A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging
Accurate individual tree segmentation (ITS) in dense rubber plantations is a challenging task due to overlapping canopies, indistinct tree apexes, and intricate branch structures. To address these challenges, we propose a bottom-up, multi-feature fusion method for segmenting rubber trees using UAV-L...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Plants |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2223-7747/14/11/1640 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849722525426122752 |
|---|---|
| author | Zhipeng Zeng Junpeng Miao Xiao Huang Peng Chen Ping Zhou Junxiang Tan Xiangjun Wang |
| author_facet | Zhipeng Zeng Junpeng Miao Xiao Huang Peng Chen Ping Zhou Junxiang Tan Xiangjun Wang |
| author_sort | Zhipeng Zeng |
| collection | DOAJ |
| description | Accurate individual tree segmentation (ITS) in dense rubber plantations is a challenging task due to overlapping canopies, indistinct tree apexes, and intricate branch structures. To address these challenges, we propose a bottom-up, multi-feature fusion method for segmenting rubber trees using UAV-LiDAR point clouds. Our approach first involves performing a trunk extraction based on branch-point density variations and neighborhood directional features, which allows for the precise separation of trunks from overlapping canopies. Next, we introduce a multi-feature fusion strategy that replaces single-threshold constraints, integrating geometric, directional, and density attributes to classify core canopy points, boundary points, and overlapping regions. Disputed points are then iteratively assigned to adjacent trees based on neighborhood growth angle consistency, enhancing the robustness of the segmentation. Experiments conducted in rubber plantations with varying canopy closure (low, medium, and high) show accuracies of 0.97, 0.98, and 0.95. Additionally, the crown width and canopy projection area derived from the segmented individual tree point clouds are highly consistent with ground truth data, with R<sup>2</sup> values exceeding 0.98 and 0.97, respectively. The proposed method provides a reliable foundation for 3D tree modeling and biomass estimation in structurally complex plantations, advancing precision forestry and ecosystem assessment by overcoming the critical limitations of existing ITS approaches in high-closure tropical agroforests. |
| format | Article |
| id | doaj-art-7b5fbd7b29c843aea52aa9f03f70f90a |
| institution | DOAJ |
| issn | 2223-7747 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Plants |
| spelling | doaj-art-7b5fbd7b29c843aea52aa9f03f70f90a2025-08-20T03:11:19ZengMDPI AGPlants2223-77472025-05-011411164010.3390/plants14111640A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and RangingZhipeng Zeng0Junpeng Miao1Xiao Huang2Peng Chen3Ping Zhou4Junxiang Tan5Xiangjun Wang6Rubber Research Institute, Chinese Academy of Tropical Agricultural Sciences, Haikou 571101, ChinaCollege of Earth Sciences, Chengdu University of Technology, Chengdu 610059, ChinaRubber Research Institute, Chinese Academy of Tropical Agricultural Sciences, Haikou 571101, ChinaCollege of Earth Sciences, Chengdu University of Technology, Chengdu 610059, ChinaThe 4th Geological Brigade of Sichuan, Chengdu 611130, ChinaCollege of Earth Sciences, Chengdu University of Technology, Chengdu 610059, ChinaRubber Research Institute, Chinese Academy of Tropical Agricultural Sciences, Haikou 571101, ChinaAccurate individual tree segmentation (ITS) in dense rubber plantations is a challenging task due to overlapping canopies, indistinct tree apexes, and intricate branch structures. To address these challenges, we propose a bottom-up, multi-feature fusion method for segmenting rubber trees using UAV-LiDAR point clouds. Our approach first involves performing a trunk extraction based on branch-point density variations and neighborhood directional features, which allows for the precise separation of trunks from overlapping canopies. Next, we introduce a multi-feature fusion strategy that replaces single-threshold constraints, integrating geometric, directional, and density attributes to classify core canopy points, boundary points, and overlapping regions. Disputed points are then iteratively assigned to adjacent trees based on neighborhood growth angle consistency, enhancing the robustness of the segmentation. Experiments conducted in rubber plantations with varying canopy closure (low, medium, and high) show accuracies of 0.97, 0.98, and 0.95. Additionally, the crown width and canopy projection area derived from the segmented individual tree point clouds are highly consistent with ground truth data, with R<sup>2</sup> values exceeding 0.98 and 0.97, respectively. The proposed method provides a reliable foundation for 3D tree modeling and biomass estimation in structurally complex plantations, advancing precision forestry and ecosystem assessment by overcoming the critical limitations of existing ITS approaches in high-closure tropical agroforests.https://www.mdpi.com/2223-7747/14/11/1640individual tree segmentationLiDAR point cloudsrubber plantationsbottom-up segmentationmulti-feature fusionprecision forestry |
| spellingShingle | Zhipeng Zeng Junpeng Miao Xiao Huang Peng Chen Ping Zhou Junxiang Tan Xiangjun Wang A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging Plants individual tree segmentation LiDAR point clouds rubber plantations bottom-up segmentation multi-feature fusion precision forestry |
| title | A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging |
| title_full | A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging |
| title_fullStr | A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging |
| title_full_unstemmed | A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging |
| title_short | A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle–Light Detecting and Ranging |
| title_sort | bottom up multi feature fusion algorithm for individual tree segmentation in dense rubber tree plantations using unmanned aerial vehicle light detecting and ranging |
| topic | individual tree segmentation LiDAR point clouds rubber plantations bottom-up segmentation multi-feature fusion precision forestry |
| url | https://www.mdpi.com/2223-7747/14/11/1640 |
| work_keys_str_mv | AT zhipengzeng abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT junpengmiao abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT xiaohuang abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT pengchen abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT pingzhou abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT junxiangtan abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT xiangjunwang abottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT zhipengzeng bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT junpengmiao bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT xiaohuang bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT pengchen bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT pingzhou bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT junxiangtan bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging AT xiangjunwang bottomupmultifeaturefusionalgorithmforindividualtreesegmentationindenserubbertreeplantationsusingunmannedaerialvehiclelightdetectingandranging |