Please wait a minute...
吉林化工学院学报, 2025, 42(7): 17-23     https://doi.org/10.16039/j.cnki.cn22-1249.2025.07.004
  本期目录 | 过刊浏览 | 高级检索 |
基于改进YOLOv8n的种子目标检测方法
王影*,梁秋阳*,常广良**,刘麒*
1.吉林化工学院 信息与控制工程学院,吉林 吉林 132022;2.科世达(长春)汽车电器有限公司,吉林 长春130000

Seed Object Detection Method based on Improved YOLOv8
WANG Ying*, LIANG Qiuyang*, CHANG Guangliang**, LIU Qi*
1.School of Information and Control Engineering,Jilin Institute of Chemical Technology,Jilin City 132022,China;2. Kesshida (Changchun) Automobile Electrical Appliance Co., LTD., Changchun, Jilin 130000, China

下载:  PDF (1605KB) 
输出:  BibTeX | EndNote (RIS)      
摘要 针对当前农作物种子分拣过程中,人工分拣效率低下及现有机器视觉识别系统存在的检测速度慢、识别准确率低等问题,提出了一种基于改进YOLOv8n的种子目标检测方法。首先,在C2f中将轻量化网络FasterNet替换Bottleneck,减少冗余计算和内存访问,提升网络运行速度与能力。其次,引入EMA注意力机制,通过并行子网结构和跨空间信息聚合更好地关注多尺度特征,提高种子识别精度。最后,采用Wise-IOU-v3损失函数,减少低质量标注的影响,加快网络收敛速度。实验结果显示,与标准的YOLOv8n算法相比,改进的YOLOv8n算法在精确率、召回率、mAP(0.5)和mAP(0.5:0.95)分别提高了2.2%、3.4%、1.4%、4.4%,FLOPs减少了20.2%,参数量减少了27.2%。改进的YOLOv8n在精度和速度权衡方面展现出明显优势,可为农业自动化分拣设备提供更可靠的技术支持。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王影
梁秋阳
常广良
刘麒
关键词:  种子识别   YOLOv8n   FLOPs   目标检测    
Abstract: Aiming at the problems of low manual sorting efficiency and slow detection speed and low recognition accuracy of existing machine vision recognition systems in the current process crop seed sorting, a seed target detection method based on improved YOLOv8n is proposed. First,in C2f,the lightweight network FasterNet is used replace Bottleneck, which reduces redundant calculations and memory access, and improves the network operation speed and capability. Second, the EMA attention mechanism is introduced, which uses parallel sub structure and cross-space information aggregation to focus better on multi-scale features,and improve the accuracy of seed recognition. Finally, the Wise-IOU-v3 loss function used,which reduces the impact of low-quality annotations and accelerates the convergence speed of the network. The experimental results show that compared with the standard YOLOv8 algorithm, the improved YOLOv8n algorithm has improved by 2.2%, 3.4%, 1.4%, and 4.4 in precision,recall,mAP(0.5),and mAP(0.5:0.95),and the FLOPs are reduced by 20.2%,and the number of parameters is reduced by 27.2%. The improved YOLOv8n shows significant advantages in the trade-off precision and speed, and it can provide more reliable technical support for agricultural automatic sorting equipment.
Key words:  seed identification    YOLOv8n    FLOPs    object detection
               出版日期:  2025-07-25      发布日期:  2025-12-21      整期出版日期:  2025-07-25
ZTFLH:     
  TP 391.41  
引用本文:    
王影, 梁秋阳, 常广良, 刘麒. 基于改进YOLOv8n的种子目标检测方法[J]. 吉林化工学院学报, 2025, 42(7): 17-23.
WANG Ying, LIANG Qiuyang, CHANG Guangliang, LIU Qi. Seed Object Detection Method based on Improved YOLOv8. Journal of Jilin Institute of Chemical Technology, 2025, 42(7): 17-23.
链接本文:  
https://xuebao.jlict.edu.cn/CN/10.16039/j.cnki.cn22-1249.2025.07.004  或          https://xuebao.jlict.edu.cn/CN/Y2025/V42/I7/17
[1] 颜维凤, 缑燕飞, 甘树坤, 吕雪飞. 基于RGB-D相机的机械臂抓取位姿检测[J]. 吉林化工学院学报, 2025, 42(5): 77-83.
[2] 刘 麒, 李奎东, 常广良, 王 影. 基于改进YOLOv7的水果目标检测方法[J]. 吉林化工学院学报, 2024, 41(7): 12-17.
[3] 李双远, 刘向阳. 基于改进的Faster R-CNN算法建筑领域裂缝检测研究[J]. 吉林化工学院学报, 2024, 41(5): 50-53.
[4] 王影, 孙可欣, 刘振刚, 高康盛, 刘麒. 基于改进YOLOv5的仿生机器鱼目标检测算法研究[J]. 吉林化工学院学报, 2024, 41(5): 22-29.
[5] 辛鹏, 娄铖. 基于改进YOLOv8的密集多人脸检测[J]. 吉林化工学院学报, 2024, 41(11): 24-30.
[6] 董如意, 崔冉. 基于YOLOV5L的交通信号灯识别研究 [J]. 吉林化工学院学报, 2023, 40(9): 37-42.
[7] 刘麒, 盛德庆, 孙万龙, 王影.

基于改进YOLOv5s的水果目标检测研究 [J]. 吉林化工学院学报, 2023, 40(7): 34-41.

[8] 李双远 , 刘向阳. 基于CiteSpace国内外目标检测安全帽的可视化分析 [J]. 吉林化工学院学报, 2022, 39(11): 48-54.
No Suggested Reading articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed