Video Analytic Based Health Monitoring for Driver in Moving Vehicle by Extracting Effective Heart Rate Inducing Features

Kanghyu Lee, David K. Han, Hanseok Ko

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

We propose a novel remote heart rate (HR) estimation method using facial images based on video analytics. Most of previous methods have been demonstrated in well-controlled indoor environments. In contrast, this paper proposes a practical video analytic framework under actual driving conditions by extracting key HR inducing features. In particular, when cars are driven, effective and stable HR estimation becomes challenging as there are many dynamic elements, such as rapid illumination changes, vibrations, and ambient lighting that can exist in the vehicle interior. To overcome those disturbances of HR estimation, the driver face region is first detected and cropped to the region of interest (RoI). Second, the components related to HR are extracted from mixed noisy components using ensemble empirical mode decomposition (EEMD). Finally, the extracted signal is analyzed in frequency domain and smoothed with temporal filtering. To verify our approach, the proposed method is compared with recent prominent methods employing a public HCI dataset. It has been demonstrated that the proposed approach delivers superior performance under driving conditions using Bland-Altman plots.

Original languageEnglish
Article number8513487
JournalJournal of Advanced Transportation
Volume2018
DOIs
Publication statusPublished - 2018 Jan 1

Fingerprint

Health
Monitoring
Lighting
Human computer interaction
Railroad cars
Decomposition

ASJC Scopus subject areas

  • Automotive Engineering
  • Economics and Econometrics
  • Mechanical Engineering
  • Computer Science Applications
  • Strategy and Management

Cite this

Video Analytic Based Health Monitoring for Driver in Moving Vehicle by Extracting Effective Heart Rate Inducing Features. / Lee, Kanghyu; Han, David K.; Ko, Hanseok.

In: Journal of Advanced Transportation, Vol. 2018, 8513487, 01.01.2018.

Research output: Contribution to journalArticle

@article{4506278afdd9418a832ef99c9fd514a4,
title = "Video Analytic Based Health Monitoring for Driver in Moving Vehicle by Extracting Effective Heart Rate Inducing Features",
abstract = "We propose a novel remote heart rate (HR) estimation method using facial images based on video analytics. Most of previous methods have been demonstrated in well-controlled indoor environments. In contrast, this paper proposes a practical video analytic framework under actual driving conditions by extracting key HR inducing features. In particular, when cars are driven, effective and stable HR estimation becomes challenging as there are many dynamic elements, such as rapid illumination changes, vibrations, and ambient lighting that can exist in the vehicle interior. To overcome those disturbances of HR estimation, the driver face region is first detected and cropped to the region of interest (RoI). Second, the components related to HR are extracted from mixed noisy components using ensemble empirical mode decomposition (EEMD). Finally, the extracted signal is analyzed in frequency domain and smoothed with temporal filtering. To verify our approach, the proposed method is compared with recent prominent methods employing a public HCI dataset. It has been demonstrated that the proposed approach delivers superior performance under driving conditions using Bland-Altman plots.",
author = "Kanghyu Lee and Han, {David K.} and Hanseok Ko",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/8513487",
language = "English",
volume = "2018",
journal = "Journal of Advanced Transportation",
issn = "0197-6729",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Video Analytic Based Health Monitoring for Driver in Moving Vehicle by Extracting Effective Heart Rate Inducing Features

AU - Lee, Kanghyu

AU - Han, David K.

AU - Ko, Hanseok

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We propose a novel remote heart rate (HR) estimation method using facial images based on video analytics. Most of previous methods have been demonstrated in well-controlled indoor environments. In contrast, this paper proposes a practical video analytic framework under actual driving conditions by extracting key HR inducing features. In particular, when cars are driven, effective and stable HR estimation becomes challenging as there are many dynamic elements, such as rapid illumination changes, vibrations, and ambient lighting that can exist in the vehicle interior. To overcome those disturbances of HR estimation, the driver face region is first detected and cropped to the region of interest (RoI). Second, the components related to HR are extracted from mixed noisy components using ensemble empirical mode decomposition (EEMD). Finally, the extracted signal is analyzed in frequency domain and smoothed with temporal filtering. To verify our approach, the proposed method is compared with recent prominent methods employing a public HCI dataset. It has been demonstrated that the proposed approach delivers superior performance under driving conditions using Bland-Altman plots.

AB - We propose a novel remote heart rate (HR) estimation method using facial images based on video analytics. Most of previous methods have been demonstrated in well-controlled indoor environments. In contrast, this paper proposes a practical video analytic framework under actual driving conditions by extracting key HR inducing features. In particular, when cars are driven, effective and stable HR estimation becomes challenging as there are many dynamic elements, such as rapid illumination changes, vibrations, and ambient lighting that can exist in the vehicle interior. To overcome those disturbances of HR estimation, the driver face region is first detected and cropped to the region of interest (RoI). Second, the components related to HR are extracted from mixed noisy components using ensemble empirical mode decomposition (EEMD). Finally, the extracted signal is analyzed in frequency domain and smoothed with temporal filtering. To verify our approach, the proposed method is compared with recent prominent methods employing a public HCI dataset. It has been demonstrated that the proposed approach delivers superior performance under driving conditions using Bland-Altman plots.

UR - http://www.scopus.com/inward/record.url?scp=85058927669&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85058927669&partnerID=8YFLogxK

U2 - 10.1155/2018/8513487

DO - 10.1155/2018/8513487

M3 - Article

AN - SCOPUS:85058927669

VL - 2018

JO - Journal of Advanced Transportation

JF - Journal of Advanced Transportation

SN - 0197-6729

M1 - 8513487

ER -