Real-Time Detection and Counting of Wheat Spikes Based on Improved YOLOv10

计算机科学 稳健性(进化) 人工智能 模式识别(心理学) 特征提取 精确性和召回率 特征(语言学) 背景(考古学) 棱锥(几何) 块(置换群论) 可扩展性 数据挖掘 数学 数据库 古生物学 生物化学 化学 语言学 哲学 几何学 生物 基因
作者
Sitong Guan,Yiming Lin,Guoyu Lin,Peisen Su,Siluo Huang,Xianyong Meng,Pingzeng Liu,Jun Yan
出处
期刊:Agronomy [Multidisciplinary Digital Publishing Institute]
卷期号:14 (9): 1936-1936 被引量:8
标识
DOI:10.3390/agronomy14091936
摘要

Wheat is one of the most crucial food crops globally, with its yield directly impacting global food security. The accurate detection and counting of wheat spikes is essential for monitoring wheat growth, predicting yield, and managing fields. However, the current methods face challenges, such as spike size variation, shading, weed interference, and dense distribution. Conventional machine learning approaches have partially addressed these challenges, yet they are hampered by limited detection accuracy, complexities in feature extraction, and poor robustness under complex field conditions. In this paper, we propose an improved YOLOv10 algorithm that significantly enhances the model’s feature extraction and detection capabilities. This is achieved by introducing a bidirectional feature pyramid network (BiFPN), a separated and enhancement attention module (SEAM), and a global context network (GCNet). BiFPN leverages both top-down and bottom-up bidirectional paths to achieve multi-scale feature fusion, improving performance in detecting targets of various scales. SEAM enhances feature representation quality and model performance in complex environments by separately augmenting the attention mechanism for channel and spatial features. GCNet captures long-range dependencies in the image through the global context block, enabling the model to process complex information more accurately. The experimental results demonstrate that our method achieved a precision of 93.69%, a recall of 91.70%, and a mean average precision (mAP) of 95.10% in wheat spike detection, outperforming the benchmark YOLOv10 model by 2.02% in precision, 2.92% in recall, and 1.56% in mAP. Additionally, the coefficient of determination (R2) between the detected and manually counted wheat spikes was 0.96, with a mean absolute error (MAE) of 3.57 and a root-mean-square error (RMSE) of 4.09, indicating strong correlation and high accuracy. The improved YOLOv10 algorithm effectively solves the difficult problem of wheat spike detection under complex field conditions, providing strong support for agricultural production and research.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
小潘完成签到 ,获得积分10
刚刚
小奕完成签到,获得积分10
刚刚
默默荔枝完成签到 ,获得积分10
1秒前
清秀不言完成签到 ,获得积分10
1秒前
酷小裤完成签到,获得积分10
2秒前
酷炫翠桃完成签到,获得积分10
3秒前
范德萨范德萨完成签到,获得积分10
3秒前
支雨泽完成签到,获得积分10
4秒前
周芷卉发布了新的文献求助10
5秒前
美丽的仙人掌完成签到,获得积分10
7秒前
喏晨完成签到 ,获得积分10
7秒前
喵喵完成签到 ,获得积分10
7秒前
yiyao完成签到,获得积分10
8秒前
10秒前
友好的钢笔完成签到 ,获得积分10
10秒前
Ziyi_Xu完成签到,获得积分10
10秒前
大模型应助WCheng采纳,获得10
10秒前
violetlishu完成签到 ,获得积分10
13秒前
松思完成签到,获得积分10
14秒前
学业顺利完成签到,获得积分10
14秒前
orangelion完成签到,获得积分10
15秒前
老木虫发布了新的文献求助10
15秒前
哇哈完成签到 ,获得积分10
16秒前
kangshuai完成签到,获得积分10
16秒前
皛皛完成签到 ,获得积分10
17秒前
奋斗的夜山完成签到 ,获得积分10
18秒前
01259完成签到 ,获得积分10
19秒前
刚睡醒完成签到,获得积分10
20秒前
20秒前
重要的惜萍完成签到,获得积分10
21秒前
少年旭完成签到,获得积分10
21秒前
摸鱼鱼完成签到,获得积分10
24秒前
爆米花完成签到,获得积分10
24秒前
25秒前
w婷完成签到 ,获得积分10
25秒前
研友_ZzrWKZ完成签到 ,获得积分10
26秒前
科研通AI5应助老木虫采纳,获得10
26秒前
壮观复天完成签到 ,获得积分10
26秒前
河马完成签到,获得积分10
27秒前
奶油蜜豆卷完成签到,获得积分10
29秒前
高分求助中
Continuum Thermodynamics and Material Modelling 2000
江岸区志(下卷) 800
Wind energy generation systems - Part 3-2: Design requirements for floating offshore wind turbines 600
こんなに痛いのにどうして「なんでもない」と医者にいわれてしまうのでしょうか 510
Seven new species of the Palaearctic Lauxaniidae and Asteiidae (Diptera) 400
A method for calculating the flow in a centrifugal impeller when entropy gradients are present 240
Global Higher Education Practices in Times of Crisis: Questions for Sustainability and Digitalization 200
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3695165
求助须知:如何正确求助?哪些是违规求助? 3246694
关于积分的说明 9850684
捐赠科研通 2958298
什么是DOI,文献DOI怎么找? 1622050
邀请新用户注册赠送积分活动 767750
科研通“疑难数据库(出版商)”最低求助积分说明 741256