Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles

@article{Scheiner2019RadarbasedRU,
  title={Radar-based Road User Classification and Novelty Detection with Recurrent Neural Network Ensembles},
  author={Nicolas Scheiner and Nils Appenrodt and J{\"u}rgen Dickmann and Bernhard Sick},
  journal={2019 IEEE Intelligent Vehicles Symposium (IV)},
  year={2019},
  pages={722-729}
}
  • Nicolas Scheiner, Nils Appenrodt, +1 author Bernhard Sick
  • Published 2019
  • Computer Science, Mathematics, Engineering
  • 2019 IEEE Intelligent Vehicles Symposium (IV)
  • Radar-based road user classification is an important yet still challenging task towards autonomous driving applications. The resolution of conventional automotive radar sensors results in a sparse data representation which is tough to recover by subsequent signal processing. In this article, classifier ensembles originating from a one-vs-one binarization paradigm are enriched by one-vs-all correction classifiers. They are utilized to efficiently classify individual traffic participants and also… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-4 OF 4 CITATIONS

    CNN Based Road User Detection Using the 3D Radar Cube

    VIEW 1 EXCERPT
    CITES METHODS

    A Multi-Stage Clustering Framework for Automotive Radar Data

    VIEW 1 EXCERPT
    CITES BACKGROUND

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 19 REFERENCES

    Radar-based Feature Design and Multiclass Classification for Road User Recognition

    VIEW 7 EXCERPTS

    Two-stage pedestrian classification in automotive radar systems

    Pedestrian classification with 24 GHz chirp sequence radar

    Road user detection with convolutional neural networks: An application to the autonomous shuttle WEpod

    • F. Gaisser, P. Jonker
    • Computer Science, Mathematics
    • 2017 Fifteenth IAPR International Conference on Machine Vision Applications (MVA)
    • 2017

    Semantic Segmentation on Radar Point Clouds

    VIEW 1 EXCERPT

    The volcanormal density for radar-based extended target tracking

    VIEW 1 EXCERPT