Abstract-The frequency modulated continuous wave (FMCW) radar is an alternative to the pulse radar when the distance to the target is short. Typical FMCW radar implementations have a homodyne architecture transceiver which limits the performances for short-range applications: the beat frequency can be relatively small and placed in the frequency range affected by the specific homodyne issues (DC offset, self-mixing and 1/f noise). Additionally, one classical problem of a FMCW radar is that the voltage controlled oscillator adds a certain degree of nonlinearity which can cause a dramatic resolution degradation for wideband sweeps. This paper proposes a short-range X-band FMCW radar platform which solves these two problems by using a heterodyne transceiver and a wideband nonlinearity correction algorithm based on high-order ambiguity functions and time resampling. The platform's displacement measurement capability was tested on range profiles and synthetic aperture radar (SAR) images acquired for various targets. The displacements were computed from the interferometric phase and the measurement errors were situated below 0.1 mm for metal bar targets placed at a few meters from the radar.

No abstract

No abstract

The interest of the automotive industry has progressively focused on subjects related to driver assistance systems as well as autonomous cars. Cars combine a variety of sensors to perceive their surroundings robustly. Among them, radar sensors are indispensable because of their independence of lighting conditions and the possibility to directly measure velocity. However, radar interference is an issue that becomes prevalent with the increasing amount of radar systems in automotive scenarios.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. We propose two FCNs that take spectrograms of the beat signals as input, and provide the corresponding clean range profiles as output. We propose two architectures for interference mitigation which outperform the classical zeroing technique. 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 objectively compare their future work in this domain.

The interest of the automotive industry has progressively focused on subjects related to driver assistance systems as well as autonomous cars. In order to achieve remarkable results, cars combine a variety of sensors to perceive their surroundings robustly. Among them, radar sensors are indispensable because of their independence of light conditions and the possibility to directly measure velocity. However, radar interference is an issue that becomes prevalent with the increasing amount of radar systems in automotive scenarios. 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. We propose two FCNs that take spectrograms of the beat signals as input, and provide the corresponding clean range profiles as output. We propose two architectures for interference mitigation which outperform the classical zeroing technique. 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. The data set is available for download at: http://github.com/ristea/arim.