Deep learning models have significantly improved object detection essential for traffic monitoring. However, these models’ increasing complexity results in higher latency and resource consumption, making real-time object detection challenging. To address this issue, we propose a lightweight deep learning model called Empty Road Detection (ERD). ERD efficiently identifies and removes empty traffic images that do not contain any object of interest, such as vehicles, via binary classification. By serving as a preprocessing unit, ERD filters out nonessential data, reducing computational complexity and latency. ERD is highly compatible and can work seamlessly with any third-party object detection model. In our evaluation, we found that ERD improves the frame processing rate of EfficientDet, SSD, and YOLOV5 by approximately 44%, 40%, and 10%, respectively, for a real-world traffic monitoring video.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Preprocessing via Deep Learning for Enhancing Real-Time Performance of Object Detection


    Beteiligte:
    Liu, Yu (Autor:in) / Kang, Kyoung-Don (Autor:in)


    Erscheinungsdatum :

    2023-06-01


    Format / Umfang :

    5001976 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Real-time object detection for autonomous vehicles using deep learning

    Kalliomäki, Roger | BASE | 2019

    Freier Zugriff

    Real-Time Aerodrome Detection Using Deep Learning Methods

    Koopman, Cynthia / Gauci, Jason / Muscat, Alan et al. | IEEE | 2022


    Predicting transient diesel engine NOx emissions using time-series data preprocessing with deep-learning models

    Shin, Seunghyup / Lee, Youngbok / Park, Jihwan et al. | SAGE Publications | 2021



    Research on Real-Time Ship Detection Using Deep Learning

    Yu, Jingming / Wang, Jie / Ren, Rong et al. | IEEE | 2022