基于边缘计算的柑橘果实识别系统的设计
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:

广东省科学技术厅项目(2019B020223001、2021A1515010923);国家自然科学基金项目(31971797);现代农业产业技术体系建设专项(CARS–26)


Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    针对当前柑橘果实目标检测模型多数需在服务器上运行,难以直接在果园部署且识别实时性较差等问题,设计了基于边缘计算设备的便携式柑橘果实识别系统。该系统由优化的目标检测模型和嵌入式智能平台组成;通过扩展YOLOv4–Tiny目标检测算法,将所有批量归一化层合并到卷积层,加快模型前向推理速度;采用多尺度结构并使用K–means聚类方法获得柑橘数据集的先验框大小,使网络模型对柑橘果实识别具有更强的鲁棒性;使用GIOU距离度量损失函数,使网络模型更加关注柑橘图像中重叠遮挡的区域。将改进算法部署到嵌入式平台Jetson nano,试验结果表明,识别系统对柑橘果实的识别平均准确率达93.01%,单幅图片的推断时间约为150 ms,对视频的识别速率为16帧/s。

    Abstract:

    Aiming at the problems that most of the current citrus target detection models need to run on the server, it is difficult to deploy directly in the orchard and the recognition real-time is poor, a portable citrus fruit recognition system based on edge computing equipment is designed. The system consists of an optimized target detection model and an embedded intelligent platform. By extending the YOLOv4-Tiny target detection algorithm, all batch normalization layers are merged into the convolution layer to speed up the forward reasoning speed of the model. Multi-scale structure and K-means clustering method were used to obtain the prior frame size of citrus data set, which made the network model more robust to citrus fruit recognition. GIOU distance measurement loss function was used to measure the loss function, which make the network model pay more attention to the overlapping occlusion area in citrus images. The improved algorithm is deployed to embedded Jetson Nano platform to realize edge detection. The results showed that the average accuracy of the recognition system was 93.01%. The inference time of a single image is about 150 ms, and the video recognition rate is 16 frames/s.

    参考文献
    相似文献
    引证文献
引用本文

黄河清,胡嘉沛,李震,魏志威,吕石磊.基于边缘计算的柑橘果实识别系统的设计[J].湖南农业大学学报:自然科学版,2021,47(6):.

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2021-12-28
  • 出版日期: