复杂环境下小尺度烟火目标检测研究
DOI:
作者:
作者单位:

1.南京工程学院 自动化学院;2.江苏省智能感知技术与装备工程研究中心

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家自然科学基金面上项目(51675259);江苏省智能感知技术与装备工程研究中心开放基金项目(ITS202103)


Research on small scale fireworks target detection in complex environment
Author:
Affiliation:

1.School of Automation,Nanjing Institute of technology,Nanjing,Jiangsu;2.Province Research Center of Intellisense Technology and System,Nanjing,Jiangsu

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:

    针对复杂环境下起火点目标尺寸较小、起火点特征易与实际场景混淆导致烟火检测效率及准确率低等问题,提出了一种基于改进YOLOv5的小尺度烟火目标检测方法。首先,在原始YOLOv5模型输出的第三个检测层上增加第四个检测层,以此获取更大的特征图对小目标进行检测,加强网络模型的特征提取能力。其次,为解决目标在被遮挡的场景中容易出现漏检的问题,将原网络中用于计算目标框损失函数的 GIOU_Loss 替换成 DIOU_Loss。最后,利用TensorRT对模型进行压缩和加速优化,并将其部署到Jetson TX2开发板上进行加速推理实验,通过复制增强方法扩充实际烟火场景数据,大量实验结果表明,提出方法用于复杂环境下的小尺度烟火目标检测不仅检测速度快而且精度高,适于推广应用。

    Abstract:

    Aiming at the problem of low efficiency and accuracy of fireworks detection due to the small size of fire target and the confusion of fire feature with actual scene in complex environment, a small scale fireworks target detection method based on improved YOLOv5 is proposed. Firstly, a fourth detection layer is added to the third detection layer output in the original YOLOv5 model, so as to obtain a larger feature map for small target detection and strengthen the feature extraction capability of the network model. Secondly, in order to solve the problem that the target is prone to miss detection in the shielded scene, GIOU_Loss used to calculate the regression loss function of the target frame in the original network is replaced by DIOU_Loss. Finally, TensorRT is used to compress and accelerate the optimization of the model, and it is deployed to the Jetson TX2 development board for accelerated reasoning experiments. More fireworks scene data are constructed by replication enhancement method and a large number of experimental results show that the proposed method not only has a fast convergence speed, but also has a higher accuracy for small scale fire spot detection. It is suitable for popularization and application.

    参考文献
    相似文献
    引证文献
引用本文
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:2022-07-10
  • 最后修改日期:2022-07-25
  • 录用日期:2022-08-16
  • 在线发布日期:
  • 出版日期:

地址:江苏南京,宁六路219号,南京信息工程大学    邮编:210044

联系电话:025-58731025    E-mail:nxdxb@nuist.edu.cn

南京信息工程大学学报 ® 2022 版权所有  技术支持:北京勤云科技发展有限公司