Traffic environment perception is the foundation of autonomous driving, and road type recognition can provide support information for decision making of the intelligent vehicle. In this paper, we adopt the strategy of integrating the Mask R-CNN model with two different convolutional neural networks (ResNet-101 and ResNet-50) to perform the road type recognition and establish road type dataset containing pictures of the expressway and urban main road based on the TT100K dataset. The experiment results indicate that Mask R-CNN with ResNet-50 can achieve the mAP of 96.30%, which is 17.60% higher than that of ResNet-101, and can realize the recognition of road type effectively. Also, the comparison between ResNet-50 and ResNet-101 demonstrates that for different recognition tasks with different amounts of data, suitable depth network needs to be chosen carefully in order to achieve satisfying results.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Intelligent Vehicle Road Type Recognition Based on Mask R-CNN


    Beteiligte:
    Yu, Jinqiu (Autor:in) / Chen, Zhijun (Autor:in) / Wu, Chaozhong (Autor:in) / Cheng, Xiaozhao (Autor:in)

    Kongress:

    20th COTA International Conference of Transportation Professionals ; 2020 ; Xi’an, China (Conference Cancelled)


    Erschienen in:

    CICTP 2020 ; 942-951


    Erscheinungsdatum :

    2020-12-09




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Vision-Based Recognition of Road Regulation for Intelligent Vehicle

    Lim, Kwangyong / Hong, Yongwon / Ki, Minsong et al. | IEEE | 2018


    VISION-BASED RECOGNITION OF ROAD REGULATION FOR INTELLIGENT VEHICLE

    Lim, Kwangyong / Hong, Yongwon / Ki, Minsong et al. | British Library Conference Proceedings | 2018


    Intelligent vehicle license recognition system for road traffic duty

    YAO PING | Europäisches Patentamt | 2015

    Freier Zugriff

    ROAD TYPE RECOGNITION

    LOBEY OLIVIER | Europäisches Patentamt | 2021

    Freier Zugriff

    ROAD TYPE RECOGNITION

    LOBEY OLIVIER | Europäisches Patentamt | 2021

    Freier Zugriff