Due to the low resolution, high noise, and strong spatial correlation of thermal infrared images, an improved YOLOv7 algorithm is proposed to solve the problem of low accuracy in road traffic infrared target detection algorithms. Introducing CBAM attention mechanism in the backbone network and Neck network to enhance the ability to locate small targets; Replace the original SPPCSPC module with an ASPP module in the Neck network to improve the detection accuracy of images with lower resolutions; Replace the original CIoU loss function with the WIoU loss function to enhance the detection accuracy of weak and small targets. Experiments on the Chinese thermal infrared data set CTIR show that compared with the YOLOv7 algorithm, the detection accuracy mAP value of the proposed algorithm is increased by 3.4%, and the detection performance is improved.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Object Detection Algorithm Based on YOLOv7 Traffic Infrared Image


    Beteiligte:
    Guo, Wei (Autor:in) / Tang, Sitao (Autor:in)


    Erscheinungsdatum :

    11.10.2023


    Format / Umfang :

    2510952 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Traffic Sign Detection Algorithm Based on Improved YOLOv7

    Wang, Haodong / Zhang, Xindong | IEEE | 2024


    Nighttime Vehicle Object Detection Based on Improved YOLOv7

    Sun, Haichao / Ye, Hui / Zhai, Junyong | TIBKAT | 2023


    MS-YOLOv7:YOLOv7 Based on Multi-Scale for Object Detection on UAV Aerial Photography

    LiangLiang Zhao / MinLing Zhu | DOAJ | 2023

    Freier Zugriff

    YOLOv7-SC:A Traffic Sign Detection Algorithm Based On SimAM and improved SPPCSPC-C

    Huang, Qian / Nong, Haiyuan / Peng, Wenquan et al. | IEEE | 2024


    Traffic Rule Violation Detection using Detectron2 and Yolov7

    Choudhari, Rutvik / Goel, Shubham / Patel, Yash et al. | IEEE | 2023