基于改进YOLOv5算法的智慧城市多目标检测

doi:10.16046/j.cnki.issn2096-5680.2024.03.005

河北水利电力学院学报 ›› 2024, Vol. 34 ›› Issue (3): 24-29.DOI: 10.16046/j.cnki.issn2096-5680.2024.03.005

• 人工智能与机器人专题 • 上一篇下一篇

基于改进YOLOv5算法的智慧城市多目标检测

王继超^1,2, 唐勇¹, 回振桥¹, 刘浩卓¹, 刘冰¹

1.河北水利电力学院,河北省沧州市黄河西路49号 061001;
2.河北省工业机械手控制与可靠性技术创新中心,河北省沧州市黄河西路49号 061001

收稿日期:2023-11-23 修回日期:2024-07-01 出版日期:2024-09-30 发布日期:2024-10-09
通讯作者: 唐勇(1971-),男,河北沧州人,副教授,工学硕士,主要从事智能控制研究。E-mail:1576458999@qq.com
作者简介:王继超(1992-),男,河北沧州人,硕士,主要研究领域为深度学习、智能优化。E-mail:491366271@qq.com
基金资助:
沧州市科协2024年度科技创新课题(CZKX2024464);河北省水利科研与推广计划项目(2023-23);沧州市社会科学发展研究课题(2023144);河北水利电力学院基本科研业务费项目(SYKY2330、SYKY2308)

TMulti-target Detection of Smart City Based on Improved YOLOv5 Algorithm

WANG Jichao^1,2, TANG Yong¹, HUI Zhenqiao¹, LIU Haozhuo¹, LIU Bing¹

1. Department of Electrical Automation, Hebei University of Water Resources and Electric Engineering, 10060, Cangzhou, Hebei, China;
2. Hebei Industrial Manipulator Control and Reliability Technology Innovation Center, 10060, Cangzhou, China

Received:2023-11-23 Revised:2024-07-01 Online:2024-09-30 Published:2024-10-09

摘要/Abstract

摘要： 多目标检测作为智慧城市建设中的核心技术,在建立城市图谱、挖掘城市运行规律、提高城市运行效率中起着不可替代的作用。文中在优良的目标检测模型YOLOv5基础上,选取城市中的典型场景,以行人和车辆为检测目标,将原有轻量化版本算法neck部分的SPP模块进行改进,在保证检测速率的同时增加检测的精度,然后将文中改进算法和YOLOv5-s算法同时部署在智慧城市边缘设备上进行对比试验。试验结果表明,文中改进算法相较于YOLOv5-s算法在速度保持基本不变的情况下检测多目标精度提高6.8%,在一定程度上解决了智慧城市边缘设备检测速率和精度不能同时达到要求的问题,为智慧城市多目标实时检测提供了理论参考与方法依据。

关键词: 智慧城市, 多目标检测, 边缘设备, 实时检测

Abstract: As the core technology of smart city construction, multi-object detection plays an irreplaceable role in establishing city map, mining city operation law and improving city operation efficiency. Based on the excellent target detection model YOLOv5, this paper selects typical scenes in cities, takes pedestrians and vehicles as detection targets, and improves the SPP module of the neck part of the original lightweight version algorithm to ensure detection speed and increase detection accuracy. Then, the improved algorithm and YOLOv5-s algorithm were deployed on the edge devices of smart cities at the same time, and a comparative test was conducted. Experimental results show that compared with YOLOv5-s algorithm, the improved algorithm in this paper can improve the multi-target detection accuracy by 15.7% when the speed remains basically unchanged, which solves the problem that the detection rate and accuracy of edge devices in smart cities cannot meet the requirements at the same time to a certain extent, and provides a theoretical reference and method basis for multi-target real-time detection in smart cities.

Key words: smart city, multi-target detection, edge equipment, real-time detection

中图分类号:

王继超, 唐勇, 回振桥, 刘浩卓, 刘冰. 基于改进YOLOv5算法的智慧城市多目标检测[J]. 河北水利电力学院学报, 2024, 34(3): 24-29.

WANG Jichao, TANG Yong, HUI Zhenqiao, LIU Haozhuo, LIU Bing. TMulti-target Detection of Smart City Based on Improved YOLOv5 Algorithm[J]. Journal of Hebei University of Water Resources and Electric Engineering, 2024, 34(3): 24-29.

