基于改进的YOLOv5模型和射线法的车辆违停检测
作者:
中图分类号:

TP391.41

基金项目:

国家自然科学基金(62171228);江苏省研究生科研与实践创新计划(SJCX21_0354)


Illegal parking detection based on improved YOLOv5 model and ray method
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • | | |
  • 文章评论
    摘要:

    车辆违法停车将会降低道路通行效率,引发交通拥堵和交通事故.传统的车辆违停检测方法参数量大且准确度低.为此,本文提出了一种使用改进的YOLOv5模型和射线法的车辆违停检测方法.首先设计了轻量化的特征提取模块,减少模型参数量;其次在模型中加入注意力机制,从通道维度和空间维度增强模型的特征提取能力,保证模型精度;接着使用混合数据增强丰富数据集样本,提升复杂背景下的检测效果;然后选用EIoU作为损失函数提高模型定位能力.实验结果表明,改进后的模型均值平均精度达到91.35%,比原始YOLOv5s提升1.01个百分点,并且参数量减少35.79%.最后将改进后模型与射线法结合,在Jetson Xavier NX嵌入式平台的检测速度可以达到约28帧/s,能够实现实时检测.

    Abstract:

    Illegally parked vehicles reduce road traffic efficiency,and cause traffic congestion even traffic accidents.Traditional vehicle detection methods are perplexed by a large number of parameters and low accuracy.Here,we propose a method using the improved YOLOv5 model and ray method to detect illegally parked vehicles.First,a lightweight feature extraction module is designed to reduce the amount of model parameters.Second,the attention mechanism is added to the model to enhance its feature extraction ability from both channel dimension and spatial dimension to ensure the model's accuracy.Then,the mixed data is used to enhance and enrich the dataset samples thus improve the detection performance in complex backgrounds,and EIoU is selected as the loss function to improve the model's positioning performance.Experiments show that the mean accuracy of the improved YOLOv5 model reaches 91.35%,which is 1.01 percentage points higher than that of the original YOLOv5s,and the number of parameters is reduced by 35.79%.Finally,the improved YOLOv5 model is combined with the ray method,which can reach real-time inspection speed of 28 frames per second on the embedded platform of Jetson Xavier NX.

