As urbanization accelerates, traffic congestion and frequent accidents have become prominent issues, prompting the development of intelligent transportation systems. This paper focuses on the research of vehicle and pedestrian detection algorithms to improve detection accuracy in complex traffic environments. Considering the limitations of traditional object detection algorithms in complex situations, this study adopts the deep learning-based YOLOv8 algorithm and introduces the Coordinate Attention (CA) module to enhance the model's feature extraction and localization capabilities. Experimental results show that the improved YOLOv8 network achieves a 1.1% increase in detection accuracy while maintaining its original speed. Furthermore, this paper constructs a vehicle and pedestrian dataset suitable for Chinese traffic scenes, providing an effective solution for autonomous driving assistance systems. Overall, this study holds significant reference value for vehicle and pedestrian detection in the field of intelligent transportation.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Research on Deep Learning-Based Vehicle and Pedestrian Object Detection Algorithms


    Beteiligte:
    X. Zhang (Autor:in) / H. Huang (Autor:in) / J. Yang (Autor:in) / S. Jiang (Autor:in)


    Erscheinungsdatum :

    2024




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Unbekannt




    Deep Learning Approaches for Vehicle and Pedestrian Detection in Adverse Weather

    Zaman, Mostafa / Saha, Sujay / Zohrabi, Nasibeh et al. | IEEE | 2023


    Research on subway pedestrian detection algorithms based on SSD model

    Yang, Jie / He, Wen Yu / Zhang, Tian Lu et al. | Wiley | 2020

    Freier Zugriff

    Research on subway pedestrian detection algorithms based on SSD model

    Yang, Jie / He, Wen Yu / Zhang, Tian Lu et al. | IET | 2020

    Freier Zugriff

    Research on subway pedestrian detection algorithms based on SSD model

    Jie Yang / Wen Yu He / Tian Lu Zhang et al. | DOAJ | 2020

    Freier Zugriff