“…Moving beyond single-radar scenarios, different authors started exploring the use of machine learning algorithms to detect and mitigate interference between various radar types. The scope of work ranges from classifying the interference type [132] to interference mitigation using denoising neural networks such as convolutional neural network [133], autoencoder [134], [135], or recurrent neural networks [136].…”
Section: E Machine Learning and Automotive Radarmentioning
“…Moving beyond single-radar scenarios, different authors started exploring the use of machine learning algorithms to detect and mitigate interference between various radar types. The scope of work ranges from classifying the interference type [132] to interference mitigation using denoising neural networks such as convolutional neural network [133], autoencoder [134], [135], or recurrent neural networks [136].…”
Section: E Machine Learning and Automotive Radarmentioning
“…The authors reported promising results, but they still have concerns regarding the generalization capacity on real data. Another approach that relies on CNNs is proposed in [16]. The authors employ an autoencoder based on the U-Net architecture [17], which performs interference mitigation as a denoising task directly on the range-Doppler spectrum.…”
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. 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 data set is available for download at: http://github.com/ristea/arim.
“…Various signal processing techniques have been proposed to address the problem of mutual interference [6][7][8][9][10][11][12][13][14] in the frequency-modulated continuous wave (FMCW) radar or the chirp sequence (CS) radar [15]. Besides the traditional signal processing approaches, recent research results have shown that deep learning approaches can be used to solve this problem [16][17][18]. A recurrent neural network (RNN) model with self attention mechanism is trained in [16] and applied to suppress the interference-contaminated signal in the time domain.…”
Section: Introductionmentioning
confidence: 99%
“…A convolutional autoencoder is introduced in [18] for noise suppression of the RD spectrum. The prominent target peaks can be preserved after applying the autoencoder used in [18], whereby the phase information and probably the weak target peaks cannot be completely retained.…”
Section: Introductionmentioning
confidence: 99%
“…For the performance assessment, the trained autoencoder has been applied to real radar measurements. Different from [18], the proposed autoencoder reconstructs interference-contaminated samples in the time domain without suffering from difficulties in the reconstruction of phase. Furthermore, the proposed autoencoder can completely avoid the costly and challenging labeling of the radar sensor data as in [16,17].…”
In this paper, a novel interference mitigation approach using an autoencoder in combination with a traditional interference detection filter is introduced. It is shown that by employing the gated convolution, the encoder has the ability to learn the signal pattern from the remaining interference-free signal. The decoder can recover the interference-contaminated signal segments from the bottleneck representation as computed by the encoder.Experimental results show that the proposed method can provide a remarkable improvement in signal-to-interference-plus-noise ratio (SINR) and preserves its robustness on real radar measurements in severely disturbed scenarios that are more complex than the training dataset.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.