[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2523":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":26,"view_count":32,"doi":33,"paper":34,"created_at":64},2523,"Deep learning-based detection and counting of wheat seeds: Comparative benchmarking of YOLO models","https:\u002F\u002Fdoi.org\u002F10.56612\u002Fijaaeb.v6i1.249","Automated wheat-seed detection and counting play important roles in high-throughput plant phenotyping, seed characterization, and agricultural research. Conventional manual counting is labor-intensive, time-consuming, and susceptible to human error when processing large numbers of seed samples. Recent advances in deep learning and object detection provide opportunities to automate these tasks using conventional RGB images. This study focused on a deep learning-based framework for wheat-seed detection and detection-based counting using a custom red-green-blue (RGB) image dataset. A dataset comprising 832 RGB images containing 3,649 manually annotated wheat-seed instances was developed, with images representing one to ten detached wheat seeds per image. All seed instances were manually annotated using bounding boxes and formulated as a single-class object detection problem. Two lightweight object detection models, YOLOv8n and YOLO11n, were trained and evaluated under identical experimental conditions. The model performance was assessed using precision, recall, mean Average Precision at an Intersection over Union (IoU) threshold of 0.5 (mAP@0.5), mean Average Precision averaged across IoU thresholds from 0.5 to 0.95 (mAP@0.5:0.95), training loss curves, confidence-based performance curves, confusion matrices, and qualitative detection outputs. Both models achieved excellent detection performance on the custom wheat seed dataset. YOLOv8n achieved a precision of 0.9947, recall of 0.9963, mAP@0.5 of 0.9940, and mAP@0.5:0.95 of 0.5284. YOLO11n produced slightly higher performance, achieving a precision of 0.9988, recall of 0.9984, mAP@0.5 of 0.9950, and mAP@0.5:0.95 of 0.5385. Overall, the performance of the two models was similar at mAP@0.5, but at mAP@0.5:0.95 stricter criterion, YOLO11n consistently demonstrated the strongest overall performance. The findings show that lightweight YOLO models combined with RGB imaging provide an effective and easy way for automated localization and counting of wheat seeds. ​The framework provides a manually annotated RGB wheat-seed dataset and a reproducible benchmark to compare lightweight YOLO models for detection. This study provides a practical foundation for future research on automated seed phenotyping, with future work focusing on external validation using more diverse datasets, multi-class seed-quality assessment, and quantitative evaluation of counting performance.","自动化小麦种子检测与计数在高通量植物表型分析、种子表征和农业研究中发挥着重要作用。传统的人工计数在处理大量种子样本时劳动强度大、耗时长且易受人为误差影响。近年来深度学习和目标检测的进展为利用常规RGB图像实现这些任务的自动化提供了机遇。本研究聚焦于基于深度学习的框架，利用自定义红绿蓝（RGB）图像数据集进行小麦种子检测及基于检测的计数。构建了一个包含832张RGB图像、3，649个手动标注小麦种子实例的数据集，图像中每张包含一到十粒脱离的小麦种子。所有种子实例均使用边界框进行手动标注，并形式化为单类目标检测问题。在相同实验条件下训练和评估了两种轻量级目标检测模型YOLOv8n和YOLO11n。采用精确率、召回率、交并比（IoU）阈值为0.5时的平均精度均值（mAP@0.5）、IoU阈值从0.5到0.95的平均精度均值（mAP@0.5:0.95）、训练损失曲线、基于置信度的性能曲线、混淆矩阵以及定性检测输出对模型性能进行了评估。两种模型在自定义小麦种子数据集上均取得了优异的检测性能。YOLOv8n的精确率为0.9947，召回率为0.9963，mAP@0.5为0.9940，mAP@0.5:0.95为0.5284。YOLO11n的性能略高，精确率为0.9988，召回率为0.9984，mAP@0.5为0.9950，mAP@0.5:0.95为0.5385。总体而言，两种模型在mAP@0.5上的性能相似，但在mAP@0.5:0.95这一更严格的指标下，YOLO11n始终展现出最强的整体性能。研究结果表明，轻量级YOLO模型结合RGB成像为小麦种子的自动化定位和计数提供了一种有效且简便的方法。该框架提供了一个手动标注的RGB小麦种子数据集和一个可重复的基准，用于比较轻量级YOLO模型的检测性能。本研究为未来自动化种子表型分析研究提供了实用基础，未来工作将侧重于使用更多样化数据集进行外部验证、多类种子质量评估以及计数性能的定量评价。",null,"International Journal of Applied and Experimental Biology","2026-09-14T00:00:00Z","论文",10,false,73,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},15,20,17,13,8,1,"基于自建RGB数据集对YOLOv8n与YOLO11n进行小麦种子检测计数对比，方法清晰、指标完整，属细分领域可复现基准研究，对自动化种子表型有实用参考价值。",[25],{"name":10,"url":6},[27,28,29,30,31],"智慧农业","农业人工智能","小麦","高通量表型","种子检测",0,"10.56612\u002Fijaaeb.v6i1.249",{"doi":33,"openalex_id":35,"authors":36,"venue":10,"cited_by_count":32,"oa_url":6,"card":57,"direction":61,"ingested_from":63},"W7212562005",[37,40,42,45,47,49,51,53,55],{"name":38,"orcid":39},"Faisal Shahzad","https:\u002F\u002Forcid.org\u002F0009-0003-8413-2456",{"name":41,"orcid":9},"Hafiza Ayesha Arshad",{"name":43,"orcid":44},"Habib‐ur‐Rehman Athar","https:\u002F\u002Forcid.org\u002F0000-0002-8733-3865",{"name":46,"orcid":9},"Israr Hanif",{"name":48,"orcid":9},"Iqra Shokat",{"name":50,"orcid":9},"Ayesha Maryam",{"name":52,"orcid":9},"Laiba Urooj",{"name":54,"orcid":9},"Jaweria Maqbool",{"name":56,"orcid":9},"Aleena Akram",{"tldr":58,"method":59,"finding":60,"direction":61,"opportunity":62},"用自建RGB小麦种子数据集对比YOLOv8n与YOLO11n的检测计数性能。","832张RGB图像、3649个标注框，训练YOLOv8n与YOLO11n并多指标","两模型mAP@0.5均超0.994，YOLO11n在严格指标mAP@0.5:0.95上更优。","农业遥感与作物表型","可扩展多品种、多类别种子质量评估，并引入更复杂背景与计数精度量化验证。","openalex","2026-09-15T23:30:17.202179Z"]