Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Automated forest inventory: analysis of high-density airborne LiDAR point clouds with 3D deep learning (2312.15084v2)

Published 22 Dec 2023 in cs.CV

Abstract: Detailed forest inventories are critical for sustainable and flexible management of forest resources, to conserve various ecosystem services. Modern airborne laser scanners deliver high-density point clouds with great potential for fine-scale forest inventory and analysis, but automatically partitioning those point clouds into meaningful entities like individual trees or tree components remains a challenge. The present study aims to fill this gap and introduces a deep learning framework, termed ForAINet, that is able to perform such a segmentation across diverse forest types and geographic regions. From the segmented data, we then derive relevant biophysical parameters of individual trees as well as stands. The system has been tested on FOR-Instance, a dataset of point clouds that have been acquired in five different countries using surveying drones. The segmentation back-end achieves over 85% F-score for individual trees, respectively over 73% mean IoU across five semantic categories: ground, low vegetation, stems, live branches and dead branches. Building on the segmentation results our pipeline then densely calculates biophysical features of each individual tree (height, crown diameter, crown volume, DBH, and location) and properties per stand (digital terrain model and stand density). Especially crown-related features are in most cases retrieved with high accuracy, whereas the estimates for DBH and location are less reliable, due to the airborne scanning setup.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (79)
  1. Non-destructive tree volume estimation through quantitative structure modelling: Comparing UAV laser scanning with terrestrial LIDAR. Remote Sensing of Environment 233, 111355. https://doi.org/10.1016/j.rse.2019.111355.
  2. A two-stage approach for individual tree segmentation from TLS point clouds. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 15, 8682–8693. https://doi.org/10.1109/JSTARS.2022.3212445.
  3. Torch-Points3D: A modular multi-task framework for reproducible deep learning on 3D point clouds, in: International Conference on 3D Vision (3DV), pp. 1–10. https://doi.org/10.1109/3DV50981.2020.00029.
  4. Individual tree segmentation and tree height estimation using leaf-off and leaf-on UAV-LiDAR data in dense deciduous forests. Remote Sensing 14, 2787. https://doi.org/10.3390/rs14122787.
  5. Hierarchical aggregation for 3D instance segmentation, in: IEEE/CVF International Conference on Computer Vision, pp. 15447–15456. https://doi.org/10.1109/ICCV48922.2021.01518.
  6. Individual tree crown segmentation directly from UAV-borne LiDAR data using the PointNet of deep learning. Forests 12, 131. https://doi.org/10.3390/f12020131.
  7. 4D spatio-temporal convnets: Minkowski convolutional neural networks, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3075–3084. https://doi.org/10.1109/CVPR.2019.00319.
  8. Area-based vs tree-centric approaches to mapping forest carbon in southeast asian forests from airborne laser scanning data. Remote Sensing of Environment 194, 77–88. URL: https://www.sciencedirect.com/science/article/pii/S0034425717301098, doi:https://doi.org/10.1016/j.rse.2017.03.017.
  9. A new method for 3D individual tree extraction using multispectral airborne LiDAR point clouds. ISPRS Journal of Photogrammetry and Remote Sensing 144, 400–411. https://doi.org/10.1016/j.isprsjprs.2018.08.010.
  10. Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data. Methods in Ecology and Evolution 7, 1236–1245. https://doi.org/10.1111/2041-210X.12575.
  11. Tree stem detection and crown delineation in a structurally diverse deciduous forest combining leaf-on and leaf-off UAV-SfM data. Remote Sensing 15, 4366. https://doi.org/10.3390/rs15184366.
  12. Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM 24, 381–395. https://doi.org/10.1145/358669.358692.
  13. A review on 2D instance segmentation based on deep neural networks. Image and Vision Computing 120, 104401. https://doi.org/10.1016/j.imavis.2022.104401.
  14. Weakly supervised segmentation-aided classification of urban scenes from 3D LiDAR point clouds, in: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, pp. 151–157. https://doi.org/10.5194/isprs-archives-XLII-1-W1-151-2017.
  15. Fast semantic segmentation of 3D point clouds with strongly varying density, in: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Copernicus GmbH. pp. 177–184. https://doi.org/10.5194/isprs-annals-III-3-177-2016.
