EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

BFMambaNet: Boundary-Frequency-Guided Global Semantic Mamba Network for Fine-Grained Camellia oleifera Leaf Disease Segmentation

Xuanhao Li iD, Fulin Su, Yongming Yan, Shaofeng Peng, Lin Li, Fangying Wan, Ruifeng Liu

Plants · 17.08.2026 · 15 (16) · 2493

DOI: 10.3390/plants15162493 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plants, online erschienen am 17.08.2026. Verfasst von Xuanhao Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Yuelushan Laboratory Breeding Program, the Top Ten Technical Research Projects in Hunan Province, the Special Project for the Construction.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camellia oleifera leaf disease segmentation under natural field conditions is important for precision plant protection but remains challenging because lesions often show small target areas, blurred boundaries, uneven illumination, complex backgrounds, and coexisting symptoms. To address these problems, this paper proposes BFMambaNet, a Boundary-Frequency-guided Global Semantic Mamba Network for fine-grained disease segmentation. The model adopts an encoder-decoder framework and introduces a Global Semantic Mamba-based spatial selective feature modeling block to capture long-range lesion context and reduce semantic confusion. A gated wavelet spatial enhancement block is further designed to strengthen high-frequency boundary details while suppressing noisy responses. During training, boundary-frequency auxiliary supervision guides contour localization and pathological texture recovery without additional manual boundary labels. A reinforcement-learning-guided adaptive loss controller adjusts class-wise reweighting factors and loss-component weights according to the training state, improving optimization stability. A pixel-level dataset containing 1400 images and seven disease categories was constructed for evaluation. Experimental results show that BFMambaNet achieves 92.39% Precision, 91.43% Recall, 91.26% Dice, and 85.46% mIoU, outperforming representative CNN-based, Transformer-based, and Mamba-based models. Evaluations on environmental subsets confirm superior robustness, outperforming VMamba by 3.70% mIoU under uneven illumination, 3.55% mIoU under complex backgrounds, and 5.10% mIoU under coexisting symptoms. Cross-dataset validation on Apple leaf diseases further proves its generalization with 3.39% mIoU and 3.84% Dice improvements over U-Mamba, while maintaining a competitive inference speed of 30 FPS. Qualitative results also show clearer boundaries, fewer missed small lesions, and more stable predictions in complex field scenarios.

Schlagwörter

Stichwörter der Autor:innen

Camellia oleiferaMambaboundary-frequency guidancedeep learningdisease segmentation

Autor:innen und Institutionen

  • School of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China.
  • Yuelushan Laboratory, Changsha 410128, China.
  • Hunan Academy of Forestry, Changsha 410004, China.
  • College of Forestry, Central South University of Forestry and Technology, Changsha 410004, China.

ORCID-Profile: Xuanhao Li

Förderung

  • the Yuelushan Laboratory Breeding Program
  • the Top Ten Technical Research Projects in Hunan Province
  • the Special Project for the Construction
  • Operation of the State Key Laboratory of Woody Oil Resources Utilization under the Ministry of Science and Technology of China.

Zitieren

APA

Li, X., Su, F., Yan, Y., Peng, S., Li, L., Wan, F., & Liu, R. (2026). BFMambaNet: Boundary-Frequency-Guided Global Semantic Mamba Network for Fine-Grained Camellia oleifera Leaf Disease Segmentation. Plants, 15(16), 2493. https://doi.org/10.3390/plants15162493

Vancouver

Li X, Su F, Yan Y, Peng S, Li L, Wan F, et al. BFMambaNet: Boundary-Frequency-Guided Global Semantic Mamba Network for Fine-Grained Camellia oleifera Leaf Disease Segmentation. Plants. 2026;15(16):2493. doi:10.3390/plants15162493

BibTeX
@article{Li2026,
  author = {Li, Xuanhao and Su, Fulin and Yan, Yongming and Peng, Shaofeng and Li, Lin and Wan, Fangying and Liu, Ruifeng},
  title = {BFMambaNet: Boundary-Frequency-Guided Global Semantic Mamba Network for Fine-Grained Camellia oleifera Leaf Disease Segmentation},
  journal = {Plants},
  year = {2026},
  volume = {15},
  number = {16},
  pages = {2493},
  doi = {10.3390/plants15162493}
}
Kostenlos starten →