ORIGINAL RESEARCH article
Front. Plant Sci.
Sec. Plant Bioinformatics
Volume 16 - 2025 | doi: 10.3389/fpls.2025.1650229
This article is part of the Research TopicInnovative Techniques for Precision Agriculture and Big DataView all articles
CropPhenoX: high-throughput automatic extraction system for wheat seedling phenotypic traits based on software and hardware collaboration
Provisionally accepted
- Anhui Agricultural University, Hefei, 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
Accurately quantifying wheat seedling phenotypic traits is the core of genetic breeding and smart agriculture development. However, existing phenotypic extraction methods predominantly focus on model optimization, resulting in insufficient performance to meet the demands of high-throughput and high-precision detection in complex scenarios. To address this limitation, an automated phenotypic extraction system named CropPhenoX was developed based on software-hardware collaboration. Firstly, the hardware framework was established. The Siemens programmable logic controller (PLC) module was utilized to achieve intelligent scheduling of crop transportation, and the coordinated linkage control of light sources, cameras, and photoelectric switches ensured stable and efficient data acquisition. Additionally, the Modbus transmission control protocol (TCP) was adopted to enable real-time data interaction and remote monitoring. Moreover, the wheat seedling detection model Wheat-RYNet was proposed. This model integrates the detection efficiency of YOLOv5, the lightweight architecture of MobileOne, and the efficient channel attention mechanism (ECA). By implementing an adaptive rotation frame detection strategy, it effectively addresses the detection challenges posed by overlapping and tilted leaves. Finally, a phenotypic traits extraction platform was developed. It could collect high-definition images in real time, extract key traits such as leaf length and width using Wheat-RYNet, and present the results through dynamic visualizations, thereby supporting comprehensive data management throughout the entire process. Experimental results demonstrated that CropPhenoX provided an intelligent and integrated solution for crop phenotyping research, breeding analysis, and field management.
Keywords: CropPhenoX, Phenotypic trait, software-hardware collaboration, wheat, highthroughput detection
Received: 19 Jun 2025; Accepted: 15 Jul 2025.
Copyright: © 2025 Wang, Yang, Wang, Chen, Zhi and Duan. 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: Baohua Yang, Anhui Agricultural University, Hefei, China
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.