基于深度学习的密集行人检测场景算法研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

TP391

基金项目:

国家自然科学基金资助项目(62172004,61872004);安徽省科技重大专项(202003a05020028);安徽省高校协同创新项目(GXXT-2023-020);芜湖市核心技术攻关科技计划项目(2022hg10);芜湖市科技计划项目(2023kx17)


Algorithm Research on Dense Pedestrian Detection Scene Based on Deep Learning
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:

    针对密集行人检测场景存在目标尺度过小以及目标遮挡等问题,提出一种基于改进YOLOv7的密集行人检测算法。首先在特征提取网络引入MobileNet注意力模块,减少模型计算量和增强特征提取能力;其次在特征融合网络加入BepC3模块,提升了行人多尺度特征融合的能力;最后采用WD-Loss作为定位损失函数,提高模型检测的定位精度。在Wider-Person拥挤行人检测数据集上进行训练和验证,实验结果表明改进后的算法模型AP50精度达到了0.784,领先原YOLOv7算法0.031。

    Abstract:

    A dense pedestrian detection algorithm based on the improved YOLOv7 is proposed to address the issues of small target scale and occlusion in dense pedestrian detection scenarios. Firstly, the MobileNet attention module is introduced into the feature extraction network to reduce the model computation and enhance feature extraction capabilities. Secondly, the addition of the BepC3 module in the feature fusion network enhances the ability of pedestrian multi-scale feature fusion. Finally, WD-Loss is used as the localization loss function to improve the localization accuracy of the model detection. Trai-ning and validation were conducted on the Wider-Person crowded pedestrian detection dataset, and the experimental results showed that the improved algorithm model AP50 achieved an accuracy of 0.784, leading the original YOLOv7 algorithm by 0.031.

    参考文献
    相似文献
    引证文献
引用本文

马明杰,马小陆,唐得志,赵远,齐晶晶,瞿元.基于深度学习的密集行人检测场景算法研究[J].河北工程大学自然版,2024,41(4):103-112

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:2023-08-22
  • 最后修改日期:
  • 录用日期:
  • 在线发布日期: 2024-09-09
  • 出版日期:
文章二维码