A Social Distance Monitoring Method Based on Improved YOLOv4 for Surveillance Videos

被引:1
|
作者
Cai, Xingquan [1 ]
Zhou, Shun [1 ]
Cheng, Pengyan [1 ]
Feng, Dingwei [1 ]
Sun, Haiyan [1 ]
Ji, Jiaqi [2 ,3 ]
机构
[1] North China Univ Technol, Sch Informat Sci & Technol, Beijing 100144, Peoples R China
[2] Hebei Normal Univ Nationalities, Sch Math & Comp Sci, Chengde 067000, Peoples R China
[3] Technol Innovat Ctr Cultural Tourism, Big Data Hebei Prov, Chengde 067000, Peoples R China
关键词
Social distance; surveillance video; K-means clustering; target detection; offending aggregation;
D O I
10.1142/S0218001423540071
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Social distance monitoring is of great significance for public health in the era of COVID-19 pandemic. However, existing monitoring methods cannot effectively detect social distance in terms of efficiency, accuracy, and robustness. In this paper, we proposed a social distance monitoring method based on an improved YOLOv4 algorithm. Specifically, our method constructs and pre-processes a dataset. Afterwards, our method screens the valid samples and improves the K-means clustering algorithm based on the IoU distance. Then, our method detects the target pedestrians using a trained improved YOLOv4 algorithm and gets the pedestrian target detection frame location information. Finally, our method defines the observation depth parameters, generates the 3D feature space, and clusters the offending aggregation groups based on the L2 parametric distance to finally realize the pedestrian social distance monitoring of 2D video. Experiments show that the proposed social distance monitoring method based on improved YOLOv4 can accurately detect pedestrian target locations in video images, where the pre-processing operation and improved K-means algorithm can improve the pedestrian target detection accuracy. Our method can cluster the offending groups without going through calibration mapping transformation to realize the pedestrian social distance monitoring of 2D videos.
引用
收藏
页数:27
相关论文
共 50 条
  • [1] YOLOv4 Vs YOLOv5: Object Detection on Surveillance Videos
    Mohod, Nikita
    Agrawal, Prateek
    Madaan, Vishu
    [J]. ADVANCED NETWORK TECHNOLOGIES AND INTELLIGENT COMPUTING, ANTIC 2022, PT II, 2023, 1798 : 654 - 665
  • [2] Vehicle Logo Detection Method Based on Improved YOLOv4
    Jiang, Xiaoli
    Sun, Kai
    Ma, Liqun
    Qu, Zhijian
    Ren, Chongguang
    [J]. ELECTRONICS, 2022, 11 (20)
  • [3] An Improved Method for Ship Target Detection Based on YOLOv4
    Huang, Zexian
    Jiang, Xiaonan
    Wu, Fanlu
    Fu, Yao
    Zhang, Yu
    Fu, Tianjiao
    Pei, Junyan
    [J]. APPLIED SCIENCES-BASEL, 2023, 13 (03):
  • [4] A defect detection method for PCB based on the improved YOLOv4
    Wu J.
    Cheng Y.
    Shao J.
    Yang D.
    [J]. Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument, 2021, 42 (10): : 171 - 178
  • [5] An improved personal protective equipment detection method based on YOLOv4
    Qiao, Rengjie
    Cai, Chengtao
    Meng, Haiyang
    Wu, Kejun
    Wang, Feng
    Zhao, Jie
    [J]. MULTIMEDIA TOOLS AND APPLICATIONS, 2024, 83 (35) : 82621 - 82639
  • [6] Recognition and location method of orange based on improved YOLOv4 model
    Liu J.
    Li Y.
    Xiao L.
    Li W.
    Li H.
    [J]. Nongye Gongcheng Xuebao/Transactions of the Chinese Society of Agricultural Engineering, 2022, 38 (12): : 173 - 182
  • [7] Apple target recognition method in complex environment based on improved YOLOv4
    Ji, Wei
    Gao, Xiaoxiao
    Xu, Bo
    Pan, Yu
    Zhang, Zhuo
    Zhao, Dean
    [J]. JOURNAL OF FOOD PROCESS ENGINEERING, 2021, 44 (11)
  • [8] Optical Fiber Vibration Signal Identification Method Based on Improved YOLOv4
    Zhang, Jiangwei
    Mo, Jiaqing
    Ma, Xinrong
    Huang, Jincheng
    Song, Fubao
    [J]. SENSORS, 2022, 22 (23)
  • [9] An Underwater Fish Individual Recognition Method Based on Improved YoloV4 and FaceNet
    Zhang, Huanjun
    Wu, Junfeng
    Yu, Hong
    Wang, Weifang
    Zhang, Yuxuan
    Zhou, Yizhi
    [J]. 20TH INT CONF ON UBIQUITOUS COMP AND COMMUNICAT (IUCC) / 20TH INT CONF ON COMP AND INFORMATION TECHNOLOGY (CIT) / 4TH INT CONF ON DATA SCIENCE AND COMPUTATIONAL INTELLIGENCE (DSCI) / 11TH INT CONF ON SMART COMPUTING, NETWORKING, AND SERV (SMARTCNS), 2021, : 196 - 200
  • [10] An improved method for measuring frame synchronization time parameters based on YOLOv4
    Li, Yunfa
    Liu, Guanxu
    Dai, Jie
    Yang, Ming
    [J]. MICROPROCESSORS AND MICROSYSTEMS, 2022, 93