Self-Supervised Learning for Enhancing Angular Resolution in Automotive MIMO Radars

Roldan, Ignacio; Fioranelli, Francesco; Yarovoy, Alexander

doi:10.1109/tvt.2023.3269199

Cited by 4 publications

(2 citation statements)

References 35 publications

(42 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21], [22], [23], signal processing techniques were presented to interpolate the signal between antenna channels of sparse array configurations or to extrapolate small antenna arrays to larger ones. Recently, machine learning algorithms were applied to the array interpolation or extrapolation problem in [24], [25], and [26]. In [24], this was done by using real measurement data in a self-supervised way.…”

Section: Related Workmentioning

confidence: 99%

Super-Resolution Radar Imaging With Sparse Arrays Using a Deep Neural Network Trained With Enhanced Virtual Data

Schuessler¹,

Hoffmann²,

Vossiek³

2023

IEEE J. Microw.

View full text Add to dashboard Cite

This paper introduces a method based on a deep neural network (DNN) that is perfectly capable of processing radar data from extremely thinned radar apertures. The proposed DNN processing can provide both aliasing-free radar imaging and super-resolution. The results are validated by measuring the detection performance on realistic simulation data and by evaluating the Point-Spread-function (PSF) and the target-separation performance on measured point-like targets. Also, a qualitative evaluation of a typical automotive scene is conducted. It is shown that this approach can outperform state-of-the-art subspace algorithms and also other existing machine learning solutions. The presented results suggest that machine learning approaches trained with sufficiently sophisticated virtual input data are a very promising alternative to compressed sensing and subspace approaches in radar signal processing. The key to this performance is that the DNN is trained using realistic simulation data that perfectly mimic a given sparse antenna radar array hardware as the input. As ground truth, ultra-high resolution data from an enhanced virtual radar are simulated. Contrary to other work, the DNN utilizes the complete radar cube and not only the antenna channel information at certain range-Doppler detections. After training, the proposed DNN is capable of sidelobeand ambiguity-free imaging. It simultaneously delivers nearly the same resolution and image quality as would be achieved with a fully occupied array.

show abstract

Section: Related Workmentioning

confidence: 99%

Super-Resolution Radar Imaging With Sparse Arrays Using a Deep Neural Network Trained With Enhanced Virtual Data

Schuessler¹,

Hoffmann²,

Vossiek³

2023

IEEE J. Microw.

View full text Add to dashboard Cite

show abstract

“…Even if the use of automotive radar can potentially provide more robust ego-motion estimation performance than other sensors, it has several challenges. For example, radar data typically contains fewer geometrical characteristics of detected objects, because of its low resolution in range and angle-of-arrival (AoA) estimation [21]. Additionally, radar measurements are subject to various factors such as false positives, missed detections, radar cross section (RCS) fluctuations, multipath reflections, and mutual interference [22].…”

Section: Introductionmentioning

confidence: 99%