Marchetti
Dipartimento di Bioscienze e Territorio, Università degli Studi del Molise, Cda Fonte Lappone snc, Pesche (IS) 86090, Italy.
Centro di Ricerca per le Aree Interne e gli Appennini (ArIA), Università degli Studi del Molise, Via De Sanctis snc, Campobasso 86100, Italy.
Bruno Lasserre
Dipartimento di Bioscienze e Territorio, Università degli Studi del Molise, Cda Fonte Lappone snc, Pesche (IS) 86090, Italy.


This Article is part of a collection of papers presented at the CLImate-Smart Forestry in MOuntain Regions (CLIMO) workshop held in Stará Lesná, Slovakia, 9–11 September 2019.

Metrics & Citations


Other Metrics


Cite As

Export Citations

If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.

Cited by

1. Automatic Filtering and Classification of Low-Density Airborne Laser Scanner Clouds in Shrubland Environments
2. LiDAR as a Tool for Assessing Timber Assortments: A Systematic Literature Review
3. Linking crown structure with tree ring pattern: methodological considerations and proof of concept
4. Some options for Climate-Smart Forestry in Europe’s mountain regions

View Options

Get Access

Login options

Check if you access through your login credentials or your institution to get full access on this article.


Click on the button below to subscribe to Canadian Journal of Forest Research

Purchase options

Purchase this article to get full access to it.

Restore your content access

Enter your email address to restore your content access:

Note: This functionality works only for purchases done as a guest. If you already have an account, log in to access the content to which you are entitled.

View options


View PDF

Full Text

View Full Text





Share Options


Share the article link

Share on social media