Vehicle Detection with Automotive Radar Using Deep Learning on Range-Azimuth-Doppler Tensors
Abstract
Radar has been a key enabler of advanced driver assistance systems in automotive for over two decades. Being an inexpensive, all-weather and long-range sensor that simultaneously provides velocity measurements, radar is expected to be indispensable to the future of autonomous driving. Traditional radar signal processing techniques often cannot distinguish reflections from objects of interest from clutter and are generally limited to detecting peaks in the received signal. These peak detection methods effectively collapse the image-like radar signal into a sparse point cloud. In this paper, we demonstrate a deep-learning-based vehicle detection solution which operates on the image-like tensor instead of the point cloud resulted by peak detection.To the best of our knowledge, we are the first to implement such a system.
Cite
Text
Major et al. "Vehicle Detection with Automotive Radar Using Deep Learning on Range-Azimuth-Doppler Tensors." IEEE/CVF International Conference on Computer Vision Workshops, 2019. doi:10.1109/ICCVW.2019.00121Markdown
[Major et al. "Vehicle Detection with Automotive Radar Using Deep Learning on Range-Azimuth-Doppler Tensors." IEEE/CVF International Conference on Computer Vision Workshops, 2019.](https://mlanthology.org/iccvw/2019/major2019iccvw-vehicle/) doi:10.1109/ICCVW.2019.00121BibTeX
@inproceedings{major2019iccvw-vehicle,
title = {{Vehicle Detection with Automotive Radar Using Deep Learning on Range-Azimuth-Doppler Tensors}},
author = {Major, Bence and Fontijne, Daniel and Ansari, Amin and Sukhavasi, Ravi Teja and Gowaiker, Radhika and Hamilton, Michael and Lee, Sean and Grzechnik, Slawomir K. and Subramanian, Sundar},
booktitle = {IEEE/CVF International Conference on Computer Vision Workshops},
year = {2019},
pages = {924-932},
doi = {10.1109/ICCVW.2019.00121},
url = {https://mlanthology.org/iccvw/2019/major2019iccvw-vehicle/}
}