  16. Individual tree segmentation and species classification using high-density close-range multispectral laser scanning data. ISPRS Open Journal of Photogrammetry and Remote Sensing 9, 100039. https://doi.org/10.1016/j.ophoto.2023.100039.
  17. A hierarchical region-merging algorithm for 3-D segmentation of individual trees using UAV-LiDAR point clouds. IEEE Transactions on Geoscience and Remote Sensing 60, 1–16. https://doi.org/10.1109/TGRS.2021.3121419.
  18. Towards low vegetation identification: A new method for tree crown segmentation from LiDAR data based on a symmetrical structure detection algorithm (SSD). Remote Sensing of Environment 270, 112857. https://doi.org/10.1016/j.rse.2021.112857.
  19. Direct and automatic measurements of stem curve and volume using a high-resolution airborne laser scanning system. Science of Remote Sensing 5, 100050. https://doi.org/10.1016/j.srs.2022.100050.
  20. A segmentation-based method to retrieve stem volume estimates from 3-D tree height models produced by laser scanners. IEEE Transactions on Geoscience and Remote Sensing 39, 969–975. https://doi.org/10.1109/36.921414.
  21. PointGroup: Dual-set point grouping for 3D instance segmentation, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4866–4875. https://doi.org/10.1109/CVPR42600.2020.00492.
  22. LWSNet: A point-based segmentation network for leaf-wood separation of individual trees. Forests 14, 1303. https://doi.org/10.3390/f14071303.
  23. ultralytics/yolov5: v7.0 - YOLOv5 SOTA Realtime Instance Segmentation. URL: https://doi.org/10.5281/zenodo.7347926.
  24. Allometric equations for integrating remote sensing imagery into forest monitoring programmes. Global Change Biology 23, 177–190. https://doi.org/10.1111/gcb.13388.
  25. An international comparison of individual tree detection and extraction using airborne laser scanning. Remote Sensing 4, 950–974. https://doi.org/10.3390/rs4040950.
  26. Semantic segmentation of point cloud data using raw laser scanner measurements and deep neural networks. ISPRS Open Journal of Photogrammetry and Remote Sensing 3, 100011. https://doi.org/10.1016/j.ophoto.2021.100011.
  27. Remote sensing and forest inventories in Nordic countries–roadmap for the future. Scandinavian Journal of Forest Research 33, 397–412. https://doi.org/10.1080/02827581.2017.1416666.
  28. New opportunities for forest remote sensing through ultra-high-density drone lidar. Surveys in Geophysics 40, 959–977. https://doi.org/10.1007/s10712-019-09529-9.
  29. Automated segmentation of individual tree structures using deep learning over LiDAR point cloud data. Forests 14, 1159. https://doi.org/10.3390/f14061159.
  30. Forest structural complexity tool—an open source, fully-automated tool for measuring forest point clouds. Remote Sensing 13, 4677. https://doi.org/10.3390/rs13224677.
  31. Sensor agnostic semantic segmentation of structurally diverse and complex forest point clouds using deep learning. Remote Sensing 13, 1413. https://doi.org/10.3390/rs13081413.
  32. Very high density point clouds from UAV laser scanning for automatic tree stem detection and direct diameter measurement. Remote Sensing 12, 1236. https://doi.org/10.3390/rs12081236.
  33. Deep learning enables image-based tree counting, crown segmentation, and height prediction at national scale. PNAS Nexus 2, 1–16. https://doi.org/10.1093/pnasnexus/pgad076.
  34. International benchmarking of terrestrial laser scanning approaches for forest inventories. ISPRS Journal of Photogrammetry and Remote Sensing 144, 137–179. https://doi.org/10.1016/j.isprsjprs.2018.06.021.
  35. Forest in situ observations using unmanned aerial vehicle as an alternative of terrestrial measurements. Forest Ecosystems 6. https://doi.org/10.1186/s40663-019-0173-3.
  36. Accounting for forest condition in Europe based on an international statistical standard. Nature Communications 14, 3723. https://doi.org/10.1038/s41467-023-39434-0.
  37. hdbscan: Hierarchical density based clustering. The Journal of Open Source Software 2, 205. https://doi.org/10.21105/joss.00205.
