YOLOv8-FDA: lightweight wheat ear detection and counting in drone images based on improved YOLOv8.

IF 4.1 2区生物学 Q1 PLANT SCIENCES

Frontiers in Plant Science Pub Date : 2025-09-24 eCollection Date: 2025-01-01 DOI:10.3389/fpls.2025.1682243

Yuxuan Lin, Xiao Xiao, Haifeng Lin

{"title":"YOLOv8-FDA: lightweight wheat ear detection and counting in drone images based on improved YOLOv8.","authors":"Yuxuan Lin, Xiao Xiao, Haifeng Lin","doi":"10.3389/fpls.2025.1682243","DOIUrl":null,"url":null,"abstract":"Introduction: Wheat is a vital global staple crop, where accurate ear detection and counting are essential for yield prediction and field management. However, the complexity of field environments poses significant challenges to achieving lightweight yet high-precision detection.Methods: This study proposes YOLOv8-FDA, a lightweight detection and counting method based on YOLOv8. The approach integrates RFAConv for enhanced feature extraction, DySample for efficient multi-scale upsampling, HWD for compressed and accelerated model training, and the SDL loss for improved bounding box regression.Results: Experimental results on the GWHD dataset show that YOLOv8-FDA achieves a precision of 86.3%, recall of 77.5%, and mAP@0.5 of 84.9%, outperforming the original YOLOv8n by significant margins. The model size is 2.96MB with a computational cost of 8.3 GFLOPs, and it operates at 19.2 FPS, enabling real-time counting with over 97.5% accuracy using cross-row segmentation.Discussion: The proposed YOLOv8-FDA model demonstrates strong detection performance, lightweight characteristics, and efficient real-time capability, indicating its high practicality and suitability for deployment in real-world agricultural applications.","PeriodicalId":12632,"journal":{"name":"Frontiers in Plant Science","volume":"16 ","pages":"1682243"},"PeriodicalIF":4.1000,"publicationDate":"2025-09-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12504506/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in Plant Science","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.3389/fpls.2025.1682243","RegionNum":2,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"Q1","JCRName":"PLANT SCIENCES","Score":null,"Total":0}

引用次数: 0

Abstract

Introduction: Wheat is a vital global staple crop, where accurate ear detection and counting are essential for yield prediction and field management. However, the complexity of field environments poses significant challenges to achieving lightweight yet high-precision detection.

Methods: This study proposes YOLOv8-FDA, a lightweight detection and counting method based on YOLOv8. The approach integrates RFAConv for enhanced feature extraction, DySample for efficient multi-scale upsampling, HWD for compressed and accelerated model training, and the SDL loss for improved bounding box regression.

Results: Experimental results on the GWHD dataset show that YOLOv8-FDA achieves a precision of 86.3%, recall of 77.5%, and mAP@0.5 of 84.9%, outperforming the original YOLOv8n by significant margins. The model size is 2.96MB with a computational cost of 8.3 GFLOPs, and it operates at 19.2 FPS, enabling real-time counting with over 97.5% accuracy using cross-row segmentation.

Discussion: The proposed YOLOv8-FDA model demonstrates strong detection performance, lightweight characteristics, and efficient real-time capability, indicating its high practicality and suitability for deployment in real-world agricultural applications.

查看原文本刊更多论文

YOLOv8- fda：基于改进的YOLOv8的无人机图像中轻量级小麦穗检测和计数。

小麦是全球重要的主粮作物，准确的穗检测和计数对产量预测和田间管理至关重要。然而，现场环境的复杂性对实现轻量化、高精度的检测提出了重大挑战。方法：本研究提出了基于YOLOv8的轻量级检测计数方法YOLOv8- fda。该方法集成了用于增强特征提取的RFAConv，用于高效多尺度上采样的DySample，用于压缩和加速模型训练的HWD，以及用于改进边界盒回归的SDL损失。结果：在GWHD数据集上的实验结果表明，YOLOv8-FDA的准确率为86.3%，召回率为77.5%,mAP@0.5为84.9%，明显优于原始的YOLOv8n。模型大小为2.96MB，计算成本为8.3 GFLOPs，运行速度为19.2 FPS，使用交叉行分割实现实时计数，准确率超过97.5%。讨论：提出的YOLOv8-FDA模型具有强大的检测性能、轻量级特性和高效的实时能力，表明其具有很高的实用性和在实际农业应用中部署的适用性。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Frontiers in Plant Science PLANT SCIENCES-

CiteScore

7.30

自引率

14.30%

发文量

4844

审稿时长

14 weeks

期刊介绍： In an ever changing world, plant science is of the utmost importance for securing the future well-being of humankind. Plants provide oxygen, food, feed, fibers, and building materials. In addition, they are a diverse source of industrial and pharmaceutical chemicals. Plants are centrally important to the health of ecosystems, and their understanding is critical for learning how to manage and maintain a sustainable biosphere. Plant science is extremely interdisciplinary, reaching from agricultural science to paleobotany, and molecular physiology to ecology. It uses the latest developments in computer science, optics, molecular biology and genomics to address challenges in model systems, agricultural crops, and ecosystems. Plant science research inquires into the form, function, development, diversity, reproduction, evolution and uses of both higher and lower plants and their interactions with other organisms throughout the biosphere. Frontiers in Plant Science welcomes outstanding contributions in any field of plant science from basic to applied research, from organismal to molecular studies, from single plant analysis to studies of populations and whole ecosystems, and from molecular to biophysical to computational approaches. Frontiers in Plant Science publishes articles on the most outstanding discoveries across a wide research spectrum of Plant Science. The mission of Frontiers in Plant Science is to bring all relevant Plant Science areas together on a single platform.