Video-based contactless heart-rate detection and counting via joint blind source separation with adaptive noise canceller

Kanghyu Lee, Junmuk Lee, Changwoo Ha, Minseok Han, Hanseok Ko

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Driver assistance systems are a major focus of the automotive industry. Although technological functions that help drivers are improving, themonitoring of driver state functions receives less attention. In this respect, the human heart rate (HR) is one of themost important bio-signals, and it can be detected remotely using consumer-grade cameras. Based on this, a video-based driver state monitoring system using HR signals is proposed in this paper. In a practical automotive environment, monitoring the HR is very challenging due to changes in illumination, vibrations, and human motion. In order to overcome these problems, source separation strategies were employed using joint blind source separation, and feature combination was adopted tomaximize HR variation. Noise-assisted data analysis was then adopted using ensemble empiricalmode decomposition to extract the pure HR. Finally, power spectral density analysis was conducted in the frequency domain, and a post-processing smoothing filter was applied. The performance of the proposed approach was tested based on commonly employedmetrics using the MAHNOB-HCI public dataset and compared with recently proposed competing methods. The experimental results proved that ourmethod is robust for a variety of driving conditions based on testing using a driving dataset and static indoor environments.

Original languageEnglish
Article number4349
JournalApplied Sciences (Switzerland)
Volume9
Issue number20
DOIs
Publication statusPublished - 2019 Oct 1

Fingerprint

heart rate
Blind source separation
counting
Source separation
Monitoring
Power spectral density
Human computer interaction
Automotive industry
smoothing
grade
Lighting
Cameras
industries
illumination
cameras
Decomposition
decomposition
filters
vibration
Testing

Keywords

  • Blind source separation
  • Cardiac signal
  • Heart rate
  • Remote photoplethysmography

ASJC Scopus subject areas

  • Materials Science(all)
  • Instrumentation
  • Engineering(all)
  • Process Chemistry and Technology
  • Computer Science Applications
  • Fluid Flow and Transfer Processes

Cite this

Video-based contactless heart-rate detection and counting via joint blind source separation with adaptive noise canceller. / Lee, Kanghyu; Lee, Junmuk; Ha, Changwoo; Han, Minseok; Ko, Hanseok.

In: Applied Sciences (Switzerland), Vol. 9, No. 20, 4349, 01.10.2019.

Research output: Contribution to journalArticle

@article{afddb545b2fa4f2e892ae8a9a7903882,
title = "Video-based contactless heart-rate detection and counting via joint blind source separation with adaptive noise canceller",
abstract = "Driver assistance systems are a major focus of the automotive industry. Although technological functions that help drivers are improving, themonitoring of driver state functions receives less attention. In this respect, the human heart rate (HR) is one of themost important bio-signals, and it can be detected remotely using consumer-grade cameras. Based on this, a video-based driver state monitoring system using HR signals is proposed in this paper. In a practical automotive environment, monitoring the HR is very challenging due to changes in illumination, vibrations, and human motion. In order to overcome these problems, source separation strategies were employed using joint blind source separation, and feature combination was adopted tomaximize HR variation. Noise-assisted data analysis was then adopted using ensemble empiricalmode decomposition to extract the pure HR. Finally, power spectral density analysis was conducted in the frequency domain, and a post-processing smoothing filter was applied. The performance of the proposed approach was tested based on commonly employedmetrics using the MAHNOB-HCI public dataset and compared with recently proposed competing methods. The experimental results proved that ourmethod is robust for a variety of driving conditions based on testing using a driving dataset and static indoor environments.",
keywords = "Blind source separation, Cardiac signal, Heart rate, Remote photoplethysmography",
author = "Kanghyu Lee and Junmuk Lee and Changwoo Ha and Minseok Han and Hanseok Ko",
year = "2019",
month = "10",
day = "1",
doi = "10.3390/app9204349",
language = "English",
volume = "9",
journal = "Applied Sciences (Switzerland)",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "20",

}

TY - JOUR

T1 - Video-based contactless heart-rate detection and counting via joint blind source separation with adaptive noise canceller

AU - Lee, Kanghyu

AU - Lee, Junmuk

AU - Ha, Changwoo

AU - Han, Minseok

AU - Ko, Hanseok

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Driver assistance systems are a major focus of the automotive industry. Although technological functions that help drivers are improving, themonitoring of driver state functions receives less attention. In this respect, the human heart rate (HR) is one of themost important bio-signals, and it can be detected remotely using consumer-grade cameras. Based on this, a video-based driver state monitoring system using HR signals is proposed in this paper. In a practical automotive environment, monitoring the HR is very challenging due to changes in illumination, vibrations, and human motion. In order to overcome these problems, source separation strategies were employed using joint blind source separation, and feature combination was adopted tomaximize HR variation. Noise-assisted data analysis was then adopted using ensemble empiricalmode decomposition to extract the pure HR. Finally, power spectral density analysis was conducted in the frequency domain, and a post-processing smoothing filter was applied. The performance of the proposed approach was tested based on commonly employedmetrics using the MAHNOB-HCI public dataset and compared with recently proposed competing methods. The experimental results proved that ourmethod is robust for a variety of driving conditions based on testing using a driving dataset and static indoor environments.

AB - Driver assistance systems are a major focus of the automotive industry. Although technological functions that help drivers are improving, themonitoring of driver state functions receives less attention. In this respect, the human heart rate (HR) is one of themost important bio-signals, and it can be detected remotely using consumer-grade cameras. Based on this, a video-based driver state monitoring system using HR signals is proposed in this paper. In a practical automotive environment, monitoring the HR is very challenging due to changes in illumination, vibrations, and human motion. In order to overcome these problems, source separation strategies were employed using joint blind source separation, and feature combination was adopted tomaximize HR variation. Noise-assisted data analysis was then adopted using ensemble empiricalmode decomposition to extract the pure HR. Finally, power spectral density analysis was conducted in the frequency domain, and a post-processing smoothing filter was applied. The performance of the proposed approach was tested based on commonly employedmetrics using the MAHNOB-HCI public dataset and compared with recently proposed competing methods. The experimental results proved that ourmethod is robust for a variety of driving conditions based on testing using a driving dataset and static indoor environments.

KW - Blind source separation

KW - Cardiac signal

KW - Heart rate

KW - Remote photoplethysmography

UR - http://www.scopus.com/inward/record.url?scp=85074176409&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074176409&partnerID=8YFLogxK

U2 - 10.3390/app9204349

DO - 10.3390/app9204349

M3 - Article

AN - SCOPUS:85074176409

VL - 9

JO - Applied Sciences (Switzerland)

JF - Applied Sciences (Switzerland)

SN - 2076-3417

IS - 20

M1 - 4349

ER -