Vehicle detection comes as a key technology in smart traffic systems and automated driving, but existing vehicle detection models face challenges in the face of small-sized vehicles and occluded vehicles. In the present work, an improved model based on the YOLOv5s and attention mechanism is proposed to resolve the problem. In the proposed model, a spatial attention module and a channel attention module are introduced, the feature pyramid network is optimized, and the loss function is improved, which substantially increases the accuracy and efficiency of vehicle detection. Our method will provide technical support for smart traffic and automated driving, and inspire further research on vehicle detection methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    An improved vehicle detection model based on YOLOv5s and attention mechanism


    Beteiligte:
    Zhao, Haiquan (Herausgeber:in) / Tang, Xinhua (Herausgeber:in) / Yang, Xiaoqin (Autor:in) / Alias, Syazwina (Autor:in) / Wang, Hui (Autor:in)

    Kongress:

    International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2025) ; 2025 ; Nanjing, China


    Erschienen in:

    Proc. SPIE ; 13664 ; 1366459


    Erscheinungsdatum :

    16.07.2025





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Ship-YOLOv5s: improved YOLOv5 ship target detection based on attention mechanism

    Zhang, Peng / Sun, Ze / Dong, Junwei et al. | SPIE | 2025


    Tank Armored Vehicle Target Detection Based on Improved YOLOv5s

    Li, Xinwei / Mao, Yuxin / Yu, Jianjun et al. | IEEE | 2024


    Research on Road Vehicle Detection based on improved Yolov5s

    Shao, Lei / Fan, Zhenqiang / Li, Ji et al. | British Library Conference Proceedings | 2022


    Research on Vehicle Detection Method Based on Improved YOLOv5s

    Ma, Liangliang / Zhong, Runlu / Shi, Xiaohong et al. | IEEE | 2024


    UAV target detection algorithm based on improved YOLOv5s

    Zhang, Tao / Wang, Fenmei / Chen, Dongxu et al. | SPIE | 2023