A lightweight LiDAR-SLAM system integrated with semantic segmentation for the acquisition of forest biomass parameters
Research paper
Key message
We propose a lightweight LiDAR-based simultaneous localization and mapping system that integrates semantic segmentation. The system was evaluated on forest point clouds collected in real-world forest environments and on multiple publicly available datasets. Results demonstrate that the proposed system is both efficient and accurate for individual-tree clustering and diameter at breast height estimation.
Keywords
3D LiDAR; Point cloud; Semantic segmentation
Publication
Zhao, Y., Zhao, S., Zhou, Y. et al. A lightweight LiDAR-SLAM system integrated with semantic segmentation for the acquisition of forest biomass parameters. Annals of Forest Science 83, 21 (2026). https://doi.org/10.1186/s13595-026-01336-8
Data availability
The raw point cloud data recorded by LiDAR has been uploaded to the GitHub repository, and the link is: https://github.com/xiaopengfly513/FSMD.
Handling editor
Shengli Tao