Environment perception is crucial for autonomous vehicle (AV) safety. Most existing AV perception algorithms have not studied the surrounding environment complexity and failed to include the environment complexity parameter. This paper proposes a novel attention-based neural network model to predict the complexity level of the surrounding driving environment. The proposed model takes naturalistic driving videos and corresponding vehicle dynamics parameters as input. It consists of a Yolo-v3 object detection algorithm, a heat map generation algorithm, CNN-based feature extractors, and attention-based feature extractors for both video and time-series vehicle dynamics data inputs to extract features. The output from the proposed algorithm is a surrounding environment complexity parameter. The Berkeley DeepDrive dataset (BDD Dataset) and subjectively labeled surrounding environment complexity levels are used for model training and validation to evaluate the algorithm. The proposed attention-based network achieves 91.22% average classification accuracy to classify the surrounding environment complexity. It proves that the environment complexity level can be accurately predicted and applied for future AVs' environment perception studies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Attention-based Neural Network for Driving Environment Complexity Perception


    Contributors:
    Zhang, Ce (author) / Eskandarian, Azim (author) / Du, Xuelai (author)


    Publication date :

    2021-09-19


    Size :

    1153405 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Driving Environment Perception Using Stereovision

    Nedevschi, S. S. / Danescu, R. / Marita, T. et al. | British Library Conference Proceedings | 2005


    Driving environment perception using stereovision

    Nedevschi, S. / Danescu, R. / Marita, T. et al. | IEEE | 2005


    A Dual-Attention-Based Neural Network for See-Through Driving Decision

    Xu, Fanqi / Li, Jinglin / Yuan, Quan et al. | IEEE | 2020


    Intelligent driving environment perception analysis system

    XIAO ZUMING | European Patent Office | 2021

    Free access

    Cross-country environment automatic driving perception model training and automatic driving perception method

    WANG LIANG / ZHANG ZHANG / YANG YI | European Patent Office | 2024

    Free access