Collecting and annotating traffic scene datasets is time-consuming and laborious. Virtual data can serve as an important supplement to the real-world traffic scene. Therefore, we propose a closed-loop data augmentation method based on car crash sequences in traffic scenes. Through the CARLA simulation platform, we obtain crash data that is difficult to collect in real-world traffic scenes, and this is then taken as the basis for subsequent pedestrian pose augmentation. To generate rare pedestrian poses, we specifically used boundary value sampling and ideas from genetic algorithms, which broadened the variety of pedestrian stances in the scenes. An efficient detection model was also employed to provide feedback signals for the closed-loop architecture. Based on this feedback, we created scenes for the corner case with various weather, city, and time conditions. The augmentation efficiency can be significantly improved by closed-loop construction. This approach enables us to produce a diverse and comprehensive dataset that can enhance the performance of pedestrian detection models in various traffic scenes.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    VCrash: A Closed-Loop Traffic Crash Augmentation with Pose Controllable Pedestrian


    Contributors:
    Lu, Bo (author) / Miao, Qinghai (author) / Dai, Xingyuan (author) / Lv, Yisheng (author)


    Publication date :

    2023-09-24


    Size :

    3193037 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    POSE-GUIDED PERSON IMAGE SYNTHESIS FOR DATA AUGMENTATION IN PEDESTRIAN DETECTION

    Zhi, Rong / Guo, Zijie / Zhang, Wuqiang et al. | British Library Conference Proceedings | 2021


    Pose-Guided Person Image Synthesis for Data Augmentation in Pedestrian Detection

    Zhi, Rong / Guo, Zijie / Zhang, Wuqiang et al. | IEEE | 2021


    National Pedestrian Crash Report

    D. Chang | NTIS | 2008


    SEMI-CLOSED LOOP ROLLOUTS FOR DATA AUGMENTATION

    PHAN TUNG / WOLFF ERIC | European Patent Office | 2023

    Free access

    SEMI-CLOSED LOOP ROLLOUTS FOR DATA AUGMENTATION

    PHAN TUNG MINH / WOLFF ERIC | European Patent Office | 2025

    Free access