Data augmentation plays a crucial role in training a CNN-based detector. Most previous approaches were based on using a combination of general image-processing operations and could only produce limited plausible image variations. Recently, GAN (Generative Adversarial Network) based methods have shown compelling visual results. However, they are prone to fail at preserving image-objects and maintaining translation consistency when faced with large and complex domain shifts, such as day-to-night. In this paper, we propose AugGAN, a GAN-based data augmenter which could transform on-road driving images to a desired domain while image-objects would be well-preserved. The contribution of this work is three-fold: (1) we design a structure-aware unpaired image-to-image translation network which learns the latent data transformation across different domains while artifacts in the transformed images are greatly reduced; (2) we quantitatively prove that the domain adaptation capability of a vehicle detector is not limited by its training data; (3) our object-preserving network provides significant performance gain in the difficult day-to-night case in terms of vehicle detection. AugGAN could generate more visually plausible images compared to competing methods on different on-road image translation tasks across domains. In addition, we quantitatively evaluate different methods by training Faster R-CNN and YOLO with datasets generated from the transformed results and demonstrate significant improvement on the object detection accuracies by using the proposed AugGAN model.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    GAN-Based Day-to-Night Image Style Transfer for Nighttime Vehicle Detection


    Beteiligte:
    Lin, Che-Tsung (Autor:in) / Huang, Sheng-Wei (Autor:in) / Wu, Yen-Yi (Autor:in) / Lai, Shang-Hong (Autor:in)


    Erscheinungsdatum :

    01.02.2021


    Format / Umfang :

    7232534 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Improved Nighttime Traffic Detection Using Day-To-Night Image Transfer

    Guo, Feng / Liu, Jian / Xie, Quanyi et al. | Transportation Research Record | 2023


    Night Vision and Nighttime Lighting for Mariners

    Rothblum, A. / Wyatt, D. | British Library Conference Proceedings | 2007


    Nighttime Vehicle Object Detection Based on Improved YOLOv7

    Sun, Haichao / Ye, Hui / Zhai, Junyong | TIBKAT | 2023


    Nighttime Vehicle Detection for Heavy Trucks

    Zhang, Zhijuan / Chen, Hui / Xiao, Zhiguang et al. | British Library Conference Proceedings | 2015


    Improved Nighttime Vehicle Detection Using the Cross-Domain Image Translation

    Guo, Feng / Deng, Yihao / Chang, Honglei et al. | ASCE | 2024