Pedestrian detection aims to automatically identify and locate pedestrian objects in images or videos, enabling applications such as intelligent surveillance, traffic safety, and crowd counting. To address the issue of low accuracy in pedestrian detection using the YOLOv4 object detection algorithm, an improved YOLOv4 algorithm is proposed to enhance pedestrian detection performance. By incorporating the DenseNet model and ECANet attention mechanism, experiments are conducted on the INRIA dataset. The improved YOLOv4 algorithm achieves an average precision (AP) of 93.97%, which is a 4.85% improvement compared to the original YOLOv4 algorithm.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pedestrian Detection Algorithm Based on Improved YOLOv4


    Contributors:
    Zheng, Ziheng (author) / Ni, Chenhui (author) / Zeng, Guolei (author)


    Publication date :

    2023-10-11


    Size :

    2762766 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Detection Algorithm Based on Improved YOLOv4 for Pedestrian

    Kong, Wen / Qiao, Yidan / Wei, Ziqi | IEEE | 2022


    Improved YOLOv4-tiny network for pedestrian detection

    Fan, Pengbo / Chen, Tingzheng / Zhou, Zongtan et al. | IEEE | 2022


    A Improved Yolov4’s vehicle and pedestrian detection method

    Wang, Hailong / Tian, Shihe / Zhang, Zhian et al. | VDE-Verlag | 2022


    Improved YOLOv4 for Pedestrian Detection and Counting in UAV Images

    Hao Kong / Zhi Chen / Wenjing Yue et al. | DOAJ | 2022

    Free access

    UAV Target Detection Algorithm Based on Improved YOLOv4

    Wang, Wenyue / Li, Jian / Zhang, Qi | Springer Verlag | 2022