Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning
Abstract Southern pine forests play a key role in the ecological function and economic vitality of the southeastern United States. High-resolution terrestrial laser scanning (TLS) has become an indispensable tool for advancing tree structural research and monitoring. A critical challenge in this fie...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-09681-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849343881398714368 |
|---|---|
| author | Jinyi Xia Timothy A. Martin Gary F. Peter Kody M. Brock Jeff W. Atkins Matthew A. Gitzendanner Inacio Bueno Kim Calders Ana Paula Dalla Corte Andrew T. Hudak Monique Bohora Schlickmann Michael G. Andreu Caio Hamamura Carine Klauberg Carlos A. Silva |
| author_facet | Jinyi Xia Timothy A. Martin Gary F. Peter Kody M. Brock Jeff W. Atkins Matthew A. Gitzendanner Inacio Bueno Kim Calders Ana Paula Dalla Corte Andrew T. Hudak Monique Bohora Schlickmann Michael G. Andreu Caio Hamamura Carine Klauberg Carlos A. Silva |
| author_sort | Jinyi Xia |
| collection | DOAJ |
| description | Abstract Southern pine forests play a key role in the ecological function and economic vitality of the southeastern United States. High-resolution terrestrial laser scanning (TLS) has become an indispensable tool for advancing tree structural research and monitoring. A critical challenge in this field is the accurate segmentation of leaf and wood components, which directly impacts the reliability of Quantitative Structure Models (QSMs). Segmentation techniques have progressed, but most existing methods are tailored for broadleaf species, with limited exploration for coniferous species such as southern pines. Addressing this gap, our study evaluates the performance of multiple segmentation algorithms on TLS data from southern pines, providing valuable insights into improving structural analysis and supporting more precise and efficient forest research and monitoring methodologies. We collected TLS data from longleaf pine (Pinus palustris Mill.) and loblolly pine (Pinus taeda L.) trees in Florida, USA, and compared the performance of four segmentation algorithms: TLSep, Graph, DBSCAN, and KPConv to separate leaf and wood. We found that KPConv was the most accurate method of segmenting wood and leaf points, with an overall accuracy (OA) of 98% and F1 score of 98% for loblolly pine and 95% and 94%, respectively, for longleaf pine. Although KPConv requires a substantial initial investment for training, its inference time is fast, making it a strong candidate for high-accuracy large-scale applications. These results led to highly reliable QSMs across trunk, branch, and total volume estimates. In contrast, DBSCAN, while slightly less accurate (OA of 92% for loblolly pine and 90% for longleaf pine), does not require training data and offers a favorable trade-off between performance and efficiency. These findings highlight the importance of selecting segmentation algorithms based on specific research goals, balancing accuracy and computational feasibility in forest structural modeling. |
| format | Article |
| id | doaj-art-59fefa82a8dc4e608b87b7bb55824e9d |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-59fefa82a8dc4e608b87b7bb55824e9d2025-08-20T03:42:49ZengNature PortfolioScientific Reports2045-23222025-07-0115111710.1038/s41598-025-09681-wCombined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanningJinyi Xia0Timothy A. Martin1Gary F. Peter2Kody M. Brock3Jeff W. Atkins4Matthew A. Gitzendanner5Inacio Bueno6Kim Calders7Ana Paula Dalla Corte8Andrew T. Hudak9Monique Bohora Schlickmann10Michael G. Andreu11Caio Hamamura12Carine Klauberg13Carlos A. Silva14School of Forest, Fisheries, and Geomatics Sciences, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaUSDA Forest Service Southern Research StationDepartment of Biology, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaQ-ForestLab – Laboratory of Quantitative Forest Ecosystem Science, Department of Environment, Ghent UniversityDepartment of Forest Engineering, Federal University of Paraná (UFPR)USDA Forest Service Rocky Mountain Research StationSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaFederal Institute of Education, Science and Technology of São PauloSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaSchool of Forest, Fisheries, and Geomatics Sciences, University of FloridaAbstract Southern pine forests play a key role in the ecological function and economic vitality of the southeastern United States. High-resolution terrestrial laser scanning (TLS) has become an indispensable tool for advancing tree structural research and monitoring. A critical challenge in this field is the accurate segmentation of leaf and wood components, which directly impacts the reliability of Quantitative Structure Models (QSMs). Segmentation techniques have progressed, but most existing methods are tailored for broadleaf species, with limited exploration for coniferous species such as southern pines. Addressing this gap, our study evaluates the performance of multiple segmentation algorithms on TLS data from southern pines, providing valuable insights into improving structural analysis and supporting more precise and efficient forest research and monitoring methodologies. We collected TLS data from longleaf pine (Pinus palustris Mill.) and loblolly pine (Pinus taeda L.) trees in Florida, USA, and compared the performance of four segmentation algorithms: TLSep, Graph, DBSCAN, and KPConv to separate leaf and wood. We found that KPConv was the most accurate method of segmenting wood and leaf points, with an overall accuracy (OA) of 98% and F1 score of 98% for loblolly pine and 95% and 94%, respectively, for longleaf pine. Although KPConv requires a substantial initial investment for training, its inference time is fast, making it a strong candidate for high-accuracy large-scale applications. These results led to highly reliable QSMs across trunk, branch, and total volume estimates. In contrast, DBSCAN, while slightly less accurate (OA of 92% for loblolly pine and 90% for longleaf pine), does not require training data and offers a favorable trade-off between performance and efficiency. These findings highlight the importance of selecting segmentation algorithms based on specific research goals, balancing accuracy and computational feasibility in forest structural modeling.https://doi.org/10.1038/s41598-025-09681-w3D point cloudWood point segmentationArtificial intelligenceLiDAR |
| spellingShingle | Jinyi Xia Timothy A. Martin Gary F. Peter Kody M. Brock Jeff W. Atkins Matthew A. Gitzendanner Inacio Bueno Kim Calders Ana Paula Dalla Corte Andrew T. Hudak Monique Bohora Schlickmann Michael G. Andreu Caio Hamamura Carine Klauberg Carlos A. Silva Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning Scientific Reports 3D point cloud Wood point segmentation Artificial intelligence LiDAR |
| title | Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning |
| title_full | Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning |
| title_fullStr | Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning |
| title_full_unstemmed | Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning |
| title_short | Combined impact of semantic segmentation and quantitative structure modelling of Southern pine trees using terrestrial laser scanning |
| title_sort | combined impact of semantic segmentation and quantitative structure modelling of southern pine trees using terrestrial laser scanning |
| topic | 3D point cloud Wood point segmentation Artificial intelligence LiDAR |
| url | https://doi.org/10.1038/s41598-025-09681-w |
| work_keys_str_mv | AT jinyixia combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT timothyamartin combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT garyfpeter combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT kodymbrock combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT jeffwatkins combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT matthewagitzendanner combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT inaciobueno combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT kimcalders combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT anapauladallacorte combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT andrewthudak combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT moniquebohoraschlickmann combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT michaelgandreu combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT caiohamamura combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT carineklauberg combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning AT carlosasilva combinedimpactofsemanticsegmentationandquantitativestructuremodellingofsouthernpinetreesusingterrestriallaserscanning |