  38. Predicting forest stand characteristics with airborne scanning laser using a practical two-stage procedure and field data. Remote Sensing of Environment 80, 88–99. https://doi.org/10.1016/S0034-4257(01)00290-5.
  39. Laser scanning of forest resources: the nordic experience. Scandinavian Journal of Forest Research 19, 482–499. https://doi.org/10.1080/02827580410019553.
  40. Mix3D: Out-of-context data augmentation for 3D scenes, in: International Conference on 3D Vision (3DV), pp. 116–125. https://doi.org/10.1109/3DV53792.2021.00022.
  41. Individual tree detection and estimation of stem attributes with mobile laser scanning along boreal forest roads. ISPRS Journal of Photogrammetry and Remote Sensing 187, 211–224. https://doi.org/10.1016/j.isprsjprs.2022.03.004.
  42. Detecting and measuring individual trees using an airborne laser scanner. Photogrammetric engineering and remote sensing 68, 925–932.
  43. Two-phase forest inventory using very-high-resolution laser scanning. Remote Sensing of Environment 271, 112909. https://doi.org/10.1016/j.rse.2022.112909.
  44. Estimation of forest growing stock volume with UAV laser scanning data: Can it be done without field data? Remote Sensing 12, 1245. https://doi.org/10.3390/rs12081245.
  45. Tree height-growth trajectory estimation using uni-temporal UAV laser scanning data and deep learning. Forestry: An International Journal of Forest Research 96, 37–48. URL: https://doi.org/10.1093/forestry/cpac026, doi:10.1093/forestry/cpac026, arXiv:https://academic.oup.com/forestry/article-pdf/96/1/37/48536552/cpac026.pdf.
  46. Tree height-growth trajectory estimation using uni-temporal UAV laser scanning data and deep learning. Forestry: An International Journal of Forest Research 96, 37–48. https://doi.org/10.1093/forestry/cpac026.
  47. FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees. https://doi.org/10.48550/arXiv.2309.01279.
  48. lidR: An R package for analysis of Airborne Laser Scanning (ALS) data. Remote Sensing of Environment 251, 112061. https://doi.org/10.1016/j.rse.2020.112061.
  49. CoSMix: Compositional semantic mix for domain adaptation in 3D LiDAR segmentation, in: European Conference on Computer Vision (ECCV), Springer. pp. 586–602. https://doi.org/10.1007/978-3-031-19827-4_34.
  50. Triangle: Engineering a 2D Quality Mesh Generator and Delaunay Triangulator, in: Lin, M.C., Manocha, D. (Eds.), Applied Computational Geometry: Towards Geometric Engineering. Springer-Verlag. volume 1148 of Lecture Notes in Computer Science, pp. 203–222. From the First ACM Workshop on Applied Computational Geometry.
  51. Delaunay refinement algorithms for triangular mesh generation. Computational Geometry: Theory and Applications 22, 21–74. https://doi.org/10.1016/S0925-7721(01)00047-5.
  52. Instance segmentation of individual tree crowns with YOLOv5: A comparison of approaches using the ForInstance benchmark LiDAR dataset. ISPRS Open Journal of Photogrammetry and Remote Sensing 9, 100045. https://doi.org/10.1016/j.ophoto.2023.100045.
  53. A graph-based segmentation algorithm for tree crown extraction using airborne LiDAR data. ISPRS Journal of Photogrammetry and Remote Sensing 104, 30–43. https://doi.org/10.1016/j.isprsjprs.2015.01.018.
  54. Individual tree crown segmentation and crown width extraction from a heightmap derived from aerial laser scanning data using a deep learning framework. Frontiers in Plant Science 13, 914974. https://doi.org/10.3389/fpls.2022.914974.
  55. Modelling internal tree attributes for breeding applications in Douglas-fir progeny trials using RPAS-ALS. Science of Remote Sensing 7, 100072. https://doi.org/10.1016/j.srs.2022.100072.
  56. A survey on deep domain adaptation for LiDAR perception, in: IEEE Intelligent Vehicles Symposium Workshops (IV Workshops), pp. 350–357. https://doi.org/10.1109/IVWorkshops54471.2021.9669228.
