EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Improved YOLOv8 for Tree Species Detection Using Bark Texture Features

Jihao Yu, Zhelin Cui, Xiaofeng Geng, Yannan Xu, Qizhe Yu

Applied Sciences · 06.06.2026 · 16 (12) · 5726

DOI: 10.3390/app16125726 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 06.06.2026. Verfasst von Jihao Yu und 4 weiteren Autor:innen. Die Arbeit nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Jiangsu Forestry Science and Technology Innovation and Promotion Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tree bark is a relatively stable visual feature for tree species detection because it remains visible throughout the year and is less affected by seasonal changes than leaves or flowers. However, bark-texture-based tree species detection in natural scenes remains challenging because of limited dedicated datasets, subtle inter-class texture differences, complex backgrounds, and scale variation. This work evaluated whether task-oriented multi-scale feature fusion and attention-based feature enhancement can improve YOLOv8s for bark-texture-based tree species detection. To this end, the Tree_bark dataset was constructed, containing 134 annotated classes and 8216 valid images, and YOLOv8s was used as the baseline detector. Three multi-scale enhancement strategies, three lightweight attention mechanisms, and their fused configuration were systematically compared under the same data split and evaluation setting. On the validation set, the baseline YOLOv8s achieved a mAP@0.5 of 0.443, a mAP@0.5:0.95 of 0.339, and a Recall of 0.400. The final fused D1 model, combining WeightedConcat_B1 and EMA, showed the highest overall performance among the compared settings under the current experimental setting, with a mAP@0.5 of 0.485, a mAP@0.5:0.95 of 0.365, and a Recall of 0.435. Compared with the baseline, D1 improved mAP@0.5 by 0.042, mAP@0.5:0.95 by 0.026, and Recall by 0.035. These results indicate that moderate adaptive multi-scale fusion and lightweight attention enhancement can improve bark-texture-based tree species detection in complex natural scenes. The proposed framework provides a useful reference for fine-grained tree species detection based on bark texture, although further validation across broader regions and more complex field conditions is still needed.

Förderung

  • Jiangsu Forestry Science and Technology Innovation and Promotion Project

Zitieren

APA

Yu, J., Cui, Z., Geng, X., Xu, Y., & Yu, Q. (2026). Improved YOLOv8 for Tree Species Detection Using Bark Texture Features. Applied Sciences, 16(12), 5726. https://doi.org/10.3390/app16125726

Vancouver

Yu J, Cui Z, Geng X, Xu Y, Yu Q. Improved YOLOv8 for Tree Species Detection Using Bark Texture Features. Applied Sciences. 2026;16(12):5726. doi:10.3390/app16125726

BibTeX
@article{Yu2026,
  author = {Yu, Jihao and Cui, Zhelin and Geng, Xiaofeng and Xu, Yannan and Yu, Qizhe},
  title = {Improved YOLOv8 for Tree Species Detection Using Bark Texture Features},
  journal = {Applied Sciences},
  year = {2026},
  volume = {16},
  number = {12},
  pages = {5726},
  doi = {10.3390/app16125726}
}
Kostenlos starten →