基于改进YOLOv5和视频图像的车型识别
DOI:
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

U495

基金项目:

国家自然科学基金项目(面上项目,重点项目,重大项目)


Vehicle Type Recognition Based on Improved YOLOv5 and Video Images
Author:
Affiliation:

Fund Project:

The National Natural Science Foundation of China (71871011)

  • 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:

    为了提高车型识别的精度和检测速度,本文提出了改进YOLOv5的车型识别算法。首先利用高速公路收费的监控视频数据扩充BIT-Vehicle车型数据集,同时针对数据集中各车型图片数量不均衡现象利用图像翻转、添加高斯噪声、色彩变化等图像处理技术对各车型数量进行均衡化,构建BIT-Vehicle-Extend数据集;其次,添加RFB (Receptive Field Block)模块用于增加网络感受野,有助于模型捕捉全局特征;第三,将无参数的SimAM注意力机制添加Bottleneck中,在不增加参数的情况下,提高网络的特征提取能力。最后,实验结果表明,相比于原始网络模型,本文所提出的YOLOv5优化算法,mAP0.5和mAP0.5:0.95 达到98.7%和96.3%,分别提高了0.7%和1.5%。在检测速度方面,达到90 frames/s,与原网络相比检测速度基本不变。因此,本文所提出的YOLOv5优化算法,能够高精度的实时检测车型信息,满足车型识别检测需要。

    Abstract:

    In order to improve the accuracy and detection speed of vehicle type recognition, an improved vehicle recognition algorithm of YOLOv5 is proposed in this paper. Firstly, the BIT-Vehicle dataset is expanded by using the monitoring video data of highway toll collection. At the same time, aiming at the imbalance of the number of pictures of each vehicle in the data set, the number of each vehicle is balanced by using image processing technologies such as image flipping, adding Gaussian noise and color gamut change, and the BIT-Vehicle-Extend dataset is constructed; Secondly, the RFB module is added to increase the network receptive field, which is helpful to capture the global features of the model; Thirdly, the parameter free SimAM attention mechanism is added to bottleneck to improve the feature extraction ability of the network without adding parameters. Finally, the experimental results show that compared with the original network model, the proposed YOLOv5 optimization algorithm, mAP0.5 and mAP0 5: 0.95 to 98.7% and 96.3%, increased by 0.7% and 1.5% respectively. In terms of detection speed, it reaches 90 frames/s, which is basically unchanged compared with the original network. Therefore, the YOLOv5 optimization algorithm proposed in this paper can detect the vehicle information in real time with high precision and meet the requirements of vehicle identification and detection.

    参考文献
    相似文献
    引证文献
引用本文

王志斌,冯雷,张少波,等. 基于改进YOLOv5和视频图像的车型识别[J]. 科学技术与工程, 2022, 22(23): 10295-10300.
Wang Zhibin, Feng Lei, Zhang Shaobo, et al. Vehicle Type Recognition Based on Improved YOLOv5 and Video Images[J]. Science Technology and Engineering,2022,22(23):10295-10300.

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:2021-12-31
  • 最后修改日期:2022-05-19
  • 录用日期:2022-04-04
  • 在线发布日期: 2022-09-06
  • 出版日期:
×
律回春渐,新元肇启|《科学技术与工程》编辑部恭祝新岁!
亟待确认版面费归属稿件,敬请作者关注