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

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

5 Citaten (Scopus)

Samenvatting

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.

Originele taal-2	Engels
Titel	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Uitgeverij	Institute of Electrical and Electronics Engineers
Aantal pagina's	5
ISBN van elektronische versie	978-1-7281-6327-7
DOI's	https://doi.org/10.1109/ICASSP49357.2023.10096297
Status	Gepubliceerd - 5 mei 2023
Evenement	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Rhodes Island, Griekenland Duur: 4 jun. 2023 → 10 jun. 2023

Congres

Congres	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Verkorte titel	ICASSP 2023
Land/Regio	Griekenland
Stad	Rhodes Island
Periode	4/06/23 → 10/06/23

Trefwoorden

Deep learning
Acoustic distortion
Signal processing algorithms
Interference
Signal reconstruction
Radar signal processing
Radar applications

Toegang tot document

10.1109/ICASSP49357.2023.10096297

Andere bestanden en links

Link naar publicatie in Scopus

Citeer dit

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) Artikel 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, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Griekenland, 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.

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › 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

Samenvatting

Congres

Trefwoorden

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit