Lightweight target detection for the field flat jujube based on improved YOLOv5

棱锥(几何) 人工智能 特征(语言学) 增采样 计算机科学 特征提取 目标检测 行人检测 卷积(计算机科学) 模式识别(心理学) 领域(数学) 计算机视觉 探测器 算法 图像(数学) 人工神经网络 数学 工程类 电信 哲学 语言学 纯数学 运输工程 行人 几何学
作者
Shi-Lin Li,Shujuan Zhang,Jianxin Xue,Haixia Sun
出处
期刊:Computers and Electronics in Agriculture [Elsevier BV]
卷期号:202: 107391-107391 被引量:52
标识
DOI:10.1016/j.compag.2022.107391
摘要

The efficient detection of the flat jujube in a complex natural environment has great significance in intelligent agricultural operations. Aiming at the problems of the low detection efficiency of field flat jujubes and complex target detection algorithms that are difficult to deploy on low-cost equipment, an improved lightweight algorithm based on You Only Look Once (YOLOv5) is proposed. First, the method screens for the multiscale detection structure that is suitable for the flat jujube by adjusting the number of layers of target detection, which improves the accuracy of detection and reduces the nuisance parameter. Then, multiscale feature fusion is achieved more efficiently by using the bidirectional feature pyramid network (BiFPN), and the feature extraction capability of the model is further improved by introducing a dual coordinate attention mechanism. Finally, the method reduces the difficulties of the model by introducing depthwise separable convolution and adding a ghost module after upsampling layers. The experimental results showed that the mean average precision (mAP) and model size of the lightweight network reached 97.2 % and 7.1 MB. Compared with the YOLOv5 baseline network, the parameters decreased by 49.15 %, while the mAP increased by 1.8 %. The method further improved algorithm performance and reduced computational cost compared with the mainstream one-stage target detection algorithms of the YOLOv5s, YOLOx_s, YOLOv4, YOLOv3 and single shot multibox detector (SSD). Compared to these algorithms, the mAP of the proposed improved model increased by 1.8 %, 0.9 %, 5.5 %, 6.5 % and 2.9 %, respectively. Meanwhile, the model size was compressed by 49.15 %, 73.99 %, 94.42 %, 94.24 % and 86.69 %, respectively. The improved algorithm has higher detection accuracy, while reducing the calculations and parameters, which reduces the dependence on hardware and provides a reference for deploying automated picking of the field flat jujube.
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
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

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
SYLH应助科研通管家采纳,获得10
刚刚
Ava应助科研通管家采纳,获得10
刚刚
充电宝应助科研通管家采纳,获得10
刚刚
神的女人发布了新的文献求助10
刚刚
pcr163应助科研通管家采纳,获得30
刚刚
Liufgui应助科研通管家采纳,获得20
刚刚
褪黑素应助科研通管家采纳,获得10
刚刚
刚刚
刚刚
刚刚
刚刚
刚刚
刚刚
刚刚
SYLH应助科研通管家采纳,获得20
刚刚
MchemG应助Qianyun采纳,获得30
2秒前
2秒前
2秒前
2秒前
Knight-1124发布了新的文献求助10
2秒前
2秒前
华仔应助徐智秀采纳,获得10
2秒前
2秒前
旺旺旺完成签到,获得积分20
3秒前
4秒前
和谐一万发布了新的文献求助10
5秒前
可口可乐发布了新的文献求助10
5秒前
6秒前
6秒前
6秒前
程之杭完成签到,获得积分10
7秒前
战战发布了新的文献求助10
7秒前
zengwr发布了新的文献求助10
9秒前
科研助手6应助神的女人采纳,获得10
10秒前
呼呼啦呼啦完成签到,获得积分10
11秒前
11秒前
Jasper应助sylnd126采纳,获得10
11秒前
哈哈发布了新的文献求助20
13秒前
Anita完成签到,获得积分10
13秒前
所所应助和谐一万采纳,获得10
14秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3988732
求助须知:如何正确求助?哪些是违规求助? 3531027
关于积分的说明 11252281
捐赠科研通 3269732
什么是DOI,文献DOI怎么找? 1804764
邀请新用户注册赠送积分活动 881869
科研通“疑难数据库(出版商)”最低求助积分说明 809021