Estimating the Magnitude and Phase of Automotive Radar Signals Under Multiple Interference Sources With Fully Convolutional Networks

Radar sensors are gradually becoming a wide-spread equipment for road vehicles, playing a crucial role in autonomous driving and road safety. The broad adoption of radar sensors increases the chance of interference among sensors from different vehicles, generating corrupted range profiles and range-Doppler maps. In order to extract distance and velocity of multiple targets from range-Doppler maps, the interference affecting each range profile needs to be mitigated. In this paper, we propose a fully convolutional neural network for automotive radar interference mitigation. 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. 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. While most previous works successfully estimated the magnitude of automotive radar signals, we propose a deep learning model that can accurately estimate the phase. 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. 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. Our data set is available for download at: http://github.com/ristea/arim-v2.

[1]  Song Han,et al.  Learning both Weights and Connections for Efficient Neural Network , 2015, NIPS.

[2]  Mingjie Sun,et al.  Rethinking the Value of Network Pruning , 2018, ICLR.

[3]  Jungwoo Lee,et al.  A Peer-to-Peer Interference Analysis for Automotive Chirp Sequence Radars , 2018, IEEE Transactions on Vehicular Technology.

[4]  M. Kunert,et al.  The EU project MOSARIM: A general overview of project objectives and conducted work , 2012, 2012 9th European Radar Conference.

[5]  Christian Waldschmidt,et al.  Analytical and Experimental Investigations on Mitigation of Interference in a DBF MIMO Radar , 2017, IEEE Transactions on Microwave Theory and Techniques.

[6]  J.B. Allen,et al.  A unified approach to short-time Fourier analysis and synthesis , 1977, Proceedings of the IEEE.

[7]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[8]  G.M. Brooker,et al.  Mutual Interference of Millimeter-Wave Radar Systems , 2007, IEEE Transactions on Electromagnetic Compatibility.

[9]  Babak Hossein Khalaj,et al.  Grey Prediction Based Handoff Algorithm , 2007 .

[10]  Radu Tudor Ionescu,et al.  Convolutional Neural Networks With Intermediate Loss for 3D Super-Resolution of CT and MRI Scans , 2020, IEEE Access.

[11]  In-So Kweon,et al.  CBAM: Convolutional Block Attention Module , 2018, ECCV.

[12]  Yu Tsao,et al.  Noise Reduction in ECG Signals Using Fully Convolutional Denoising Autoencoders , 2019, IEEE Access.

[13]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[14]  Francesco Laghezza,et al.  Enhanced Interference Detection Method in Automotive FMCW Radar Systems , 2019, 2019 20th International Radar Symposium (IRS).

[15]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[16]  A. Boudraa,et al.  EMD-Based Signal Noise Reduction , 2005 .

[17]  Wenguan Wang,et al.  Deep Visual Attention Prediction , 2017, IEEE Transactions on Image Processing.

[18]  Yi Hu,et al.  A comparative intelligibility study of single-microphone noise reduction algorithms. , 2007, The Journal of the Acoustical Society of America.

[19]  Marc Moonen,et al.  Binaural Noise Reduction Algorithms for Hearing Aids That Preserve Interaural Time Delay Cues , 2007, IEEE Transactions on Signal Processing.

[20]  Faruk Uysal,et al.  Synchronous and Asynchronous Radar Interference Mitigation , 2019, IEEE Access.

[21]  Andrei Anghel,et al.  Fully Convolutional Neural Networks for Automotive Radar Interference Mitigation , 2020, 2020 IEEE 92nd Vehicular Technology Conference (VTC2020-Fall).

[22]  Akihiro Kajiwara,et al.  Road Debris Detection Using 79GHz Radar , 2019, 2019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall).

[23]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[24]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[25]  Alexander Yarovoy,et al.  An Interference Mitigation Technique for FMCW Radar Using Beat-Frequencies Interpolation in the STFT Domain , 2019, IEEE Transactions on Microwave Theory and Techniques.

[26]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[27]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[28]  Xueru Bai,et al.  Interference Mitigation for Synthetic Aperture Radar Based on Deep Residual Network , 2019, Remote. Sens..

[29]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[30]  Trevor Darrell,et al.  Fully Convolutional Networks for Semantic Segmentation , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[31]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[32]  Ruth Bentler,et al.  Digital Noise Reduction: An Overview , 2006, Trends in amplification.

[33]  Steven L. Brunton,et al.  Deep learning of dynamics and signal-noise decomposition with time-stepping constraints , 2018, J. Comput. Phys..

[34]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[35]  Radu Tudor Ionescu,et al.  Recognizing Facial Expressions of Occluded Faces using Convolutional Neural Networks , 2019, ICONIP.

[36]  Franz Pernkopf,et al.  Resource-Efficient Deep Neural Networks for Automotive Radar Interference Mitigation , 2021, IEEE Journal of Selected Topics in Signal Processing.

[37]  Thomas S. Huang,et al.  Computed tomography super-resolution using convolutional neural networks , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[38]  Radu Tudor Ionescu,et al.  CocoNet: A deep neural network for mapping pixel coordinates to color values , 2018, ICONIP.

[39]  Franz Pernkopf,et al.  Complex Signal Denoising and Interference Mitigation for Automotive Radar Using Convolutional Neural Networks , 2019, 2019 22th International Conference on Information Fusion (FUSION).

[40]  M. Davies,et al.  Endovascular treatment of tracheoinnominate artery fistula: a case report. , 2006, Vascular and endovascular surgery.

[41]  Quan Shi,et al.  Interference Mitigation for Automotive Radar Using Orthogonal Noise Waveforms , 2018, IEEE Geoscience and Remote Sensing Letters.

[42]  Jungwoo Lee,et al.  A Deep Learning Approach for Automotive Radar Interference Mitigation , 2018, 2018 IEEE 88th Vehicular Technology Conference (VTC-Fall).

[43]  Robert Weigel,et al.  Automotive Radar Interference Mitigation using a Convolutional Autoencoder , 2020, 2020 IEEE International Radar Conference (RADAR).

[44]  Radu Tudor Ionescu,et al.  Optimizing the Trade-Off between Single-Stage and Two-Stage Deep Object Detectors using Image Difficulty Prediction , 2018, 2018 20th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC).

[45]  Ji Wu,et al.  Denoising deep neural networks based voice activity detection , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[46]  Jiwoo Mun,et al.  Automotive Radar Signal Interference Mitigation Using RNN with Self Attention , 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[47]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[48]  Wayne Stark,et al.  Interference in Automotive Radar Systems: Characteristics, mitigation techniques, and current and future research , 2019, IEEE Signal Processing Magazine.

[49]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Debiao Li,et al.  Efficient and Accurate MRI Super-Resolution using a Generative Adversarial Network and 3D Multi-Level Densely Connected Network , 2018, MICCAI.

[51]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[52]  DeLiang Wang,et al.  Supervised Speech Separation Based on Deep Learning: An Overview , 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[53]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[54]  Sanguthevar Rajasekaran,et al.  AutoPrune: Automatic Network Pruning by Regularizing Auxiliary Parameters , 2019, NeurIPS.