Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.03633 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914020173283328 |
|---|---|
| author | Burmeister, Josafat-Mattias Tockner, Andreas Reder, Stefan Engel, Markus Richter, Rico Mund, Jan-Peter Döllner, Jürgen |
| author_facet | Burmeister, Josafat-Mattias Tockner, Andreas Reder, Stefan Engel, Markus Richter, Rico Mund, Jan-Peter Döllner, Jürgen |
| contents | Close-range laser scanning provides detailed 3D captures of forest stands but requires efficient software for processing 3D point cloud data and extracting individual trees. Although recent studies have introduced deep learning methods for tree instance segmentation, these approaches require large annotated datasets and substantial computational resources. As a resource-efficient alternative, we present a revised version of the treeX algorithm, an unsupervised method that combines clustering-based stem detection with region growing for crown delineation. While the original treeX algorithm was developed for personal laser scanning (PLS) data, we provide two parameter presets, one for ground-based laser scanning (stationary terrestrial - TLS and PLS), and one for UAV-borne laser scanning (ULS). We evaluated the method on six public datasets (FOR-instance, ForestSemantic, LAUTx, NIBIO MLS, TreeLearn, Wytham Woods) and compared it to six open-source methods (original treeX, treeiso, RayCloudTools, ForAINet, SegmentAnyTree, TreeLearn). Compared to the original treeX algorithm, our revision reduces runtime and improves accuracy, with instance detection F$_1$-score gains of +0.11 to +0.49 for ground-based data. For ULS data, our preset achieves an F$_1$-score of 0.58, whereas the original algorithm fails to segment any correct instances. For TLS and PLS data, our algorithm achieves accuracy similar to recent open-source methods, including deep learning. Given its algorithmic design, we see two main applications for our method: (1) as a resource-efficient alternative to deep learning approaches in scenarios where the data characteristics align with the method design (sufficient stem visibility and point density), and (2) for the semi-automatic generation of labels for deep learning models. To enable broader adoption, we provide an open-source Python implementation in the pointtree package. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03633 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | treeX: Unsupervised Tree Instance Segmentation in Dense Forest Point Clouds Burmeister, Josafat-Mattias Tockner, Andreas Reder, Stefan Engel, Markus Richter, Rico Mund, Jan-Peter Döllner, Jürgen Computer Vision and Pattern Recognition Artificial Intelligence I.4.6; I.5.2; I.2.10 Close-range laser scanning provides detailed 3D captures of forest stands but requires efficient software for processing 3D point cloud data and extracting individual trees. Although recent studies have introduced deep learning methods for tree instance segmentation, these approaches require large annotated datasets and substantial computational resources. As a resource-efficient alternative, we present a revised version of the treeX algorithm, an unsupervised method that combines clustering-based stem detection with region growing for crown delineation. While the original treeX algorithm was developed for personal laser scanning (PLS) data, we provide two parameter presets, one for ground-based laser scanning (stationary terrestrial - TLS and PLS), and one for UAV-borne laser scanning (ULS). We evaluated the method on six public datasets (FOR-instance, ForestSemantic, LAUTx, NIBIO MLS, TreeLearn, Wytham Woods) and compared it to six open-source methods (original treeX, treeiso, RayCloudTools, ForAINet, SegmentAnyTree, TreeLearn). Compared to the original treeX algorithm, our revision reduces runtime and improves accuracy, with instance detection F$_1$-score gains of +0.11 to +0.49 for ground-based data. For ULS data, our preset achieves an F$_1$-score of 0.58, whereas the original algorithm fails to segment any correct instances. For TLS and PLS data, our algorithm achieves accuracy similar to recent open-source methods, including deep learning. Given its algorithmic design, we see two main applications for our method: (1) as a resource-efficient alternative to deep learning approaches in scenarios where the data characteristics align with the method design (sufficient stem visibility and point density), and (2) for the semi-automatic generation of labels for deep learning models. To enable broader adoption, we provide an open-source Python implementation in the pointtree package. |
| title | treeX: Unsupervised Tree Instance Segmentation in Dense Forest Point Clouds |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence I.4.6; I.5.2; I.2.10 |
| url | https://arxiv.org/abs/2509.03633 |