More Reliable Remote Heart Rate Measurement by Signal Quality Indexes

被引:3
作者
Ernst, Hannes [1 ]
Malberg, Hagen [1 ]
Schmidt, Martin [1 ]
机构
[1] Tech Univ Dresden, Inst Biomed Engn, Fetscherstr 29, D-01307 Dresden, Germany
来源
2020 COMPUTING IN CARDIOLOGY | 2020年
关键词
D O I
10.22489/CinC.2020.165
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Accuracy of camera-based heart rate (HRcb) measurement is often impaired by artifacts, which leads to erroneous HRcb and reduced confidence in the measurement. To avoid erroneous HRcb, we investigated six signal quality indexes (SQIs) from the literature in terms of their effect size and combined them to a novel SQI-filter. All analyses were performed on the "Binghamton-Pittsburgh-RPI Multimodal Spontaneous Emotion Database" (BP4D+) in three important color channels. Signal-to-noise ratio, average maximum cross correlation of consecutive segments, and relative difference of spectral peaks were the most powerful SQIs. The SQI-filter increased accuracies of all color channels. Largest improvements (up to 60%) were achieved in the green channel resulting in 80% accuracy. The overall highest accuracy of 84% was reached in the hue channel. Motion-rich videos benefited most from the developed SQI-filter. The presented methodology helps to discard distorted signals. This enables more reliable HRcb data in further applications and increases confidence in the measurement.
引用
收藏
页数:4
相关论文
共 12 条
[1]   Robust Pulse Rate From Chrominance-Based rPPG [J].
de Haan, Gerard ;
Jeanne, Vincent .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2013, 60 (10) :2878-2886
[2]   Color Spaces and Regions of Interest in Camera Based Heart Rate Estimation [J].
Ernst, Hannes ;
Scherpf, Matthieu ;
Malberg, Hagen ;
Schmidt, Martin .
2020 11TH CONFERENCE OF THE EUROPEAN STUDY GROUP ON CARDIOVASCULAR OSCILLATIONS (ESGCO): COMPUTATION AND MODELLING IN PHYSIOLOGY NEW CHALLENGES AND OPPORTUNITIES, 2020,
[3]  
Feng LT, 2015, INT CONF ACOUST SPEE, P1310, DOI 10.1109/ICASSP.2015.7178182
[4]  
Gupta P, 2017, IEEE IMAGE PROC, P4132, DOI 10.1109/ICIP.2017.8297060
[5]   Robust heart rate estimation from multiple asynchronous noisy sources using signal quality indices and a Kalman filter [J].
Li, Q. ;
Mark, R. G. ;
Clifford, G. D. .
PHYSIOLOGICAL MEASUREMENT, 2008, 29 (01) :15-32
[6]   A machine learning approach to multi-level ECG signal quality classification [J].
Li, Qiao ;
Rajagopalan, Cadathur ;
Clifford, Gari D. .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2014, 117 (03) :435-447
[7]   Camera-based photoplethysmography in critical care patients [J].
Rasche, S. ;
Trumpp, A. ;
Waldow, T. ;
Gaetjen, F. ;
Ploetze, K. ;
Wedekind, D. ;
Schmidt, M. ;
Malberg, H. ;
Matschke, K. ;
Zaunseder, S. .
CLINICAL HEMORHEOLOGY AND MICROCIRCULATION, 2016, 64 (01) :77-90
[8]   The value of polarization in camera-based photoplethysmography [J].
Trumpp, Alexander ;
Bauer, Philipp L. ;
Rasche, Stefan ;
Malberg, Hagen ;
Zaunseder, Sebastian .
BIOMEDICAL OPTICS EXPRESS, 2017, 8 (06) :2822-2834
[9]  
Wang WJ, 2016, IEEE IMAGE PROC, P2430, DOI 10.1109/ICIP.2016.7532795
[10]   Cardiovascular assessment by imaging photoplethysmography - a review [J].
Zaunseder, Sebastian ;
Trumpp, Alexander ;
Wedekind, Daniel ;
Malberg, Hagen .
BIOMEDICAL ENGINEERING-BIOMEDIZINISCHE TECHNIK, 2018, 63 (05) :617-634