Labeled data are paramount for modern, deep learning object detection models. However, such data are not always available, either due to time and financial constraints or due to the rarity of certain objects. In this paper, we show that the CARLA simulator can be used effectively to provide automatic annotations for custom street-view objects, boosting datasets for objects with few labels. We evaluate our models on real world images and show that low-shot training data expanded by synthetic images rendered in CARLA can provide better performance than training models with low-shot examples alone. To overcome the sim-to-real domain gap, we perform domain randomization by taking advantage of CARLA's diverse simulations of weather conditions, actors, and maps. We train detectors on CARLA-generated images of two different object classes and evaluate them on publicly available datasets. We provide access to our synthetic fire hydrant33https://www.kaggle.com/xinhez/synthetic-fire-hydrants and crosswalk44https://www.kaggle.com/buvision/synthetic-crosswalks datasets as well as provide step-by-step instructions55https://www.github.com/xinhez/simulation-for-detection to generate custom datasets in CARLA.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    CARLA Simulated Data for Rare Road Object Detection


    Beteiligte:
    Bu, Tom (Autor:in) / Zhang, Xinhe (Autor:in) / Mertz, Christoph (Autor:in) / Dolan, John M. (Autor:in)


    Erscheinungsdatum :

    19.09.2021


    Format / Umfang :

    1787240 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Exploring Domain Adaptation with Depth-Based 3D Object Detection in CARLA Simulator

    Antunes, Miguel / Bergasa, Luis M. / Montiel-Marín, Santiago et al. | Springer Verlag | 2024


    ANTI-CARLA: An Adversarial Testing Framework for Autonomous Vehicles in CARLA

    Ramakrishna, Shreyas / Luo, Baiting / Kuhn, Christopher B. et al. | IEEE | 2022


    Nadar (Carla Subirana)

    Jesús Miguel Sáez-González | DOAJ | 2008

    Freier Zugriff

    Towards LiDAR and RADAR Fusion for Object Detection and Multi-object Tracking in CARLA Simulator

    Montiel-Marín, Santiago / Gómez-Huélamo, Carlos / de la Peña, Javier et al. | Springer Verlag | 2022