EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FA-CTNet: A Geometry-Aware Deep Learning Approach for Tree Species Classification from LiDAR Point Clouds

Shengchao Sha, Qianhui Liu, Yan Zhang, Ting Yun

Remote Sensing · 24.04.2026 · 18 (9) · 1311

DOI: 10.3390/rs18091311 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 24.04.2026. Verfasst von Shengchao Sha und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Rubber Research Institute.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate identification of tree species is important for forest management, biodiversity studies, and precision forestry. Near-range LiDAR point clouds provide detailed three-dimensional information about individual trees. However, the complex structure of the point clouds and the unbalanced distribution of species make automatic classification difficult. To address these issues, this study presents a Transformer model with geometric enhancement. The model combines local geometric features and global attention to improve species recognition in forest environments. It uses geometric information with biological meaning, including point cloud normals, local density, vertical structure, and growth direction. A focal loss with class balance is also introduced to reduce the impact of species distributions with long tails. Experiments on the ForSpecial20K dataset show that the proposed method performs better than representative models based on convolution, graph methods, and Transformer architectures. It achieves higher overall accuracy (78.20%), higher mean class accuracy (73.48%), and a higher Macro-F1 score (73.21%). Results from confusion matrices and visual analysis of similar species further verify the effectiveness of the geometric features and the loss design. These results suggest that modeling structural information of forests helps improve robustness and generalization. The proposed method offers a practical solution for tree-level species mapping, fusion of LiDAR data from multiple sources, and fine-scale forest inventory. It also shows the value of combining high-resolution LiDAR data with deep learning for forestry applications.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Rubber Research Institute
  • Innovation and Entrepreneurship Training Project for Undergraduates in Jiangsu Province

Zitieren

APA

Sha, S., Liu, Q., Zhang, Y., & Yun, T. (2026). FA-CTNet: A Geometry-Aware Deep Learning Approach for Tree Species Classification from LiDAR Point Clouds. Remote Sensing, 18(9), 1311. https://doi.org/10.3390/rs18091311

Vancouver

Sha S, Liu Q, Zhang Y, Yun T. FA-CTNet: A Geometry-Aware Deep Learning Approach for Tree Species Classification from LiDAR Point Clouds. Remote Sensing. 2026;18(9):1311. doi:10.3390/rs18091311

BibTeX
@article{Sha2026,
  author = {Sha, Shengchao and Liu, Qianhui and Zhang, Yan and Yun, Ting},
  title = {FA-CTNet: A Geometry-Aware Deep Learning Approach for Tree Species Classification from LiDAR Point Clouds},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {9},
  pages = {1311},
  doi = {10.3390/rs18091311}
}
Kostenlos starten →