Data collection and scene understanding have become crucial tasks in the development of intelligent vehicles, particularly in the context of autonomous driving. Deep Learning (DL) and transformer-based architectures have emerged as the preferred methods for object detection and segmentation tasks. However, DL-based methods often require extensive training with diverse data, posing challenges in terms of data availability and labeling. To address this problem, techniques such as transfer learning and data augmentation have been adopted. Simulators like CARLA have gained popularity in the autonomous driving domain, enabling the evaluation of architectures in realistic environments before real-world deployment. Synthetic data generated by simulators offers several advantages, including cost-effectiveness, access to diverse scenarios, and the ability to generate accurate ground truth annotations. In this paper, we focus our investigation on evaluating the performance and domain adaptation capabilities of a 3D object detection pipeline based on depth estimation using a stereo camera in the CARLA simulator. Our main objective is to analyze the results of the depth estimation stage using two different approaches: CoEx and SDN. The different experiments will be performed on real and synthetic scenarios from the KITTI and SHIFT datasets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

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


    Weitere Titelangaben:

    Lect. Notes in Networks, Syst.


    Beteiligte:
    Marques, Lino (Herausgeber:in) / Santos, Cristina (Herausgeber:in) / Lima, José Luís (Herausgeber:in) / Tardioli, Danilo (Herausgeber:in) / Ferre, Manuel (Herausgeber:in) / Antunes, Miguel (Autor:in) / Bergasa, Luis M. (Autor:in) / Montiel-Marín, Santiago (Autor:in) / Sánchez-García, Fabio (Autor:in) / Pardo-Decimavilla, Pablo (Autor:in)

    Kongress:

    Iberian Robotics conference ; 2023 ; Coimbra, Portugal November 22, 2023 - November 24, 2023



    Erscheinungsdatum :

    27.04.2024


    Format / Umfang :

    13 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    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


    CARLA+: An Evolution of the CARLA Simulator for Complex Environment Using a Probabilistic Graphical Model

    Sumbal Malik / Manzoor Ahmed Khan / Aadam et al. | DOAJ | 2023

    Freier Zugriff

    Autonomous Navigation with Deep Reinforcement Learning in Carla Simulator

    Wang, Peilin / Technische Universität Dresden | SLUB | 2023


    KIT Bus: A Shuttle Model for CARLA Simulator

    Xiang, Yusheng / Wang, Shuo / Su, T. et al. | DataCite | 2021

    Freier Zugriff

    CARLA Simulated Data for Rare Road Object Detection

    Bu, Tom / Zhang, Xinhe / Mertz, Christoph et al. | IEEE | 2021