In this paper, an image captioning network is proposed for traffic scene modeling, which incorporates element attention into the encoder-decoder mechanism to generate more reasonable scene captions. Firstly, the traffic scene elements are detected and segmented according to their clustered locations. Then, the image captioning network is applied to generate the corresponding caption of each subregion. The static and dynamic traffic elements are appropriately organized to construct a 3D corridor scene model. The semantic relationships between the traffic elements are specified according to the captions. The constructed 3D scene model can be utilized for the offline test of unmanned vehicles. The evaluations and comparisons based on the TSD-max and COCO datasets prove the effectiveness of the proposed framework.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Caption Generation from Road Images for Traffic Scene Construction


    Contributors:
    Wu, Chuan (author) / Li, Yaochen (author) / Li, Ling (author) / Wang, Le (author) / Liu, Yuehu (author)


    Publication date :

    2020-10-19


    Size :

    4116179 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    CAPTION GENERATION FROM ROAD IMAGES FOR TRAFFIC SCENE CONSTRUCTION

    Wu, Chuan / Li, Yaochen / Li, Ling et al. | British Library Conference Proceedings | 2020


    Caption Generation From Road Images for Traffic Scene Modeling

    Li, Yaochen / Wu, Chuan / Li, Ling et al. | IEEE | 2022


    Road Traffic Scene Acquisition

    Celinski, Ireneusz / Lukasik, Jerzy / Surma, Szymon et al. | TIBKAT | 2019


    Road Traffic Scene Acquisition

    Celiński, Ireneusz / Łukasik, Jerzy / Surma, Szymon et al. | Springer Verlag | 2018


    Caption Generation for Traffic Signs Using a Deep Neural Scheme

    Sarkar, Janarddan / Ramachandran, Radhika / Kizhiyedath, Sreejith | SAE Technical Papers | 2022