Movement Compensated Driver’s Respiratory Rate Extraction

Abstract

In non-contact vital sign monitoring using radar, radar signal distorted by the surrounding unspecified factors is unsuitable for monitoring vital signs. In order to monitor vital signs accurately, it is essential to compensate for distortion of radar signals caused by surrounding environmental factors. In this paper, we propose a driver vital signal compensation method in driving situations, including the driver’s movements using a frequency-modulated continuous-wave (FMCW) radar. Driver’s movement is quantified from the radar signal and used to set a distortion signal compensation index to compensate for the signal distortion induced in the driving situation that the driver’s movement occurs. The experimental results show that the respiration rate estimated from the radar signal compensated through the proposed method is similar to the actual respiration rate than from the signal before calibration. These results confirm the possibility of using the proposed method in a non-statistic situation and effectiveness in estimating respiration rate reflecting human movement in monitoring vital signs using FMCW radar.

In-Vehicle Monitoring by Radar: A Review

“…Nasal breath sound recordings from a smartphone, ECG (PSL-iECG2) X2 (50×70 mm) [83] The upper left of the windshield 7.29 and 8.748 Pulse oximetry X4M300 (50×70 mm) [84] The lower left of the steering wheel 2.4 Self-assessment of the participant for being drowsy Not specified [94] Behind the seat 60 A pressure sensor is worn on the abdomen 50×50 mm [80] Under the steering wheel 77 ECG, Respiration belt IWR1843BOOST [79] Behind the seat 24 ECG Not specified [88] In the driver's seat Millimeter wave Camera, Wearable physiological detection instrument Not specified [67] Rearview mirror 77 Polar H10 heart monitor AWR1642BOOST [68] Rearview mirror 120 Spirometer Not specified [49] The left top side of the subjects' chest 60 A clinical reference sensor BSM6501K IWR6843 [62] Mobile holder (right side of steering wheel) 60 Air-flow, Temperature sensor XM132 (25×20 mm) [65], [69] In front of the chest of the main subject 60 ECG XM112 [71] On the steering wheel 4.3 Edan iM50 Not specified to assess their proposed algorithms for vital sign monitoring inside a car. As can be seen in Table IX, the most common ground truth for the evaluation of estimated HR is pulse oximetry.…”

“…To improve the quality of vital sign signals inside a vehicle, random human body cancellation has been studied [62], [80], [94]. A slow-time envelope modulation results from the breathing-related vibrations of the chest and the random human body motion.…”

“…Mechanical sensors can be divided into three common categories, including resistive [8], inductive [9], and capacitive [10]. Both resistive 2 Range-doppler map or timefrequency spectrum Artificial intelligence to detect occupied seats [3], [11]- [34] The amplitude of reflected signals Left-behind child [2], [35]- [48] BR and HR difference BR and HR estimation [49]- [51] Gesture recognition to assist drivers Micro-doppler features Artificial intelligence to detect gestures [52]- [59] Occupant status monitoring BR and/or HR estimation None [60]- [77] Sensor placement for accurate BR estimation [78]- [80] Vital sign monitoring in an ambulance [81] Drowsy driving detection [82]- [87] Biometric driver seat [79] Angry driver [88] Multiple targets vital sign monitoring [89], [90] Car vibrations suppression [62], [91]- [93] Changes in the reflected power Distracted driver detection by cellphone [82] Random body movement cancellation [62], [80], [94] Airbag [95] Range-doppler map Distracted/drowsy driver based on head motion [96]- [101] Range doppler map, Changes in the phase of signals Drowsy driver based on eye blink frequency [102]- [107] and inductive sensors have difficulty discriminating between humans and objects [3]. Capacitive sensors which can detect the dielectric dispersion effects on human tissues are prone to high false detections…”

Performance Analysis of the Maximum Likelihood Estimation of Signal Period Length and Its Application in Heart Rate Estimation with Reduced Respiratory Influence

“…The estimated variance of the maximum likelihood estimator of the model ( 4) should be asymptotic to the Cramer-Rao bound in Equation ( 9) [25], and the asymptotic variance of the estimator in Equation ( 2) can be approximated as σ 2 12…”

“…The remote monitoring of human vital signals based on radars, including respiratory and heartbeat rate, is cost-effective and can provide a large amount of health information [1][2][3][4]. The methods proposed in previous studies were able to provide good respiratory rate estimations, while the heartbeat rate estimation was always variable [5].…”