  57. 3D Forest: An application for descriptions of three-dimensional forest structures using terrestrial LiDAR. PLoS ONE 12, e0176871. https://doi.org/10.1371/journal.pone.0176871.
  58. Comparative testing of single-tree detection algorithms under different types of forest. Forestry: An International Journal of Forest Research 85, 27–40. https://doi.org/10.1093/forestry/cpr051.
  59. SoftGroup for 3D instance segmentation on point clouds, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 2698–2707. https://doi.org/10.1109/CVPR52688.2022.00273.
  60. Unsupervised semantic and instance segmentation of forest point clouds. ISPRS Journal of Photogrammetry and Remote Sensing 165, 86–97. https://doi.org/10.1016/j.isprsjprs.2020.04.020.
  61. Tree segmentation and parameter measurement from point clouds using deep and handcrafted features. Remote Sensing 15, 1086. https://doi.org/10.3390/rs15041086.
  62. Scientific discovery in the age of artificial intelligence. Nature 620, 47–60. https://doi.org/10.1038/s41586-023-06221-2.
  63. Associatively segmenting instances and semantics in point clouds, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 4091–4100. https://doi.org/10.1109/CVPR.2019.00422.
  64. 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 Journal of Photogrammetry and Remote Sensing 147, 132–145. https://doi.org/10.1016/j.isprsjprs.2018.11.008.
  65. Smallest enclosing disks (balls and ellipsoids), in: Maurer, H. (Ed.), New Results and New Trends in Computer Science, Springer Berlin Heidelberg, Berlin, Heidelberg. pp. 359–370. https://doi.org/10.1007/BFb0038202.
  66. Point2Tree(P2T)—framework for parameter tuning of semantic and instance segmentation used with mobile laser scanning data in coniferous forest. Remote Sensing 15, 3737. https://doi.org/10.3390/rs15153737.
  67. Detection, segmentation, and model fitting of individual tree stems from airborne laser scanning of forests using deep learning. Remote Sensing 12, 1469. https://doi.org/10.3390/rs12091469.
  68. 3D graph-based individual-tree isolation (Treeiso) from terrestrial laser scanning point clouds. Remote Sensing 14, 6116. https://doi.org/10.3390/rs14236116.
  69. Filtering stems and branches from terrestrial laser scanning point clouds using deep 3-D fully convolutional networks. Remote Sensing 10, 1215. https://doi.org/10.3390/rs10081215.
  70. Towards accurate instance segmentation in large-scale LiDAR point clouds. https://doi.org/10.48550/arXiv.2307.02877.
  71. A review of panoptic segmentation for mobile mapping point clouds. ISPRS Journal of Photogrammetry and Remote Sensing 203, 373–391. https://doi.org/10.1016/j.isprsjprs.2023.08.008.
  72. Separation of wood and foliage for trees from ground point clouds using a novel least-cost path model. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 14, 6414–6425. https://doi.org/10.1109/JSTARS.2021.3090502.
  73. A self-adaptive mean shift tree-segmentation method using UAV LiDAR data. Remote Sensing 12, 515. https://doi.org/10.3390/rs12030515.
  74. How to assess the accuracy of the individual tree-based forest inventory derived from remotely sensed data: a review. International Journal of Remote Sensing 37, 4521–4553. https://doi.org/10.1080/01431161.2016.1214302.
  75. Individual tree segmentation from LiDAR point clouds for urban forest inventory. Remote Sensing 7, 7892–7913. https://doi.org/10.3390/rs70607892.
  76. A novel approach for the detection of standing tree stems from plot-level terrestrial laser scanning data. Remote Sensing 11, 211. https://doi.org/10.3390/rs11020211.
  77. Towards intricate stand structure: A novel individual tree segmentation method for ALS point cloud based on extreme offset deep learning. Applied Science 13, 6853. https://doi.org/10.3390/app13116853.
  78. MaskGroup: Hierarchical point grouping and masking for 3D instance segmentation, in: International Conference on Multimedia and Expo, pp. 1–6. https://doi.org/10.1109/ICME52920.2022.9859996.
  79. LiDAR-based regional inventory of tall trees—Wellington, New Zealand. Forests 9, 702. https://doi.org/10.3390/f9110702.
Citations (19)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now