    参考文献
    [1] 张增超,李强,孙红雨,等.基于地磁传感器和UWB技术的停车位车辆检测方法与实现[J].传感技术学报,2019,32(12):1917-1922 ZHANG Zengchao,LI Qiang,SUN Hongyu,et al.Parking vehicle detection method and implementation based on geomagnetic sensor and UWB technology[J].Chinese Journal of Sensors and Actuators,2019,32(12):1917-1922
    [2] 王殿海,胡宏宇,李志慧,等.违章停车检测与识别算法[J].吉林大学学报(工学版),2010,40(1):42-46 WANG Dianhai,HU Hongyu,LI Zhihui,et al.Detection and recognition algorithm of illegal parking[J].Journal of Jilin University (Engineering and Technology Edition),2010,40(1):42-46
    [3] Ye Q,Zhang Y M,Ma L.Video-based detection method of illegal parking vehicles[J].Energy Procedia,2011,11:4949-4957
    [4] 杨祖莨,丁洁,刘晋峰.一种新的结合卷积神经网络的隧道内停车检测方法[J].重庆大学学报,2021,44(6):49-59 YANG Zuliang,DING Jie,LIU Jinfeng.A new tunnel vehicle stopping detection methodology combined with convolutional neural network[J].Journal of Chongqing University (Natural Science Edition),2021,44(6):49-59
    [5] 唐洁.基于改进的卷积神经网络的违章停车检测[D].合肥:安徽大学,2019 TANG Jie.Illegal parking detection based on improved convolution neural network[D].Hefei:Anhui University,2019
    [6] 梅舒欢,闵巍庆,刘林虎,等.基于Faster R-CNN的食品图像检索和分类[J].南京信息工程大学学报(自然科学版),2017,9(6):635-641 MEI Shuhuan,MIN Weiqing,LIU Linhu,et al.Faster R-CNN based food image retrieval and classification[J].Journal of Nanjing University of Information Science&Technology (Natural Science Edition),2017,9(6):635-641
    [7] 温秀兰,焦良葆,李子康,等.复杂环境下小尺度烟火目标检测研究[J].南京信息工程大学学报(自然科学版),2023,15(6):676-683 WEN Xiulan,JIAO Liangbao,LI Zikang,et al.Small scale smoke&fire target detection in complex environment[J].Journal of Nanjing University of Information Science&Technology (Natural Science Edition),2023,15(6):676-683
    [8] 刘寒迪,赵德群,陈星辉,等.基于改进SSD的航拍施工车辆检测识别系统设计[J].国外电子测量技术,2020,39(7):127-132 LIU Handi,ZHAO Dequn,CHEN Xinghui,et al.Design of detection and recognition system of aerial photography construction vehicle based on improved SSD[J].Foreign Electronic Measurement Technology,2020,39(7):127-132
    [9] Liu W,Anguelov D,Erhan D,et al.SSD:single shot multibox detector[C]//European Conference on Computer Vision.Cham:Springer,2016:21-37
    [10] Tang H R,Peng A M,Zhang D M,et al.SSD real-time illegal parking detection based on contextual information transmission[J].Computers,Materials&Continua,2020,62(1):293-307
    [11] 丁冰,杨祖莨,丁洁,等.基于改进YOLOv3的高速公路隧道内停车检测方法[J].计算机工程与应用,2021,57(23):234-239 DING Bing,YANG Zuliang,DING Jie,et al.Detection method of highway tunnel vehicle stopping based on improved YOLOv3[J].Computer Engineering and Applications,2021,57(23):234-239
    [12] 许璧麒,马志强,宝财吉拉呼,等.基于YOLOv5的高速公路小目标车辆逆行检测模型[J].国外电子测量技术,2022,41(11):146-153 XU Biqi,MA Zhiqiang,BAO Caijilahu,et al.Small target vehicle in highway retrograde detection model based on YOLOv5[J].Foreign Electronic Measurement Technology,2022,41(11):146-153
    [13] 庄建军,叶振兴.基于改进YOLOv5m的电动车骑行者头盔与车牌检测方法[J].南京信息工程大学学报,2024,16(1):1-10 ZHUANG Jianjun,YE Zhenxing.Helmet and license plate detection for electric bike rider based on improved YOLOv5m[J].Journal of Nanjing University of Information Science&Technology,2024,16(1):1-10
    [14] 韩泽山,杨红柳,赵建光,等.基于改进YOLOv5s的口罩佩戴检测算法研究[J].信息技术与信息化,2023(2):22-25 HAN Zeshan,YANG Hongliu,ZHAO Jianguang,et al.Research on mask wearing detection algorithm based on improved YOLOv5s[J].Information Technology and Informatization,2023(2):22-25
    [15] Lin T Y,Dollár P,Girshick R,et al.Feature pyramid networks for object detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).July 21-26,2017,Honolulu,HI,USA.IEEE,2017:936-944
    [16] Liu S,Qi L,Qin H F,et al.Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.June 18-23,2018,Salt Lake City,UT,USA.IEEE,2018:8759-8768
    [17] Han K,Wang Y H,Tian Q,et al.GhostNet:more features from cheap operations[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).June 13-19,2020,Seattle,WA,USA.IEEE,2020:1577-1586
    [18] Woo S,Park J,Lee J Y,et al.CBAM:convolutional block attention module[C]//European Conference on Computer Vision.Cham:Springer,2018:3-19
    引证文献
引用本文

庄建军,徐子恒,张若愚.基于改进的YOLOv5模型和射线法的车辆违停检测[J].南京信息工程大学学报(自然科学版),2024,16(3):341-351
ZHUANG Jianjun, XU Ziheng, ZHANG Ruoyu. Illegal parking detection based on improved YOLOv5 model and ray method[J]. Journal of Nanjing University of Information Science & Technology, 2024,16(3):341-351

复制
分享
文章指标
  • 点击次数:111
  • 下载次数: 733
  • HTML阅读次数: 184
  • 引用次数: 0
历史
  • 收稿日期:2023-04-02
  • 在线发布日期: 2024-06-15
  • 出版日期: 2024-05-28

地址:江苏省南京市宁六路219号    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 ® 2025 版权所有  技术支持:北京勤云科技发展有限公司