Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding

J. Overdevest; A.G.C. Koppelaar; M.J.G. Bekooij; J. Youn; R.J.G. van Sloun

doi:10.1109/ICASSP49357.2023.10096297

Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding

J. Overdevest, A.G.C. Koppelaar, M.J.G. Bekooij, J. Youn, R.J.G. van Sloun

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

7 Citations (Scopus)

17 Downloads (Pure)

Abstract

Removal of frequency-modulated continuous wave (FMCW) interference by zeroing corrupted samples causes significant distortions and peak power losses in the range-Doppler map. Existing methods aim to diminish these distortions by utilizing data from one dimension to reconstruct the corrupted samples, which do not perform well when a large number of samples are interfered and have diﬃculty recovering weak target signals.In this paper, model-based deep learning interference mitigation algorithms, called ALISTA and ALFISTA, are presented that reduce these artifacts by leveraging the full integration gain using all uncorrupted fast-time and slow-time samples. Simulations with 50% corrupted samples show that target peak power loss and velocity peak-to-sidelobe ratio (VPSR) with a 20-layer ALFISTA improves with 5.5 and 9.6 dB compared to zeroing. Furthermore, significant improvements in precision and recall are observed, even when large amounts (50-80%) of samples are missing.

Original language	English
Title of host publication	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Publisher	Institute of Electrical and Electronics Engineers
Number of pages	5
ISBN (Electronic)	978-1-7281-6327-7
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10096297
Publication status	Published - 5 May 2023
Event	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece Duration: 4 Jun 2023 → 10 Jun 2023

Conference

Conference	48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
Abbreviated title	ICASSP 2023
Country/Territory	Greece
City	Rhodes Island
Period	4/06/23 → 10/06/23

Keywords

ALFISTA
ALISTA
Deep Unfolding
Radar Interference Mitigation
Signal Reconstruction

Access to Document

10.1109/ICASSP49357.2023.10096297

pdfFinal published version, 1.36 MBLicence: TAVERNE

Cite this

Overdevest, J., Koppelaar, A. G. C., Bekooij, M. J. G., Youn, J., & Sloun, R. J. G. V. (2023). Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Article 10096297 Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICASSP49357.2023.10096297

@inproceedings{a10b4e7753c4490986112c3632cb2b90,

title = "Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding",

abstract = "Removal of frequency-modulated continuous wave (FMCW) interference by zeroing corrupted samples causes significant distortions and peak power losses in the range-Doppler map. Existing methods aim to diminish these distortions by utilizing data from one dimension to reconstruct the corrupted samples, which do not perform well when a large number of samples are interfered and have diﬃculty recovering weak target signals.In this paper, model-based deep learning interference mitigation algorithms, called ALISTA and ALFISTA, are presented that reduce these artifacts by leveraging the full integration gain using all uncorrupted fast-time and slow-time samples. Simulations with 50% corrupted samples show that target peak power loss and velocity peak-to-sidelobe ratio (VPSR) with a 20-layer ALFISTA improves with 5.5 and 9.6 dB compared to zeroing. Furthermore, significant improvements in precision and recall are observed, even when large amounts (50-80%) of samples are missing.",

keywords = "Deep learning, Acoustic distortion, Signal processing algorithms, Interference, Signal reconstruction, Radar signal processing, Radar applications, ALFISTA, ALISTA, Deep Unfolding, Radar Interference Mitigation, Signal Reconstruction",

author = "J. Overdevest and A.G.C. Koppelaar and M.J.G. Bekooij and J. Youn and Sloun, {R.J.G. van}",

year = "2023",

month = may,

day = "5",

doi = "10.1109/ICASSP49357.2023.10096297",

language = "English",

booktitle = "ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, ICASSP 2023 ; Conference date: 04-06-2023 Through 10-06-2023",

}

Overdevest, J, Koppelaar, AGC, Bekooij, MJG, Youn, J & Sloun, RJGV 2023, Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 10096297, Institute of Electrical and Electronics Engineers, 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023, Rhodes Island, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10096297

Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding. / Overdevest, J.; Koppelaar, A.G.C.; Bekooij, M.J.G. et al.
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Institute of Electrical and Electronics Engineers, 2023. 10096297.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding

AU - Overdevest, J.

AU - Koppelaar, A.G.C.

AU - Bekooij, M.J.G.

AU - Youn, J.

AU - Sloun, R.J.G. van

PY - 2023/5/5

Y1 - 2023/5/5

N2 - Removal of frequency-modulated continuous wave (FMCW) interference by zeroing corrupted samples causes significant distortions and peak power losses in the range-Doppler map. Existing methods aim to diminish these distortions by utilizing data from one dimension to reconstruct the corrupted samples, which do not perform well when a large number of samples are interfered and have diﬃculty recovering weak target signals.In this paper, model-based deep learning interference mitigation algorithms, called ALISTA and ALFISTA, are presented that reduce these artifacts by leveraging the full integration gain using all uncorrupted fast-time and slow-time samples. Simulations with 50% corrupted samples show that target peak power loss and velocity peak-to-sidelobe ratio (VPSR) with a 20-layer ALFISTA improves with 5.5 and 9.6 dB compared to zeroing. Furthermore, significant improvements in precision and recall are observed, even when large amounts (50-80%) of samples are missing.

AB - Removal of frequency-modulated continuous wave (FMCW) interference by zeroing corrupted samples causes significant distortions and peak power losses in the range-Doppler map. Existing methods aim to diminish these distortions by utilizing data from one dimension to reconstruct the corrupted samples, which do not perform well when a large number of samples are interfered and have diﬃculty recovering weak target signals.In this paper, model-based deep learning interference mitigation algorithms, called ALISTA and ALFISTA, are presented that reduce these artifacts by leveraging the full integration gain using all uncorrupted fast-time and slow-time samples. Simulations with 50% corrupted samples show that target peak power loss and velocity peak-to-sidelobe ratio (VPSR) with a 20-layer ALFISTA improves with 5.5 and 9.6 dB compared to zeroing. Furthermore, significant improvements in precision and recall are observed, even when large amounts (50-80%) of samples are missing.

KW - Deep learning

KW - Acoustic distortion

KW - Signal processing algorithms

KW - Interference

KW - Signal reconstruction

KW - Radar signal processing

KW - Radar applications

KW - ALFISTA

KW - ALISTA

KW - Deep Unfolding

KW - Radar Interference Mitigation

KW - Signal Reconstruction

UR - http://www.scopus.com/inward/record.url?scp=85168782719&partnerID=8YFLogxK

U2 - 10.1109/ICASSP49357.2023.10096297

DO - 10.1109/ICASSP49357.2023.10096297

M3 - Conference contribution

BT - ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - Institute of Electrical and Electronics Engineers

T2 - 48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

Y2 - 4 June 2023 through 10 June 2023

ER -

Signal Reconstruction for FMCW Radar Interference Mitigation Using Deep Unfolding

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this