The advancement of computer vision technologies has led to significant improvements in object detection systems, which are critical for various applications in the automotive industry. The implementation and evaluation of object detection based on convolutional neural networks (CNN) takes front stage in this research article. A CNN-based object detection model is presented and evaluated for accuracy, precision, recall and F-1 score. The proposed model has shown the object detection accuracy of 97.33%. The experiments establish that the CNN based object detection substantially increases the precision of multiple objects’ recognition in the vehicular scenario. The proposed strategy of optimized CNN model is efficient for real-time vehicular applications thus contributing to the improvement of security and automation in current automobiles.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Scalable Object Detection Solution for Vehicular Applications


    Contributors:
    Thakur, Kunal (author) / Soni, Dhruv (author) / Taneja, Ashu (author)


    Publication date :

    2024-10-04


    Size :

    566805 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Scalable parallel simulator for vehicular collision detection

    Grinberg,I. / Wiseman,Y. / Univ.of Bar-Ilan,IL | Automotive engineering | 2013


    Scalable parallel simulator for vehicular collision detection

    Grinberg, Ilan / Wiseman, Yair | IEEE | 2010



    Vehicular object detection device

    SAKAKIBARA KOSUKE / OHMI MASANOBU / YAMAMOTO SEIJI et al. | European Patent Office | 2018

    Free access

    VEHICULAR OBJECT DETECTION DEVICE

    SAKAKIBARA KOSUKE / OHMI MASANOBU / YAMAMOTO SEIJI et al. | European Patent Office | 2017

    Free access