Among them, radar sensors are indispensable because of their independence of lighting conditions and the possibility to directly measure velocity. Cars combine a variety of sensors to perceive their surroundings robustly. The interest of the automotive industry has progressively focused on subjects related to driver assistance systems as well as autonomous cars. In this paper, we address this issue for frequency modulated continuous wave (FMCW) radars with fully convolutional neural networks (FCNs), a state-of-the-art deep learning technique. However, radar interference is an issue that becomes prevalent with the increasing amount of radar systems in automotive scenarios. Among them, radar sensors are indispensable because of their independence of light conditions and the possibility to directly measure velocity. In order to achieve remarkable results, cars combine a variety of sensors to perceive their surroundings robustly. Our data set is available for download at. Considering the lack of databases for automotive radar interference mitigation, we release as open source our large-scale data set that closely replicates the real-world automotive scenario for multiple interference cases, allowing others to objectively compare their future work in this domain. For instance, our novel approach reduces the phase estimation error with respect to the commonly-adopted zeroing technique by half, from 12.55 degrees to 6.58 degrees. While most previous works successfully estimated the magnitude of automotive radar signals, we propose a deep learning model that can accurately estimate the phase. To our knowledge, we are the first to apply weight pruning in the automotive radar domain, obtaining superior results compared to the widely-used dropout. In order to train our network in a real-world scenario, we introduce a new data set of realistic automotive radar signals with multiple targets and multiple interferers. In this paper, we propose a fully convolutional neural network for automotive radar interference mitigation. In order to extract distance and velocity of multiple targets from range-Doppler maps, the interference affecting each range profile needs to be mitigated. The broad adoption of radar sensors increases the chance of interference among sensors from different vehicles, generating corrupted range profiles and range-Doppler maps. Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The data set is available for download at. Moreover, considering the lack of databases for this task, we release as open source a large scale data set that closely replicates real world automotive scenarios for single-interference cases, allowing others to compare objectively their future work in this domain. We propose two architectures for interference mitigation which outperform the classical zeroing technique. We propose two FCNs that take spectrograms of the beat signals as input, and provide the corresponding clean range profiles as output.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |