《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (4): 1291-1296.DOI: 10.11772/j.issn.1001-9081.2022020313

• 多媒体计算与计算机仿真 • 上一篇    

基于改进YOLOv5s电动车头盔的自动检测与识别

朱周华, 齐琦()   

  1. 西安科技大学 通信与信息工程学院,西安 710600
  • 收稿日期:2022-03-18 修回日期:2022-07-14 接受日期:2022-07-18 发布日期:2022-08-16 出版日期:2023-04-10
  • 通讯作者: 齐琦
  • 作者简介:朱周华(1976—),女,陕西西安人,副教授,硕士,主要研究方向:机器学习、目标检测、数字信号处理;
  • 基金资助:
    国家自然科学基金资助项目(61901358)

Automatic detection and recognition of electric vehicle helmet based on improved YOLOv5s

Zhouhua ZHU, Qi QI()   

  1. College of Communication and Information Technology,Xi’an University of Science and Technology,Xi’an Shaanxi 710600,China
  • Received:2022-03-18 Revised:2022-07-14 Accepted:2022-07-18 Online:2022-08-16 Published:2023-04-10
  • Contact: Qi QI
  • About author:ZHU Zhouhua, born in 1976, M. S., associate professor. Her research interests include machine learning, object detection, digital signal processing.
  • Supported by:
    National Natural Science Foundation of China(61901358)

摘要:

针对目前电动车头盔小目标检测的精度低、鲁棒性差,相关系统不完善等问题,提出了基于改进YOLOv5s的电动车头盔检测算法。所提算法引入卷积块注意力模块(CBAM)和协调注意力(CA)模块,采用改进的非极大值抑制(NMS),即DIoU-NMS(Distance Intersection over Union-Non Maximum Suppression);同时增加多尺度特征融合检测,并结合密集连接网络改善特征提取效果;最后,建立了电动车驾驶人头盔检测系统。在自建的电动车头盔佩戴数据集上,当交并比(IoU)为0.5时,所提算法的平均精度均值(mAP)比原始YOLOv5s提升了7.1个百分点,召回率(Recall)提升了1.6个百分点。实验结果表明,所提改进的YOLOv5s算法更能满足在实际情况中对电动车及驾驶员头盔的检测精度要求,一定程度上降低了电动车交通事故的发生率。

关键词: 电动车头盔检测, YOLOv5s, 注意力机制, 非极大值抑制, 多尺度特征检测

Abstract:

Aiming at the problems of low detection precision, poor robustness, and imperfect related systems in the current small object detection of electric vehicle helmet, an electric vehicle helmet detection model was proposed based on improved YOLOv5s algorithm. In the proposed model, Convolutional Block Attention Module (CBAM) and Coordinate Attention (CA) module were introduced, and the improved Non-Maximum Suppression (NMS) - Distance Intersection over Union-Non Maximum Suppression (DIoU-NMS) was used. At the same time, multi-scale feature fusion detection was added and densely connected network was combined to improve feature extraction effect. Finally, a helmet detection system for electric vehicle drivers was established. The improved YOLOv5s algorithm had the mean Average Precision (mAP) increased by 7.1 percentage points when the Intersection over Union (IoU) is 0.5, and Recall increased by 1.6 percentage points compared with the original YOLOv5s on the self-built electric vehicle helmet wearing dataset. Experimental results show that the improved YOLOv5s algorithm can better meet the requirements for detection precision of electric vehicles and the helmets of their drivers in actual situations, and reduce the incidence rate of electric vehicle traffic accidents to a certain extent.

Key words: electric vehicle helmet detection, YOLOv5s, attention mechanism, Non-Maximum Suppression (NMS), multi-scale feature detection

中图分类号: