Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes
The automatic extraction of individual tree from mobile laser scanning (MLS) scenes has important applications in tree growth monitoring, tree parameter calculation and tree modeling. However, trees often grow in rows and tree crowns overlap with varying shapes, and there is also incompleteness caus...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/6/1567 |
| _version_ | 1827747794801131520 |
|---|---|
| author | Xiaojuan Ning Yishu Ma Yuanyuan Hou Zhiyong Lv Haiyan Jin Zengbo Wang Yinghui Wang |
| author_facet | Xiaojuan Ning Yishu Ma Yuanyuan Hou Zhiyong Lv Haiyan Jin Zengbo Wang Yinghui Wang |
| author_sort | Xiaojuan Ning |
| collection | DOAJ |
| description | The automatic extraction of individual tree from mobile laser scanning (MLS) scenes has important applications in tree growth monitoring, tree parameter calculation and tree modeling. However, trees often grow in rows and tree crowns overlap with varying shapes, and there is also incompleteness caused by occlusion, which makes individual tree extraction a challenging problem. In this paper, we propose a trunk-constrained and tree structure analysis method to extract trees from scanned urban scenes. Firstly, multi-feature enhancement is performed via PointNet to segment the tree points from raw urban scene point clouds. Next, the candidate local tree trunk clusters are obtained by clustering based on the intercepted local tree trunk layer, and the real local tree trunk is obtained by removing noise data. Then, the trunk is located and extracted by combining circle fitting and region growing, so as to obtain the center of the tree crown. Further, the points near the tree’s crown (core points) are segmented through distance difference, and the tree crown boundary (boundary points) is distinguished by analyzing the density and centroid deflection angle. Therefore, the core and boundary points are deleted to obtain the remaining points (intermediate points). Finally, the core, intermediate and boundary points, as well as the tree trunks, are combined to extract individual tree. The performance of the proposed method was evaluated on the Pairs-Lille-3D dataset, which is a benchmark for point cloud classification, and data were produced using a mobile laser system (MLS) applied to two different cities in France (Paris and Lille). Overall, the precision, recall, and F1-score of instance segmentation were 90.00%, 98.22%, and 99.08%, respectively. The experimental results demonstrate that our method can effectively extract trees with multiple rows of occlusion and improve the accuracy of tree extraction. |
| first_indexed | 2024-03-11T05:57:17Z |
| format | Article |
| id | doaj.art-6cea0587df304f80a77a43bdc2f137c2 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T05:57:17Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6cea0587df304f80a77a43bdc2f137c22023-11-17T13:38:53ZengMDPI AGRemote Sensing2072-42922023-03-01156156710.3390/rs15061567Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor ScenesXiaojuan Ning0Yishu Ma1Yuanyuan Hou2Zhiyong Lv3Haiyan Jin4Zengbo Wang5Yinghui Wang6Institute of Computer Science and Engineering, Xi’an University of Technology, No. 5 South of Jinhua Road, Xi’an 710048, ChinaInstitute of Computer Science and Engineering, Xi’an University of Technology, No. 5 South of Jinhua Road, Xi’an 710048, ChinaInstitute of Computer Science and Engineering, Xi’an University of Technology, No. 5 South of Jinhua Road, Xi’an 710048, ChinaInstitute of Computer Science and Engineering, Xi’an University of Technology, No. 5 South of Jinhua Road, Xi’an 710048, ChinaInstitute of Computer Science and Engineering, Xi’an University of Technology, No. 5 South of Jinhua Road, Xi’an 710048, ChinaCollege of Mathematics and Statistics, Hengyang Normal University, Hengyang 421002, ChinaSchool of Artificial Intelligence and Computer Science, Jiangnan University, 1800 of Lihu Road, Wuxi 214122, ChinaThe automatic extraction of individual tree from mobile laser scanning (MLS) scenes has important applications in tree growth monitoring, tree parameter calculation and tree modeling. However, trees often grow in rows and tree crowns overlap with varying shapes, and there is also incompleteness caused by occlusion, which makes individual tree extraction a challenging problem. In this paper, we propose a trunk-constrained and tree structure analysis method to extract trees from scanned urban scenes. Firstly, multi-feature enhancement is performed via PointNet to segment the tree points from raw urban scene point clouds. Next, the candidate local tree trunk clusters are obtained by clustering based on the intercepted local tree trunk layer, and the real local tree trunk is obtained by removing noise data. Then, the trunk is located and extracted by combining circle fitting and region growing, so as to obtain the center of the tree crown. Further, the points near the tree’s crown (core points) are segmented through distance difference, and the tree crown boundary (boundary points) is distinguished by analyzing the density and centroid deflection angle. Therefore, the core and boundary points are deleted to obtain the remaining points (intermediate points). Finally, the core, intermediate and boundary points, as well as the tree trunks, are combined to extract individual tree. The performance of the proposed method was evaluated on the Pairs-Lille-3D dataset, which is a benchmark for point cloud classification, and data were produced using a mobile laser system (MLS) applied to two different cities in France (Paris and Lille). Overall, the precision, recall, and F1-score of instance segmentation were 90.00%, 98.22%, and 99.08%, respectively. The experimental results demonstrate that our method can effectively extract trees with multiple rows of occlusion and improve the accuracy of tree extraction.https://www.mdpi.com/2072-4292/15/6/1567mobile laser scanningindividual tree detectionMLS point cloudsoutdoor scene |
| spellingShingle | Xiaojuan Ning Yishu Ma Yuanyuan Hou Zhiyong Lv Haiyan Jin Zengbo Wang Yinghui Wang Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes Remote Sensing mobile laser scanning individual tree detection MLS point clouds outdoor scene |
| title | Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes |
| title_full | Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes |
| title_fullStr | Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes |
| title_full_unstemmed | Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes |
| title_short | Trunk-Constrained and Tree Structure Analysis Method for Individual Tree Extraction from Scanned Outdoor Scenes |
| title_sort | trunk constrained and tree structure analysis method for individual tree extraction from scanned outdoor scenes |
| topic | mobile laser scanning individual tree detection MLS point clouds outdoor scene |
| url | https://www.mdpi.com/2072-4292/15/6/1567 |
| work_keys_str_mv | AT xiaojuanning trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT yishuma trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT yuanyuanhou trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT zhiyonglv trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT haiyanjin trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT zengbowang trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes AT yinghuiwang trunkconstrainedandtreestructureanalysismethodforindividualtreeextractionfromscannedoutdoorscenes |