参考文献

[1] 薛乾明.大数据背景下智慧城市空间规划与建设方法[J].科技和产业,2023,23(19):128-135.
[2] 孙瑛泽,王义鹏.“新基建”背景下智慧城市基础设施智能化建设思路[J].数字通信世界,2023,(7):166-168.
[3] 华先胜,黄建强,金仲明,等.城市大规模视觉智能综述[J].人工智能,2021,(5):6-15.
[4] 王继超,李擎,崔家瑞,等.一种改进的人工蜂群算法—粒子蜂群算法[J].工程科学学报,2018,40(7):871-881.
[5] He K, Zhang X, Ren S. etal.Spatial pyramid pooling in deep convolutional networks for visual recognition[J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2015,37(9):1904-1916.
[6] Lin T Y, Dollar P, Girshick R, et al. Feature pyramid networks for object Detection[C]//Proceedings of the IEEE Conferece on Computer Vision and Pattern Recognition, 2017:2117-2125.
[7] 王丽萍,刘磊,曾聪,等.面向智慧城市的窨井盖安全系统设计[J].物联网技术,2021,11(12):92-94.
[8] 渠逸,汪诚,余嘉博,等.基于YOLOv5的表面缺陷检测优化算法[J].空军工程大学学报,2023,24(5):80-87.
[9] 郑尚坡,陈德富,邱宝象,等.基于树莓派与YOLOv5-Lite模型的行人检测系统设计[J].计算机时代,2023(9):116-119.
[10] 王继超,张丽娟,张春茜,等.基于YOLOv4与改进DeepSORT算法的车流量检测[J].河北水利电力学院学报,2023,33(1):6-11.
[11] Redmon J, DivvalaS, GirshickR, et al. You only look once: Unified,real-time object detection with region proposal networks [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017,39(6):1137-1149.
[12] Pedmon J, Farhadi A.YOLO9000: Better, Faster, Stronger[C]//IEEE Conference on Computer Vision & Pattern Recognition,2017:6517-6525.
[13] Redmon J,Farhadi A.YOLOv3:An Incremental Improvement[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, USA,2018:1-4.
[14] BOCHKOVSKIY A, WANG C, LIAO H. YOLOv4: Optimal Speed and Accuracy of Object Detection [C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE Computer Society, 2020:392-401.
[15] 章佳琪,肖建.DID-YOLO:一种适用于嵌入式设备的移动机器人目标检测算法[J].计算机技术与发展,2023,33(10):8-14.
[16] 高伟,郭美青,张兴忠,等.基于改进PP-YOLOv2的红外图像电力设备检测[J].计算机仿真,2023,40(9):81-87+241.
[17] 孙东来,王继超,陈科,等.基于Ghost-YOLOv3-2算法的2尺度猪目标检测[J].江苏农业科学,2022,50(7):189-196.
[18] 张慧,王坤峰,王飞跃.深度学习在目标视觉检测中的应用进展与展望[J].自动化学报.2017,43(8):1289-1305.
[19] 吴晨曦,张洪欣,崔晓彤.Jetson Nano神经网络物理电磁泄漏安全研究[J].太赫兹科学与电子信息学报,2023,21(9):1144-1149.

基于改进YOLOv5算法的智慧城市多目标检测

TMulti-target Detection of Smart City Based on Improved YOLOv5 Algorithm

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

[1]	彭宁, 吴浩, 漆梓渊, 刘彦希, 宋弘. 一种电子换向器表面缺陷图像去噪和增强算法[J]. 河北水利电力学院学报, 2023, 33(3): 1-8.
[2]	张军, 刘先禄, 张宇山. 基于注意力机制的Siamese目标跟踪算法研究[J]. 河北水利电力学院学报, 2022, 32(1): 1-8.
[3]	王继超, 张丽娟, 尤田, 孙东来, 回振桥. 人脸识别的智能防疫系统设计[J]. 河北水利电力学院学报, 2021, 31(4): 55-59.
[4]	王银花. 基于K-L变换和奇异值分解的人脸识别[J]. 河北水利电力学院学报, 2020, 30(4): 38-43.
[5]	杨明. 计算机图像处理技术在网页设计中的应用研究[J]. 河北水利电力学院学报, 2019, 29(1): 56-59.
[6]	王继超, 张丽娟, 张春茜, 回振桥, 申耀辉. 基于YOLOv4与改进DeepSORT算法的车流量检测[J]. 河北水利电力学院学报, 2023, 33(1): 6-11.
[7]	王政博, 唐勇, 刘辰淼, 孙东来. 基于Kinect V2的肢体动作识别方法设计与实现[J]. 河北水利电力学院学报, 2023, 33(1): 12-18.