EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AF-RT-DETR: Adaptive cross-scale feature interaction for real-time plant disease detection in complex field environments

Ming Liu, Jiangrong Liu, Ziqi Mao, Shuzhe Cheng, Xinyang Li, Shiyu Yan

Frontiers in Plant Science · 10.04.2026 · 17

DOI: 10.3389/fpls.2026.1788655 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Plant Science, online erschienen am 10.04.2026. Verfasst von Ming Liu und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Accurate plant disease identification is of great importance for ensuring agricultural productivity and food security. However, complex illumination variations, leaf occlusion, and diverse disease spot scales throughout plant growth stages significantly increase the difficulty of real-time detection, leading to limited accuracy and robustness in existing approaches.

Methods

To address these challenges, we propose an improved RT-DETRv2-based plant disease detection model, termed AF-RT-DETR. A Bidirectional Cross Gate (BCG) module is introduced in the feature extraction stage to reduce channel redundancy and enhance discriminative feature representation through multi-level feature interactions. The original RepVGG structure is replaced with a Dynamic Channel Shift (DCS) module, effectively enlarging the receptive field and strengthening contextual feature fusion without additional computational overhead. Additionally, an improved Scale-aware Multi-level Loss (SML) emphasizes low-quality feature maps to improve detector robustness.

Results

The model achieves mAP50 and mAP50:95 of 93.6% and 67.2% on the Plant-Disease dataset, surpassing the baseline by 5.1% and 4.5%. Furthermore, the model was evaluated on multiple crops and growth stages under diverse field conditions, demonstrating robust performance and adaptability.

Discussion

These results indicate that AF-RT-DETR effectively enables real-time plant disease detection in complex field environments.

Schlagwörter

Stichwörter der Autor:innen

RT-DETRv2disease detectionfeature extractionfeature fusionobject detection

Autor:innen und Institutionen

  • School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China.
  • School of Computer and Artificial Intelligence, Wuhan Textile University, Wuhan, China.
  • China Railway 11th Bureau Group Xi'an Construction Co., Ltd., Xi'an, China.

Zitieren

APA

Liu, M., Liu, J., Mao, Z., Cheng, S., Li, X., & Yan, S. (2026). AF-RT-DETR: Adaptive cross-scale feature interaction for real-time plant disease detection in complex field environments. Frontiers in Plant Science, 17. https://doi.org/10.3389/fpls.2026.1788655

Vancouver

Liu M, Liu J, Mao Z, Cheng S, Li X, Yan S. AF-RT-DETR: Adaptive cross-scale feature interaction for real-time plant disease detection in complex field environments. Frontiers in Plant Science. 2026;17. doi:10.3389/fpls.2026.1788655

BibTeX
@article{Liu2026,
  author = {Liu, Ming and Liu, Jiangrong and Mao, Ziqi and Cheng, Shuzhe and Li, Xinyang and Yan, Shiyu},
  title = {AF-RT-DETR: Adaptive cross-scale feature interaction for real-time plant disease detection in complex field environments},
  journal = {Frontiers in Plant Science},
  year = {2026},
  volume = {17},
  doi = {10.3389/fpls.2026.1788655}
}
Kostenlos starten →