Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals

Jakob Möderl; Erik Leitinger; Franz Pernkopf; Klaus Witrisal

doi:10.1109/ICASSP49357.2023.10095725

Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals

Jakob Möderl^*, Erik Leitinger, Franz Pernkopf, Klaus Witrisal

^*Corresponding author for this work

Institute of Signal Processing and Speech Communication (4420)

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

Abstract

We present a variational message passing (VMP)-based approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In the process, the respiratory motion is estimated for contact-free vital sign monitoring. The received signal is modeled as a backscatter channel and the respiratory motion and propagation channels are estimated using VMP. We use the evidence lower bound (ELBO) to approximate the model evidence for the detection. Numerical analyses and measurements demonstrate that the proposed method leads to a significant improvement in the detection performance compared to a fast Fourier transform (FFT)-based detector or an estimator-correlator in low-signal-to-noise ratio (SNR) conditions, since the multipath components (MPCs) are better incorporated into the detection procedure. Specifically, the proposed method has a detection probability of 0.95 at −20dB SNR, while the estimator-correlator and FFT-based detector have 0.32 and 0.05, respectively.

Original language	English
Title of host publication	ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
Number of pages	5
ISBN (Electronic)	9781728163277
DOIs	https://doi.org/10.1109/ICASSP49357.2023.10095725
Publication status	Published - 7 Jun 2023
Event	48th IEEE International Conference on Acoustics, Speech, and Signal Processing: ICASSP 2023 - Rhodos, Greece Duration: 4 Jun 2023 → 9 Jun 2023

Publication series

Name	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume	2023-June
ISSN (Print)	1520-6149

Conference

Conference	48th IEEE International Conference on Acoustics, Speech, and Signal Processing
Abbreviated title	ICASSP 2023
Country/Territory	Greece
City	Rhodos
Period	4/06/23 → 9/06/23

Keywords

occupancy detection
Ultra-wideband radar
variational message passing
vital sign estimation

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Access to Document

10.1109/ICASSP49357.2023.10095725

Cite this

Möderl, J., Leitinger, E., Pernkopf, F., & Witrisal, K. (2023). Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June). https://doi.org/10.1109/ICASSP49357.2023.10095725

Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. / Möderl, Jakob ; Leitinger, Erik ; Pernkopf, Franz et al.
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2023-June).

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

Möderl, J , Leitinger, E , Pernkopf, F & Witrisal, K 2023, Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. in ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2023-June, 48th IEEE International Conference on Acoustics, Speech, and Signal Processing, Rhodos, Greece, 4/06/23. https://doi.org/10.1109/ICASSP49357.2023.10095725

Möderl J , Leitinger E , Pernkopf F , Witrisal K. Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. In ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Epub 2023 May 9. doi: 10.1109/ICASSP49357.2023.10095725

Möderl, Jakob ; Leitinger, Erik ; Pernkopf, Franz et al. / Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals. ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings. 2023. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

@inproceedings{1de3cc8e0af94feba60d551153f9980a,

title = "Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals",

abstract = "We present a variational message passing (VMP)-based approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In the process, the respiratory motion is estimated for contact-free vital sign monitoring. The received signal is modeled as a backscatter channel and the respiratory motion and propagation channels are estimated using VMP. We use the evidence lower bound (ELBO) to approximate the model evidence for the detection. Numerical analyses and measurements demonstrate that the proposed method leads to a significant improvement in the detection performance compared to a fast Fourier transform (FFT)-based detector or an estimator-correlator in low-signal-to-noise ratio (SNR) conditions, since the multipath components (MPCs) are better incorporated into the detection procedure. Specifically, the proposed method has a detection probability of 0.95 at −20dB SNR, while the estimator-correlator and FFT-based detector have 0.32 and 0.05, respectively.",

keywords = "occupancy detection, Ultra-wideband radar, variational message passing, vital sign estimation",

author = "Jakob M{\"o}derl and Erik Leitinger and Franz Pernkopf and Klaus Witrisal",

year = "2023",

month = jun,

day = "7",

doi = "10.1109/ICASSP49357.2023.10095725",

language = "English",

series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",

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

note = "48th IEEE International Conference on Acoustics, Speech, and Signal Processing : ICASSP 2023, ICASSP 2023 ; Conference date: 04-06-2023 Through 09-06-2023",

}

TY - GEN

T1 - Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals

AU - Möderl, Jakob

AU - Leitinger, Erik

AU - Pernkopf, Franz

AU - Witrisal, Klaus

PY - 2023/6/7

Y1 - 2023/6/7

N2 - We present a variational message passing (VMP)-based approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In the process, the respiratory motion is estimated for contact-free vital sign monitoring. The received signal is modeled as a backscatter channel and the respiratory motion and propagation channels are estimated using VMP. We use the evidence lower bound (ELBO) to approximate the model evidence for the detection. Numerical analyses and measurements demonstrate that the proposed method leads to a significant improvement in the detection performance compared to a fast Fourier transform (FFT)-based detector or an estimator-correlator in low-signal-to-noise ratio (SNR) conditions, since the multipath components (MPCs) are better incorporated into the detection procedure. Specifically, the proposed method has a detection probability of 0.95 at −20dB SNR, while the estimator-correlator and FFT-based detector have 0.32 and 0.05, respectively.

AB - We present a variational message passing (VMP)-based approach to detect the presence of a person based on their respiratory chest motion using multistatic ultra-wideband (UWB) radar. In the process, the respiratory motion is estimated for contact-free vital sign monitoring. The received signal is modeled as a backscatter channel and the respiratory motion and propagation channels are estimated using VMP. We use the evidence lower bound (ELBO) to approximate the model evidence for the detection. Numerical analyses and measurements demonstrate that the proposed method leads to a significant improvement in the detection performance compared to a fast Fourier transform (FFT)-based detector or an estimator-correlator in low-signal-to-noise ratio (SNR) conditions, since the multipath components (MPCs) are better incorporated into the detection procedure. Specifically, the proposed method has a detection probability of 0.95 at −20dB SNR, while the estimator-correlator and FFT-based detector have 0.32 and 0.05, respectively.

KW - occupancy detection

KW - Ultra-wideband radar

KW - variational message passing

KW - vital sign estimation

UR - http://www.scopus.com/inward/record.url?scp=85176488563&partnerID=8YFLogxK

U2 - 10.1109/ICASSP49357.2023.10095725

DO - 10.1109/ICASSP49357.2023.10095725

M3 - Conference paper

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

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

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

Y2 - 4 June 2023 through 9 June 2023

ER -

Variational Message Passing-based Respiratory Motion Estimation and Detection Using Radar Signals

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

CD-Laboratory for Dependable Intelligent Systems in Harsh Environments

SEAMAL Front - Securely Applied Machine Learning