ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Sustainable and Intelligent Phytoprotection
This article is part of the Research TopicTransformative AI-Driven Platforms: Revolutionizing Crop Phenotyping With UAV, Proximal, And Ground TechnologiesView all articles
Focal-HAIN: A Lightweight Model with Adaptive Modulation and Hierarchical Interaction for Real-Time Crop Pest and Disease Monitoring
Provisionally accepted
- Changzhou College of Information Technology, Changzhou, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
To address the problems of low detection accuracy, severe background interference and poor real-time performance existing in the current object detection models in complex agricultural monitoring scenarios, we proposed Focal-HAIN(F-HAIN), a lightweight object detection model tailored for embedded platforms. Built on the YOLOv5 architecture with design insights from RT-DETR, the proposed model incorporates two key structural enhancements to improve multi-scale feature representation and localization precision. Firstly, focus modulation was integrated into the neck network, and the F-SPPELAN module was designed to achieve adaptive and precise modulation of the feature channel based on the focus loss-guided attention mechanism. This module effectively suppresses background noise and enhances the model's response to small targets. Secondly, the HAIN module is constructed. By introducing the deep interlacing fusion strategy, the feature interaction operations within the scale are embedded into the cross-scale feature aggregation path, thereby enhancing the correlation among multi-scale features and improving the positioning accuracy. This study conducted comprehensive experiments on the IP102 dataset and deployed the model on a Raspberry Pi 4B embedded device for real-time performance verification. The experimental results show that the mAP50 of F-HAIN can reach 90.1%. Under the same experimental conditions, compared with models such as RT-DETR, YOLOv5, YOLOv8, YOLOv10 and YOLOv11, the performance of F-HAIN on mAP50 has increased by 5.5%, 6.8%, 4.9%, 5.4% and 3% respectively. Meanwhile, F-HAIN maintains a high-speed inference of 161 FPS on a high-performance workstation, and is successfully deployed in an IoT-based collaborative system where a Raspberry Pi 4B serves as the edge acquisition terminal.
Keywords: Crop Pest and Disease Detection, Focal Modulation, HAIN, Lightweight, Real-time monitoring
Received: 31 Dec 2025; Accepted: 14 Feb 2026.
Copyright: © 2026 Liu, Xu, Chang and Long. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Wei Liu
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.