基于S3-YOLOv5s的矿井人员防护设备检测算法研究
CSTR:
作者:
作者单位:

(重庆邮电大学 通信与信息工程学院, 重庆 400065)

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

重庆邮电大学校企合作项目(E2021269SD,E2022026SD).通信作者:代少升E-mail:daiss@cqupt.edu.cn


Research on Detection Algorithm of Mine Personnel Protection Equipment Based on S3-YOLOv5s
Author:
Affiliation:

(School of Communication and Information Engin., Chongqing University of Posts and Telecommun., Chongqing 400065, CHN)

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:

    针对复杂矿井环境下光照度低、目标尺度变化大、目标间遮挡严重,现有的目标检测网络特征提取困难、检测效果差等问题,提出了改进的S3-YOLOv5s的矿井人员防护设备检测算法。在主干网络中加入无参注意力模块(SimAM),提升网络的特征提取能力;引入尺度均衡特征金字塔卷积,加强多尺度特征融合;最后采用SIoU作为边框回归损失函数并使用K-means++算法进行先验锚框聚类,提高边框检测精度。实验表明,相比现有的YOLOv5s算法,所提算法在所有类别的平均检测精确度从89.64%提升到了92.86%,在复杂矿井环境条件下对人员防护设备有优良的检测能力,验证了所提方法的有效性。

    Abstract:

    Aiming at the problems of low illumination, large change of target scale, serious occlusion between targets, difficult feature extraction of existing target detection network, poor detection effect, etc. in complex mine environment, an improved S3-YOLOv5s mine personnel protection equipment detection algorithm is proposed. A simple, parameter free attention module (SimAM) was added to the backbone network to improve the feature extraction capability of the network. Scale equalizing pyramid convolution (SEPC) was introduced to strengthen multi-scale feature fusion. Finally, SIoU was used as the frame regression loss function and K-means++ algorithm was used for prior anchor frame clustering to improve the frame detection accuracy. The experimental results show that, compared with the existing YOLOv5s algorithm, the average detection accuracy of the proposed algorithm in all categories is improved from 89.64% to 92.86%, and the algorithm has excellent detection capability for personnel protection equipment under complex mine environments, which verifies the effectiveness of the proposed method.

    参考文献
    相似文献
    引证文献
引用本文

代少升,曾奇,黄炼,陈昌川,陈怡羽,卢正鑫.基于S3-YOLOv5s的矿井人员防护设备检测算法研究[J].半导体光电,2023,44(1):153-160. DAI Shaosheng, ZENG Qi, HUANG Lian, CHEN Changchuan, CHEN Yiyu, LU Zhengxin. Research on Detection Algorithm of Mine Personnel Protection Equipment Based on S3-YOLOv5s[J].,2023,44(1):153-160.

复制
分享
相关视频

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:2022-11-07
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2023-04-07
  • 出版日期:
文章二维码