{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T14:58:46Z","timestamp":1773413926745,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"8","license":[{"start":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T00:00:00Z","timestamp":1617753600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"ARC Training Centre for Forest Value","award":["IC150100004"],"award-info":[{"award-number":["IC150100004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Forest inventories play an important role in enabling informed decisions to be made for the management and conservation of forest resources; however, the process of collecting inventory information is laborious. Despite advancements in mapping technologies allowing forests to be digitized in finer granularity than ever before, it is still common for forest measurements to be collected using simple tools such as calipers, measuring tapes, and hypsometers. Dense understory vegetation and complex forest structures can present substantial challenges to point cloud processing tools, often leading to erroneous measurements, and making them of less utility in complex forests. To address this challenge, this research demonstrates an effective deep learning approach for semantically segmenting high-resolution forest point clouds from multiple different sensing systems in diverse forest conditions. Seven diverse point cloud datasets were manually segmented to train and evaluate this model, resulting in per-class segmentation accuracies of Terrain: 95.92%, Vegetation: 96.02%, Coarse Woody Debris: 54.98%, and Stem: 96.09%. By exploiting the segmented point cloud, we also present a method of extracting a Digital Terrain Model (DTM) from such segmented point clouds. This approach was applied to a set of six point clouds that were made publicly available as part of a benchmarking study to evaluate the DTM performance. The mean DTM error was 0.04 m relative to the reference with 99.9% completeness. These approaches serve as useful steps toward a fully automated and reliable measurement extraction tool, agnostic to the sensing technology used or the complexity of the forest, provided that the point cloud has sufficient coverage and accuracy. Ongoing work will see these models incorporated into a fully automated forest measurement tool for the extraction of structural metrics for applications in forestry, conservation, and research.<\/jats:p>","DOI":"10.3390\/rs13081413","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T11:31:59Z","timestamp":1617795119000},"page":"1413","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":75,"title":["Sensor Agnostic Semantic Segmentation of Structurally Diverse and Complex Forest Point Clouds Using Deep Learning"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0689-0051","authenticated-orcid":false,"given":"Sean","family":"Krisanski","sequence":"first","affiliation":[{"name":"ARC Training Centre for Forest Value, University of Tasmania, Churchill Ave., Hobart, TAS 7005, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9871-361X","authenticated-orcid":false,"given":"Mohammad Sadegh","family":"Taskhiri","sequence":"additional","affiliation":[{"name":"ARC Training Centre for Forest Value, University of Tasmania, Churchill Ave., Hobart, TAS 7005, Australia"}]},{"given":"Susana","family":"Gonzalez Aracil","sequence":"additional","affiliation":[{"name":"Interpine Group Ltd., Rotorua 3010, New Zealand"}]},{"given":"David","family":"Herries","sequence":"additional","affiliation":[{"name":"Interpine Group Ltd., Rotorua 3010, New Zealand"}]},{"given":"Paul","family":"Turner","sequence":"additional","affiliation":[{"name":"ARC Training Centre for Forest Value, University of Tasmania, Churchill Ave., Hobart, TAS 7005, Australia"}]}],"member":"1968","published-online":{"date-parts":[[2021,4,7]]},"reference":[{"key":"ref_1","unstructured":"Murphy, S., Bi, H., Volkova, L., Weston, C., Madhavan, D., Krishnaraj, S.J., Fairman, T., and Law, R. (2014). Comprehensive Carbon Assessment Program (CCAP). Validating Above-Ground Carbon Estimates of Eucalypt Dominated Forest in Victoria, Victorian Centre for Climate Change Adaptation Research (VCCCAR) and the Department of Environment and Primary Industries (DEPI)."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"806","DOI":"10.1038\/nclimate2318","article-title":"Increasing forest disturbances in Europe and their impact on carbon storage","volume":"4","author":"Seidl","year":"2014","journal-title":"Nat. Clim. Chang."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.1007\/s00442-011-2165-z","article-title":"A universal airborne LiDAR approach for tropical forest carbon mapping","volume":"168","author":"Asner","year":"2012","journal-title":"Oecologia"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.foreco.2012.06.056","article-title":"Mapping fire risk in the Model Forest of Urbi\u00f3n (Spain) based on airborne LiDAR measurements","volume":"282","year":"2012","journal-title":"For. Ecol. Manag."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.foreco.2016.12.002","article-title":"Spatially explicit measurements of forest structure and fire behavior following restoration treatments in dry forests","volume":"386","author":"Ziegler","year":"2017","journal-title":"For. Ecol. Manag."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shugart, H.H., Saatchi, S., and Hall, F.G. (2010). Importance of structure and its measurement in quantifying function of forest ecosystems. J. Geophys. Res. Biogeosci., 115.","DOI":"10.1029\/2009JG000993"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.foreco.2006.07.024","article-title":"An objective and quantitative methodology for constructing an index of stand structural complexity","volume":"235","author":"McElhinny","year":"2006","journal-title":"For. Ecol. Manag."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.foreco.2005.08.034","article-title":"Forest and woodland stand structural complexity: Its definition and measurement","volume":"218","author":"McElhinny","year":"2005","journal-title":"For. Ecol. Manag."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Piermattei, L., Karel, W., Wang, D., Wieser, M., Mokro\u0161, M., Surov\u00fd, P., Kore\u0148, M., Toma\u0161t\u00edk, J., Pfeifer, N., and Hollaus, M. (2019). Terrestrial Structure from Motion Photogrammetry for Deriving Forest Inventory Data. Remote Sens., 11.","DOI":"10.3390\/rs11080950"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mokro\u0161, M., Liang, X., Surov\u00fd, P., Valent, P., \u010cer\u0148ava, J., Chud\u00fd, F., Tun\u00e1k, D., Salo\u0148, \u0160., and Mergani\u010d, J. (2018). Evaluation of Close-Range Photogrammetry Image Collection Methods for Estimating Tree Diameters. ISPRS Int. J. Geo-Inf., 7.","DOI":"10.3390\/ijgi7030093"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Krisanski, S., Taskhiri, M.S., and Turner, P. (2020). Enhancing Methods for Under-Canopy Unmanned Aircraft System Based Photogrammetry in Complex Forests for Tree Diameter Measurement. Remote Sens., 12.","DOI":"10.3390\/rs12101652"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Ku\u017eelka, K., and Surov\u00fd, P. (2018). Mapping Forest Structure Using UAS inside Flight Capabilities. Sensors, 18.","DOI":"10.3390\/s18072245"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Trochta, J., Kr\u016f\u010dek, M., Vr\u0161ka, T., and Kr\u00e1l, K. (2017). 3D Forest: An application for descriptions of three-dimensional forest structures using terrestrial LiDAR. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0176871"},{"key":"ref_14","unstructured":"GreenValley International (2020, August 10). LIDAR360 Comprehensive Point Cloud Post-Processing Suite. Available online: https:\/\/greenvalleyintl.com\/software\/lidar360\/."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.compag.2017.10.019","article-title":"Performance of stem denoising and stem modelling algorithms on single tree point clouds from terrestrial laser scanning","volume":"143","author":"Olofsson","year":"2017","journal-title":"Comput. Electron. Agric."},{"key":"ref_16","unstructured":"Piboule, A., Krebs, M., Esclatine, L., and Herv\u00e9, J.-C. (2013, January 1\u20134). Computree: A collaborative platform for use of terrestrial lidar in dendrometry. Proceedings of the International IUFRO Conference MeMoWood, Nancy, France."},{"key":"ref_17","unstructured":"Kore\u0148, M. (2018). DendroCloud, 1.47, Technical University in Zvolen."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/j.isprsjprs.2018.06.021","article-title":"International benchmarking of terrestrial laser scanning approaches for forest inventories","volume":"144","author":"Liang","year":"2018","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"112102","DOI":"10.1016\/j.rse.2020.112102","article-title":"Terrestrial laser scanning in forest ecology: Expanding the horizon","volume":"251","author":"Calders","year":"2020","journal-title":"Remote Sens. Environ."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"438","DOI":"10.1111\/2041-210X.13121","article-title":"Extracting individual trees from lidar point clouds using treeseg","volume":"10","author":"Burt","year":"2018","journal-title":"Methods Ecol. Evol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.isprsjprs.2020.04.020","article-title":"Unsupervised semantic and instance segmentation of forest point clouds","volume":"165","author":"Wang","year":"2020","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Raumonen, P., \u00c5kerblom, M., Kaasalainen, M., Casella, E., Calders, K., and Murphy, S. (2015). Massive-scale tree modelling from TLS data. ISPRS Ann. Photogramm. Remote Sens. Spat. Inf. Sci., 2.","DOI":"10.5194\/isprsannals-II-3-W4-189-2015"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Morel, J., Bac, A., and Kanai, T. (2020). Segmentation of unbalanced and in-homogeneous point clouds and its application to 3D scanned trees. Vis. Comput.","DOI":"10.1007\/s00371-020-01966-7"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3043","DOI":"10.1109\/LRA.2018.2849499","article-title":"Automatic Segmentation of Tree Structure From Point Cloud Data","volume":"3","author":"Digumarti","year":"2018","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"142","DOI":"10.1016\/j.envsoft.2016.04.025","article-title":"Deriving comprehensive forest structure information from mobile laser scanning observations using automated point cloud classification","volume":"82","author":"Marselis","year":"2016","journal-title":"Environ. Model. Softw."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Windrim, L., and Bryson, M. (2020). Detection, Segmentation, and Model Fitting of Individual Tree Stems from Airborne Laser Scanning of Forests Using Deep Learning. Remote Sens., 12.","DOI":"10.3390\/rs12091469"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Heinzel, J., and Huber, M.O. (2017). Detecting Tree Stems from Volumetric TLS Data in Forest Environments with Rich Understory. Remote Sens., 9.","DOI":"10.3390\/rs9010009"},{"key":"ref_28","unstructured":"Lalonde, J.F., Vandapel, N., and Hebert, M. (2006). Automatic Three-Dimensional Point Cloud Processing for Forest Inventory, Carnegie Mellon University."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1080\/07038992.2017.1252907","article-title":"Layer Stacking: A Novel Algorithm for Individual Forest Tree Segmentation from LiDAR Point Clouds","volume":"43","author":"Ayrey","year":"2017","journal-title":"Can. J. Remote Sens."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ni, H., Lin, X., and Zhang, J. (2017). Classification of ALS Point Cloud with Improved Point Cloud Segmentation and Random Forests. Remote Sens., 9.","DOI":"10.3390\/rs9030288"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"3958","DOI":"10.1109\/JSTARS.2020.3008477","article-title":"A Point-Based Fully Convolutional Neural Network for Airborne LiDAR Ground Point Filtering in Forested Environments","volume":"13","author":"Jin","year":"2020","journal-title":"IEEE J. Sel. Topics Appl. Earth Obs. Remote Sens."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Ayrey, E., and Hayes, D.J. (2018). The Use of Three-Dimensional Convolutional Neural Networks to Interpret LiDAR for Forest Inventory. Remote Sens., 10.","DOI":"10.3390\/rs10040649"},{"key":"ref_33","unstructured":"Digumarti, S.T. (2019). Semantic Segmentation and Mapping for Natural Environments, ETH Zurich."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"376","DOI":"10.1111\/2041-210X.13342","article-title":"LeWoS: A universal leaf-wood classification method to facilitate the 3D modelling of large tropical trees using terrestrial LiDAR","volume":"11","author":"Wang","year":"2020","journal-title":"Methods Ecol. Evol."},{"key":"ref_35","unstructured":"Qi, C.R., Yi, L., Su, H., and Guibas, L.J. (2017). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. arXiv."},{"key":"ref_36","unstructured":"Girardeau-Montaut, D. (2019, October 06). CloudCompare, v2.11.alpha. Available online: https:\/\/www.danielgm.net\/cc\/."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1111\/2041-210X.12301","article-title":"Nondestructive estimates of above-ground biomass using terrestrial laser scanning","volume":"6","author":"Calders","year":"2015","journal-title":"Methods Ecol. Evol."},{"key":"ref_38","unstructured":"Wageningen University, Netherlands, CSIRO Land and Water, Department of Geography, University College London, School of Land and Environment, University of Melbourne, Department of Mathematics, Tampere University of Technology, Environmental Sensing Systems, Melbourne, and Remote Sensing Centre, Queensland Department of Science, Information Technology, Innovation and the Arts (2020, October 05). Terrestrial Laser Scans\u2014Riegl VZ400, Individual Tree Point Clouds and Cylinder Models, Rushworth Forest. Available online: gpv1wf_14501655e03676013s_20120504_aa2f0_r06cd_p300khz_x01.las."},{"key":"ref_39","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2016). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv."},{"key":"ref_40","unstructured":"Fey, M., and Lenssen, J.E. (2019). Fast graph representation learning with PyTorch Geometric. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","article-title":"Array programming with NumPy","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"ref_42","first-page":"2825","article-title":"Scikit-learn: Machine Learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental algorithms for scientific computing in Python","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_44","unstructured":"TerraSolid (2021, April 07). TerraScan; TerraSolid. Available online: https:\/\/terrasolid.com\/products\/terrascan\/."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.isprsjprs.2019.03.007","article-title":"Detecting and characterizing downed dead wood using terrestrial laser scanning","volume":"151","author":"Yrttimaa","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/8\/1413\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:34:13Z","timestamp":1760362453000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/13\/8\/1413"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,4,7]]},"references-count":45,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2021,4]]}},"alternative-id":["rs13081413"],"URL":"https:\/\/doi.org\/10.3390\/rs13081413","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,4,7]]}}}