TM-WSNet: A precise segmentation method for individual rubber trees based on UAV LiDAR point cloud
文献类型： 外文期刊
作者： Yan, Lele 1 ; Zhou, Guoxiong 1 ; Yan, Miying 1 ; Wang, Xiangjun 2 ;
作者机构： 1.Cent South Univ Forestry & Technol, Changsha 410004, Peoples R China
2.Chinese Acad Trop Agr Sci, Rubber Res Inst, Haikou 571101, Hainan, Peoples R China
关键词： Rubber tree segmentation; Hybrid feature extraction module; Wavelet grid sampling; Multi-level feature fusion; Scale optimization algorithm
期刊名称：PLANT PHENOMICS （ 影响因子：6.4； 五年影响因子：7.1 ）
ISSN： 2643-6515
年卷期： 2025 年 7 卷 3 期
页码：
收录情况： SCI
摘要： Rubber products have become an important strategic resource in the global economy. However, individual rubber tree segmentation in plantation environments remains challenging due to canopy background interference and significant morphological variations among trees. To address these issues, we propose a high-precision segmentation network,TM-WSNet (Spatial Geometry Enhanced Hybrid Feature Extraction Module-Wavelet Grid Feature Fusion Encoder Segmentation Network). First, we introduce SGTramba, a hybrid feature extraction module combining Grouped Transformer and Mamba architectures, designed to reduce confusion between tree crown boundaries and surrounding vegetation or background elements. Second, we propose the WGMS encoder, which enhances structural feature recognition by applying wavelet-based spatial grid downsampling and multiscale feature fusion, effectively handling variations in canopy shape and tree height. Third, a scale optimization algorithm (SCPO) is developed to adaptively search for the optimal learning rate, addressing uneven learning across different resolution scales. We evaluate TM-WSNet on a self-constructed dataset (RubberTree) and two public datasets (ShapeNetPart and ForestSemantic), where it consistently achieves high segmentation accuracy and robustness. In practical field tests, our method accurately predicts key rubber tree parameters-height, crown width, and diameter at breast height with coefficients of determination (R2) of 1.00, 0.99, and 0.89, respectively. These results demonstrate TM-WSNet's strong potential for supporting precision rubber yield estimation and health monitoring in complex plantation environments.
- 相关文献
作者其他论文 更多>>
-
A Bottom-Up Multi-Feature Fusion Algorithm for Individual Tree Segmentation in Dense Rubber Tree Plantations Using Unmanned Aerial Vehicle-Light Detecting and Ranging
作者：Zeng, Zhipeng;Huang, Xiao;Wang, Xiangjun;Zeng, Zhipeng;Miao, Junpeng;Chen, Peng;Tan, Junxiang;Zeng, Zhipeng;Zhou, Ping
关键词：individual tree segmentation; LiDAR point clouds; rubber plantations; bottom-up segmentation; multi-feature fusion; precision forestry
-
RsegNet: An Advanced Methodology for Individual Rubber Tree Segmentation and Structural Parameter Extraction from UAV LiDAR Point Clouds
作者：Wang, Hengrui;Ye, Zilin;Zhang, Qin;Wang, Mingfang;Zhou, Guoxiong;Li, Li;Lin, Shuqi;Wang, Xiangjun
关键词：Rubber tree point cloud segmentation; RsegNet; CosineU-Net; Dual-channel clustering module; Dynamic clustering optimization algorithm
-
A high-precision segmentation method for rubber tree stone cells
作者：Pan, Meixi;Zhou, Guoxiong;Yu, Yunlong;Yang, Jin;Zhao, Tianrui;Liu, Genhua;Zhang, Yuanyuan
关键词：Rubber tree stone cells; low-rank KAN module; wave-SC module; CGWO optimization algorithm
-
Phenotypic and transcriptomic analysis reveals key genes associated with plant height in rubber tree and functional characterization of the candidate gene HbFLA11
作者：Yang, Baoyi;Zhang, Yuanyuan;Li, Weiguo;Huang, Xiao;Gao, Xinsheng;Wang, Xiangjun;Yang, Baoyi;Qi, Juncang;Yang, Baoyi
关键词：
-
A Fine-Scale Segmentation Method for Individual Rubber Trees Based on UAV LiDAR Point Cloud
作者：Li, Li;Ye, Zilin;Li, Hao;Yan, Miying;Zhou, Guoxiong;Wang, Hengrui;Wang, Xiangjun;Lv, Mingjie
关键词：Vegetation; Rubber; Point cloud compression; Noise; Accuracy; Image segmentation; Feature extraction; Forests; Deep learning; Optimization; Adaptive coati particle optimization algorithm; cosine-space cross attention (CSCA); multiscale feature aggregation (MSFA) module; rubber tree fine segmentation
-
A framework for phenotyping rubber trees under intense wind stress using laser scanning and digital twin technology
作者：Yun, Ting;Yun, Ting;Yuan, Xinyue;Fang, Wenjie;Lu, Xin;Eichhorn, Markus P.;Jin, Shichao;Wang, Xiangjun;Zhang, Huaiqing
关键词：Rubber tree phenotyping; Wind stress; Aerodynamic model; Computer graphics; Terrestrial laser scanning; Digital twin
-
Genome-wide identification of rubber tree PILS auxin transporter gene families and functional characterization of HbPILS6
作者：Yang, Baoyi;Li, Weifang;Huang, Xiao;Zhang, Yuanyuan;Gao, Xinsheng;Ding, Shitao;Wang, Yao;Wang, Xiangjun;Yang, Baoyi;Qi, Juncang
关键词：
Hevea brasiliensis ;PIN-LIKES (PILS) gene family;HbPILS6 ; Plant height regulation; Auxin signaling; Stress response
