Image recognition, especially traffic sign recognition is an important task for autonomous driving and driver assistance systems. A new Convolutional Neural Network model with the ability of feature selection in frequency domain is presented in this paper, called Frequency Selective Filter Aided (FSFA) CNN model. The new model can integrate low-pass and high-pass filters into both forward and backward propagations in order to place special emphases on feature components in different frequency bands. The theoretical basis, as well as forward and backward propagations are also formulated. Experiments on CIFAR and GTSRB traffic sign recognition datasets show that the proposed model yields better performance for the task of image recognition compared with classic methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Frequency Selective Convolutional Neural Networks for Traffic Sign Recognition


    Beteiligte:
    Lian, Zifeng (Autor:in) / Jing, Xiaojun (Autor:in) / Sun, Songlin (Autor:in) / Huang, Hai (Autor:in)


    Erscheinungsdatum :

    01.05.2016


    Format / Umfang :

    430514 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Convolutional Neural Networks for Traffic Sign Recognition

    Wei, Zhonghua / Gu, Heng / Zhang, Ran et al. | TIBKAT | 2021


    Traffic sign recognition using convolutional neural networks

    Boujemaa, Kaoutar Sefrioui / Bouhoute, Afaf / Boubouh, Karim et al. | IEEE | 2017


    Real-Time Traffic Sign Recognition Using Convolutional Neural Networks

    Rao, Aditya / Motwani, Rahul / Sarguroh, Naveed et al. | Springer Verlag | 2021


    Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks

    Jin, Junqi / Fu, Kun / Zhang, Changshui | IEEE | 2014


    German Traffic Sign Recognition Using Convolutional Neural Network

    Santosh, G V S Sree / Kumar, G Chaitanya / Sandeep, G et al. | IEEE | 2022