In this paper, we present a data augmentation framework for pedestrian detection using a pose-guided person image synthesis model. The proposed framework can boost the performance of state-of-the-art pedestrian detectors by generating new and unseen pedestrian training samples with controllable appearances and poses. This is achieved by a new latent-consistent adversarial variational auto-encoder (LAVAE) model, leveraging the advantages of conditional variational auto-encoders and conditional generative adversarial networks to disengage and reconstruct person images conditioned on target poses. An additional latent regression path is introduced to preserve appearance information and to guarantee a spatial alignment during transfer. LAVAE goes beyond existing works in restoring structural information and perceptual details with limited annotations and can further benefit the pedestrian detection task in automated driving scenarios. Extensive pedestrian detection and person image synthesis experiments are performed on the EuroCity Person dataset. We show that data augmentation using LAVAE improves the accuracy of state-of-the-art pedestrian detectors significantly. Furthermore, a competitive performance can be observed when we compare LAVAE with other generative models for person image synthesis.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

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


    Contributors:


    Publication date :

    2021-07-11


    Size :

    2819718 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


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

    Lu, Bo / Miao, Qinghai / Dai, Xingyuan et al. | IEEE | 2023


    Special Pedestrian and Head Pose Detection for Autonomous Vehicles

    Shetty, Sachin / Meena, S. M. / Kulkarni, Uday et al. | British Library Conference Proceedings | 2019


    Pose Detection of Person in a Vehicle

    ZHANG XUEBING / REHFELD TIMO | European Patent Office | 2024

    Free access

    Pedestrian Behavior Interpretation from Pose Estimation

    Yang, Jun / Gui, Along / Wang, Jiahao et al. | IEEE | 2021