Tree-Main-Part-Extraction Public

This project contains the code and data for the paper "Houyu Liang, Xiang Zhou et al., Tree Main-Part Extraction: A Method for Individual Tree Point Cloud and Parameter Extraction in Complex Forest Environments Integrating Structural Characteristics and Growth Constraint Rules". The main function of this code is to perform individual tree extraction from MLS forest point clouds. The dataset can be downloaded on this page. The code needs to be downloaded from GitHub, and the code link is provided [https://github.com/lhy245/Tree-Main-Part-Extraction.git]. The dataset contains the generated results of "This project" on multiple datasets including: L1W dataset (Henrich et al., 2024), LAUx dataset (Andreas et al., 2022), NIBIO_MLS test dataset (Wielgosz et al., 2024), Boreal3D dataset (Liu et al., 2025), and a self-evaluated dataset (GenHe). The results are stored in the "dataset" folder, with each subfolder named after the original dataset it corresponds to. The "example_data" folder provides the sample dataset used in the code repository [https://github.com/lhy245/Tree-Main-Part-Extraction.git]. Reference Andreas, T., Christoph, G., Tim, R., Arne, N., 2022. LAUTx - Individual Tree Point Clouds from Austrian forest Inventory plots. https://doi.org/10.5281/ZENODO.6560112 Henrich, J., Van Delden, J., Seidel, D., Kneib, T., Ecker, A.S., 2024. TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds. Ecol. Inform. 84, 102888. https://doi.org/10.1016/j.ecoinf.2024.102888 Liu, J., Wang, Duanchu, Gong, H., Wang, C., Zhu, J., Wang, Di, 2025. Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets. https://doi.org/10.48550/ARXIV.2501.03637 Wielgosz, M., Puliti, S., Xiang, B., Schindler, K., Astrup, R., 2024. SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data. Remote Sens. Environ. 313, 114367. https://doi.org/10.1016/j.rse.2024.114367