We present our approach to unsupervised domain adaptation for single-stage object detectors on top-view grid maps in automated driving scenarios. Our goal is to train a robust object detector on grid maps generated from custom sensor data and setups. We first introduce a single-stage object detector for grid maps based on RetinaNet. We then extend our model by image- and instance-level domain classifiers at different feature pyramid levels which are trained in an adversarial manner. This allows us to train robust object detectors for unlabeled domains. We evaluate our approach quantitatively on the nuScenes and KITTI benchmarks and present qualitative domain adaptation results for unlabeled measurements recorded by our experimental vehicle. Our results demonstrate that object detection accuracy for unlabeled domains can be improved by applying our domain adaptation strategy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Single-Stage Object Detection from Top-View Grid Maps on Custom Sensor Setups


    Contributors:


    Publication date :

    2020-10-19


    Size :

    340622 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Learned Enrichment of Top-View Grid Maps Improves Object Detection

    Wirges, Sascha / Yang, Ye / Richter, Sven et al. | IEEE | 2020


    Capturing Object Detection Uncertainty in Multi-Layer Grid Maps

    Wirges, Sascha / Reith-Braun, Marcel / Lauer, Martin et al. | IEEE | 2019


    CAPTURING OBJECT DETECTION UNCERTAINTY IN MULTI-LAYER GRID MAPS

    Wirges, Sascha / Reith-Braun, Marcel / Lauer, Martin et al. | British Library Conference Proceedings | 2019


    MIM: High-Definition Maps Incorporated Multi-View 3D Object Detection

    Xiao, Jinsheng / Wang, Shurui / Zhou, Jian et al. | IEEE | 2025


    Deep Generic Dynamic Object Detection Based on Dynamic Grid Maps

    Yan, Rujiao / Schubert, Linda / Kamm, Alexander et al. | IEEE | 2024