22 Citations (Scopus)
601 Downloads (Pure)

Abstract

Heartbeat Rate (HR) reveals a person’s health condition. This paper presents an effective system for measuring HR from facial videos acquired in a more realistic environment than the testing environment of current systems. The proposed method utilizes a facial feature point tracking method by combining a
‘Good feature to track’ and a ‘Supervised descent method’ in order to overcome the limitations of currently available facial video based HR measuring systems. Such limitations include, e.g., unrealistic restriction of the
subject’s movement and artificial lighting during data capture. A face quality assessment system is also incorporated to automatically discard low quality faces that occur in a realistic video sequence to reduce
erroneous results. The proposed method is comprehensively tested on the publicly available MAHNOB-HCI database and our local dataset, which are collected in realistic scenarios. Experimental results show that the
proposed system outperforms existing video based systems for HR measurement.
Original languageEnglish
JournalI E E E Intelligent Systems
Volume31
Issue number3
Pages (from-to)40-48
ISSN1541-1672
DOIs
Publication statusPublished - 2016

Fingerprint

Human computer interaction
Data acquisition
Lighting
Health
Testing

Keywords

  • Heartbeat rate
  • facial video
  • supervised descent method (SDM)
  • good feature to track (GFT)
  • Head motion detection

Cite this

@article{4505dca611b34e5c98f543e74f7c9a41,
title = "Heartbeat Rate Measurement from Facial Video",
abstract = "Heartbeat Rate (HR) reveals a person’s health condition. This paper presents an effective system for measuring HR from facial videos acquired in a more realistic environment than the testing environment of current systems. The proposed method utilizes a facial feature point tracking method by combining a‘Good feature to track’ and a ‘Supervised descent method’ in order to overcome the limitations of currently available facial video based HR measuring systems. Such limitations include, e.g., unrealistic restriction of thesubject’s movement and artificial lighting during data capture. A face quality assessment system is also incorporated to automatically discard low quality faces that occur in a realistic video sequence to reduceerroneous results. The proposed method is comprehensively tested on the publicly available MAHNOB-HCI database and our local dataset, which are collected in realistic scenarios. Experimental results show that theproposed system outperforms existing video based systems for HR measurement.",
keywords = "Heartbeat rate, facial video, supervised descent method (SDM), good feature to track (GFT), Head motion detection",
author = "Haque, {Mohammad Ahsanul} and Ramin Irani and Kamal Nasrollahi and Moeslund, {Thomas B.}",
year = "2016",
doi = "10.1109/MIS.2016.20",
language = "English",
volume = "31",
pages = "40--48",
journal = "I E E E Intelligent Systems",
issn = "1541-1672",
publisher = "IEEE",
number = "3",

}

Heartbeat Rate Measurement from Facial Video. / Haque, Mohammad Ahsanul; Irani, Ramin; Nasrollahi, Kamal; Moeslund, Thomas B.

In: I E E E Intelligent Systems, Vol. 31, No. 3, 2016, p. 40-48.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Heartbeat Rate Measurement from Facial Video

AU - Haque, Mohammad Ahsanul

AU - Irani, Ramin

AU - Nasrollahi, Kamal

AU - Moeslund, Thomas B.

PY - 2016

Y1 - 2016

N2 - Heartbeat Rate (HR) reveals a person’s health condition. This paper presents an effective system for measuring HR from facial videos acquired in a more realistic environment than the testing environment of current systems. The proposed method utilizes a facial feature point tracking method by combining a‘Good feature to track’ and a ‘Supervised descent method’ in order to overcome the limitations of currently available facial video based HR measuring systems. Such limitations include, e.g., unrealistic restriction of thesubject’s movement and artificial lighting during data capture. A face quality assessment system is also incorporated to automatically discard low quality faces that occur in a realistic video sequence to reduceerroneous results. The proposed method is comprehensively tested on the publicly available MAHNOB-HCI database and our local dataset, which are collected in realistic scenarios. Experimental results show that theproposed system outperforms existing video based systems for HR measurement.

AB - Heartbeat Rate (HR) reveals a person’s health condition. This paper presents an effective system for measuring HR from facial videos acquired in a more realistic environment than the testing environment of current systems. The proposed method utilizes a facial feature point tracking method by combining a‘Good feature to track’ and a ‘Supervised descent method’ in order to overcome the limitations of currently available facial video based HR measuring systems. Such limitations include, e.g., unrealistic restriction of thesubject’s movement and artificial lighting during data capture. A face quality assessment system is also incorporated to automatically discard low quality faces that occur in a realistic video sequence to reduceerroneous results. The proposed method is comprehensively tested on the publicly available MAHNOB-HCI database and our local dataset, which are collected in realistic scenarios. Experimental results show that theproposed system outperforms existing video based systems for HR measurement.

KW - Heartbeat rate

KW - facial video

KW - supervised descent method (SDM)

KW - good feature to track (GFT)

KW - Head motion detection

U2 - 10.1109/MIS.2016.20

DO - 10.1109/MIS.2016.20

M3 - Journal article

VL - 31

SP - 40

EP - 48

JO - I E E E Intelligent Systems

JF - I E E E Intelligent Systems

SN - 1541-1672

IS - 3

ER -