English

中国农机化学报

中国农机化学报 ›› 2024, Vol. 45 ›› Issue (3): 205-211.DOI: 10.13733/j.jcam.issn.2095-5553.2024.03.028

• 农业智能化研究 • 上一篇    下一篇

基于改进YOLOv5的草莓病害智能识别终端设计

乔珠峰1, 2,赵秋菊1, 2,郭建鑫1, 2,陈会娜1, 2,平阳1, 2,赵继春1, 2   

  • 出版日期:2024-03-15 发布日期:2024-04-16
  • 基金资助:
    农业农村部农业大数据重点实验室项目(NYNCBDSJ2022001);北京市数字农业创新团队项目(BAIC10—2023);北京市农林科学院改革与发展专项(GGFZSJS2023)

Design of strawberry disease intelligent identification terminal based on improved YOLOv5

Qiao Zhufeng1, 2, Zhao Qiuju1, 2, Guo Jianxin1, 2, Chen Huina1, 2, Ping Yang1, 2, Zhao Jichun1, 2   

  • Online:2024-03-15 Published:2024-04-16

摘要: 为实现低成本、便捷、高效的草莓病害识别与检测,提升草莓种植与生产效益,在YOLOv5模型基础上,引入高效通道注意力(Efficient Channel Attention,ECA)机制,研究构建一种草莓病害识别模型,应用嵌入式与软件工程技术研发草莓病害识别终端设备。终端设备应用系统由图像采集、图像检测、检测结果展示和数据传输等模块组成,实现草莓图像实时采集和病害实时识别检测等功能。基于草莓病害检测数据集对系统开展测试,结果表明,该系统可以有效识别草莓白粉菌果病、角斑病、叶斑病等病害。与YOLOv5相比,AP0.5∶0.95、AP0.5、AP0.75、APM、APL都有比较大幅度提升。系统具有高效、便捷、实时等优点,可广泛应用于草莓生产领域,从而有效提升草莓病害识别与检测效率。

关键词: 草莓病害, YOLOv5, 图像检测, 嵌入式, 模型识别

Abstract: In order to achieve lowcost, convenient, and efficient identification and detection of strawberry diseases, and improve the efficiency of strawberry planting and production, based on YOLOv5 model, an efficient channel attention (ECA) mechanism was introduced to study and construct a strawberry disease recognition model. The embedded and software engineering technology was applied to develop and implement a strawberry disease recognition terminal device. The system consisted of modules such as image acquisition, image detection, display of detection results, and data transmission. The system realized realtime collection of strawberry images and disease identification and checking functions. The system was tested using Kaggles strawberry disease detection dataset, and the experimental results showed that the system could effectively identify diseases such as strawberry powdery mildew fruit, and strawberry corner spot, and leaf spot. And compared with YOLOv5, there is a significant improvement in AP0.5∶0.95、AP0.5、AP0.75、APM、APL. The system has the advantages of efficiency, convenience, and realtime online, which can be widely applied in the field of strawberry production, thereby effectively improving the efficiency of strawberry disease identification and detection.

Key words: strawberry diseases, YOLOv5, image detection, embedded, model identification

中图分类号: