StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training

Maize (<i>Zea mays</i> L.), a vital global food crop, relies on its stomatal structure for regulating photosynthesis and responding to drought. Conventional manual stomatal detection methods are inefficient, subjective, and inadequate for high-throughput plant phenotyping research. To ad...

Full description

Saved in:
Bibliographic Details
Main Authors: Ziqi Yang, Yiran Liao, Ziao Chen, Zhenzhen Lin, Wenyuan Huang, Yanxi Liu, Yuling Liu, Yamin Fan, Jie Xu, Lijia Xu, Jiong Mu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Plants
Subjects:
Online Access:https://www.mdpi.com/2223-7747/14/13/2070
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849701728912408576
author Ziqi Yang
Yiran Liao
Ziao Chen
Zhenzhen Lin
Wenyuan Huang
Yanxi Liu
Yuling Liu
Yamin Fan
Jie Xu
Lijia Xu
Jiong Mu
author_facet Ziqi Yang
Yiran Liao
Ziao Chen
Zhenzhen Lin
Wenyuan Huang
Yanxi Liu
Yuling Liu
Yamin Fan
Jie Xu
Lijia Xu
Jiong Mu
author_sort Ziqi Yang
collection DOAJ
description Maize (<i>Zea mays</i> L.), a vital global food crop, relies on its stomatal structure for regulating photosynthesis and responding to drought. Conventional manual stomatal detection methods are inefficient, subjective, and inadequate for high-throughput plant phenotyping research. To address this, we curated a dataset of over 1500 maize leaf epidermal stomata images and developed a novel lightweight detection model, StomaYOLO, tailored for small stomatal targets and subtle features in microscopic images. Leveraging the YOLOv11 framework, StomaYOLO integrates the Small Object Detection layer P2, the dynamic convolution module, and exploits large-scale epidermal cell features to enhance stomatal recognition through auxiliary training. Our model achieved a remarkable 91.8% mean average precision (mAP) and 98.5% precision, surpassing numerous mainstream detection models while maintaining computational efficiency. Ablation and comparative analyses demonstrated that the Small Object Detection layer, dynamic convolutional module, multi-task training, and knowledge distillation strategies substantially enhanced detection performance. Integrating all four strategies yielded a nearly 9% mAP improvement over the baseline model, with computational complexity under 8.4 GFLOPS. Our findings underscore the superior detection capabilities of StomaYOLO compared to existing methods, offering a cost-effective solution that is suitable for practical implementation. This study presents a valuable tool for maize stomatal phenotyping, supporting crop breeding and smart agriculture advancements.
format Article
id doaj-art-1c8fe63d8c2f48feb5cc68d921d53884
institution DOAJ
issn 2223-7747
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Plants
spelling doaj-art-1c8fe63d8c2f48feb5cc68d921d538842025-08-20T03:17:52ZengMDPI AGPlants2223-77472025-07-011413207010.3390/plants14132070StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task TrainingZiqi Yang0Yiran Liao1Ziao Chen2Zhenzhen Lin3Wenyuan Huang4Yanxi Liu5Yuling Liu6Yamin Fan7Jie Xu8Lijia Xu9Jiong Mu10College of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Mechanical and Electrical Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaMaize Research Institute, Sichuan Agricultural University, Chengdu 611130, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaMaize Research Institute, Sichuan Agricultural University, Chengdu 611130, ChinaMaize Research Institute, Sichuan Agricultural University, Chengdu 611130, ChinaMaize Research Institute, Sichuan Agricultural University, Chengdu 611130, ChinaMaize Research Institute, Sichuan Agricultural University, Chengdu 611130, ChinaCollege of Mechanical and Electrical Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaCollege of Information Engineering, Sichuan Agricultural University, Ya’an 625000, ChinaMaize (<i>Zea mays</i> L.), a vital global food crop, relies on its stomatal structure for regulating photosynthesis and responding to drought. Conventional manual stomatal detection methods are inefficient, subjective, and inadequate for high-throughput plant phenotyping research. To address this, we curated a dataset of over 1500 maize leaf epidermal stomata images and developed a novel lightweight detection model, StomaYOLO, tailored for small stomatal targets and subtle features in microscopic images. Leveraging the YOLOv11 framework, StomaYOLO integrates the Small Object Detection layer P2, the dynamic convolution module, and exploits large-scale epidermal cell features to enhance stomatal recognition through auxiliary training. Our model achieved a remarkable 91.8% mean average precision (mAP) and 98.5% precision, surpassing numerous mainstream detection models while maintaining computational efficiency. Ablation and comparative analyses demonstrated that the Small Object Detection layer, dynamic convolutional module, multi-task training, and knowledge distillation strategies substantially enhanced detection performance. Integrating all four strategies yielded a nearly 9% mAP improvement over the baseline model, with computational complexity under 8.4 GFLOPS. Our findings underscore the superior detection capabilities of StomaYOLO compared to existing methods, offering a cost-effective solution that is suitable for practical implementation. This study presents a valuable tool for maize stomatal phenotyping, supporting crop breeding and smart agriculture advancements.https://www.mdpi.com/2223-7747/14/13/2070maize stomaYOLOmulti-task trainingprecision agriculture
spellingShingle Ziqi Yang
Yiran Liao
Ziao Chen
Zhenzhen Lin
Wenyuan Huang
Yanxi Liu
Yuling Liu
Yamin Fan
Jie Xu
Lijia Xu
Jiong Mu
StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
Plants
maize stoma
YOLO
multi-task training
precision agriculture
title StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
title_full StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
title_fullStr StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
title_full_unstemmed StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
title_short StomaYOLO: A Lightweight Maize Phenotypic Stomatal Cell Detector Based on Multi-Task Training
title_sort stomayolo a lightweight maize phenotypic stomatal cell detector based on multi task training
topic maize stoma
YOLO
multi-task training
precision agriculture
url https://www.mdpi.com/2223-7747/14/13/2070
work_keys_str_mv AT ziqiyang stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT yiranliao stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT ziaochen stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT zhenzhenlin stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT wenyuanhuang stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT yanxiliu stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT yulingliu stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT yaminfan stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT jiexu stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT lijiaxu stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining
AT jiongmu stomayoloalightweightmaizephenotypicstomatalcelldetectorbasedonmultitasktraining