EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TB-DLossNet: Fine-Grained Segmentation of Tea Leaf Diseases Based on Semantic-Visual Fusion

Shuqi Zheng, Hao Zhou, Ziyang Shi, Fulin Su, Wei Shi, Ruifeng Liu, Lin Li, Fangying Wan

Plants · 27.03.2026 · 15 (7) · 1035

DOI: 10.3390/plants15071035 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Plants, online erschienen am 27.03.2026. Verfasst von Shuqi Zheng und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Hunan Forestry Department, Education Department Key Program of Hunan Province, Hunan Provincial Science and Technology Innovation Program Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Camellia oleifera is an economically vital woody oil crop. Its productivity and oil quality are severely compromised by various diseases. Implementing pixel-level lesion segmentation within complex field environments is crucial for advancing precision plant protection. Despite recent progress, existing segmentation methods struggle with three primary challenges: semantic ambiguity arising from evolving pathological stages, blurred boundaries due to overlapping lesions, and the high omission rate of micro-lesions. To address these issues, this paper presents TB-DLossNet (Text-Conditioned Boundary-Aware Network with Dynamic Loss Reweighting), a novel segmentation framework based on semantic-visual multi-modal fusion. Leveraging VMamba as the visual backbone, the proposed model innovatively integrates BERT-encoded structured text as an auxiliary modality to resolve visual ambiguities through cross-modal semantic guidance. Furthermore, a boundary enhancement branch is incorporated alongside a multi-scale deep supervision strategy to mitigate boundary displacement and ensure the topological continuity of lesion structures. To tackle the detection of small-scale targets, we designed a dynamic weight loss function conditioned on lesion area, significantly bolstering the model’s sensitivity to minute pathological features. Additionally, to alleviate the scarcity of high-quality data, we curated a comprehensive multi-modal dataset encompassing seven typical diseases of Camellia oleifera. Experimental results demonstrate that TB-DLossNet achieves a Mean Intersection over Union (mIoU) of 87.02%, outperforming the state-of-the-art unimodal VMamba and multimodal Lvit by 4.9% and 2.59%, respectively. Qualitative evaluations confirm that our model exhibits lower false-negative rates and superior boundary-fitting precision in heterogeneous field scenarios. Finally, generalization tests on an apple disease dataset further validate the robustness and transferability of the proposed framework.

Schlagwörter

Stichwörter der Autor:innen

Camellia oleiferaVMambadeep learningmultimodal integrationpest and disease segmentation

Autor:innen und Institutionen

  • School of Electronic Information and Physics, Central South University of Forestry and Technology, Changsha 410004, China.
  • College of Forestry, Central South University of Forestry and Technology, Changsha 410004, China.

Förderung

  • Hunan Forestry Department
  • Education Department Key Program of Hunan Province
  • Hunan Provincial Science and Technology Innovation Program Project
  • National Natural Science Foundation of China
  • School of Electrical and Information Engineering, Hunan Institute of Engineering
  • National Natural Science Foundation of China https://ror.org/01h0zpd94
  • School of Electrical and Information Engineering, Hunan Institute of Engineering https://ror.org/03zj2rn70

Zitieren

APA

Zheng, S., Zhou, H., Shi, Z., Su, F., Shi, W., Liu, R., Li, L., & Wan, F. (2026). TB-DLossNet: Fine-Grained Segmentation of Tea Leaf Diseases Based on Semantic-Visual Fusion. Plants, 15(7), 1035. https://doi.org/10.3390/plants15071035

Vancouver

Zheng S, Zhou H, Shi Z, Su F, Shi W, Liu R, et al. TB-DLossNet: Fine-Grained Segmentation of Tea Leaf Diseases Based on Semantic-Visual Fusion. Plants. 2026;15(7):1035. doi:10.3390/plants15071035

BibTeX
@article{Zheng2026,
  author = {Zheng, Shuqi and Zhou, Hao and Shi, Ziyang and Su, Fulin and Shi, Wei and Liu, Ruifeng and Li, Lin and Wan, Fangying},
  title = {TB-DLossNet: Fine-Grained Segmentation of Tea Leaf Diseases Based on Semantic-Visual Fusion},
  journal = {Plants},
  year = {2026},
  volume = {15},
  number = {7},
  pages = {1035},
  doi = {10.3390/plants15071035}
}
Kostenlos starten →