Driver attention cues contribute to the following intended maneuver prediction and provide a risk indicator for the advanced driver-assistance systems in complex driving scenarios. The diverse traffic scenes result in a challenging task to predict human visual attention with high generalization capability. The data heterogeneity caused by multiple sources with different data characteristics, such as video sources, was investigated in the current research and mitigated using the domain adaption modules (i.e., domain-specific batch normalization, Gaussian priors, and smoothing filter) and the domain-specific focal loss. Inspired by human attention mechanism, generic coders and task-driven attention modules were incorporated into a lightweight network to replicate human-like perceptual patterns, such as the perception of latent risk. Integrating these adaptive modules, we proposed the adaptive driver attention (ADA) model to predict salient regions in different traffic scenes. Consequently, the ADA model trained jointly on four driver attention datasets achieves the best performance against the state-of-the-art methods across seven metrics. Retrospective visualizations of the network and cross-validation results further explain the merit of the proposed method. Since these approaches are generic, adaptive modules are universally applicable for standard deep neural network architectures to alleviate the heterogeneity across datasets and easily extended for arbitrary traffic scenes in the real world.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multisource Adaption for Driver Attention Prediction in Arbitrary Driving Scenes


    Contributors:
    Gan, Shun (author) / Pei, Xizhe (author) / Ge, Yulong (author) / Wang, Qingfan (author) / Shang, Shi (author) / Li, Shengbo Eben (author) / Nie, Bingbing (author)

    Published in:

    Publication date :

    2022-11-01


    Size :

    3916230 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    DADA: Driver Attention Prediction in Driving Accident Scenarios

    Fang, Jianwu / Yan, Dingxin / Qiao, Jiahuan et al. | IEEE | 2022



    Driver perceptual adaption to nonplanar rearview mirrors

    Flannagan,M.J. / Sivak,M. / Traube,E.C. et al. | Automotive engineering | 1996


    ENHANCED DRIVER ATTENTION MODULE FOR DRIVING ASSISTANCE SYSTEM

    SCHNEIDER GEORG / HEINRICHS-BARTSCHER SASCHA | European Patent Office | 2018

    Free access