Pedestrian crossing prediction (PCP) in driving scenes plays a critical role in ensuring the safe decision of intelligent vehicles. Due to the limited observations and annotations of pedestrian crossing behaviors in real situations, recent studies have begun to leverage synthetic data with flexible variation to boost prediction performance, employing domain adaptation frameworks. However, different domain knowledge has distinct cross-domain distribution gaps, which necessitates suitable domain knowledge adaption ways for PCP tasks. In this work, we propose a gated syn-to-real knowledge transfer approach for PCP (Gated-S2R-PCP), which has two aims: 1) designing the suitable domain adaptation ways for different kinds of crossing-domain knowledge, and 2) transferring suitable knowledge for specific situations with gated knowledge fusion. Specifically, we design a framework that contains three domain adaption methods including style transfer, distribution approximation, and knowledge distillation for various information, such as visual, semantic, depth, bounding boxes, etc. A learnable gated unit (LGU) is employed to fuse suitable cross-domain knowledge to boost pedestrian crossing prediction. We construct a new synthetic benchmark S2R-PCP-3181 with 3181 sequences (489,740 frames) which contains the pedestrian bounding boxes, RGB frames, semantic segmentation maps, and depth maps. With the synthetic S2R-PCP-3181, we transfer the knowledge to two real challenging datasets of PIE and JAAD, and superior PCP performance is obtained to the state-of-the-art methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Gating Syn-to-Real Knowledge for Pedestrian Crossing Prediction in Safe Driving


    Beteiligte:
    Bai, Jie (Autor:in) / Fang, Jianwu (Autor:in) / Lv, Yisheng (Autor:in) / Lv, Chen (Autor:in) / Xue, Jianru (Autor:in) / Li, Zhengguo (Autor:in)


    Erscheinungsdatum :

    01.06.2025


    Format / Umfang :

    4728930 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Pedestrian safe crossing simulation system based on coupling driving algorithm

    WANG YANLIN / WEI XINKAI / SONG TAO et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    PEDESTRIAN CROSSING PREDICTION METHOD AND PEDESTRIAN CROSSING PREDICTION DEVICE

    FANG FANG / TSUCHIYA CHIKAO / TAKEI SHOICHI et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    PedCross: Pedestrian Crossing Prediction for Auto-Driving Bus

    Kitchat, Kotcharat / Chiu, Yi-Lun / Lin, Yu-Chiu et al. | IEEE | 2024


    Pedestrian safe crossing vehicle indication system

    JENSEN PAUL W | Europäisches Patentamt | 2018

    Freier Zugriff

    Pedestrian Safe Crossing Vehicle Indication System

    JENSEN PAUL W | Europäisches Patentamt | 2015

    Freier Zugriff