In this paper, we present RegNet, the first deep convolutional neural network (CNN) to infer a 6 degrees of freedom (DOF) extrinsic calibration between multimodal sensors, exemplified using a scanning LiDAR and a monocular camera. Compared to existing approaches, RegNet casts all three conventional calibration steps (feature extraction, feature matching and global regression) into a single real-time capable CNN. Our method does not require any human interaction and bridges the gap between classical offline and target-less online calibration approaches as it provides both a stable initial estimation as well as a continuous online correction of the extrinsic parameters. During training we randomly decalibrate our system in order to train RegNet to infer the correspondence between projected depth measurements and RGB image and finally regress the extrinsic calibration. Additionally, with an iterative execution of multiple CNNs, that are trained on different magnitudes of decalibration, our approach compares favorably to state-of-the-art methods in terms of a mean calibration error of 0.28° for the rotational and 6 cm for the translation components even for large decalibrations up to 1.5 m and 20°.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    RegNet: Multimodal sensor registration using deep neural networks


    Beteiligte:
    Schneider, Nick (Autor:in) / Piewak, Florian (Autor:in) / Stiller, Christoph (Autor:in) / Franke, Uwe (Autor:in)


    Erscheinungsdatum :

    2017-06-01


    Format / Umfang :

    3760972 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Sensor registration using neural networks

    Karniely, H. / Siegelmann, H.T. | IEEE | 2000


    PAPERS - Sensor Registration Using Neural Networks

    Karniely, H. | Online Contents | 2000


    A Variable Speed Fault Detection Approach for Electric Motors in EV Applications based on STFT and RegNet

    Mohammad-Alikhani, Arta / Pradhan, Subarni / Dhale, Sumedh et al. | IEEE | 2023


    Image registration of multimodal data using 3D GeoArcs

    OWECHKO YURI | Europäisches Patentamt | 2017

    Freier Zugriff

    Multimodal functional and morphological nonrigid image registration

    Bernardes, R. / Baptista, P. / Cunha-Vaz, J. et al. | IEEE | 2005