Literature DB >> 31479423

Robust heart-rate estimation from facial videos using Project_ICA.

Lin Qi1, Huidong Yu, Lisheng Xu, Ramadhani Selemani Mpanda, Stephen E Greenwald.   

Abstract

OBJECTIVE: Remote photoplethysmography (rPPG) can achieve non-contact measurement of heart rate (HR) from a continuous video sequence by scanning the skin surface. However, practical applications are still limited by factors such as non-rigid facial motion and head movement. In this work, a detailed system framework for remotely estimating heart rate from facial videos under various movement conditions is described. APPROACH: After the rPPG signal has been obtained from a defined region of the facial skin, a method, termed 'Project_ICA', based on a skin reflection model, is employed to extract the pulse signal from the original signal. MAIN
RESULTS: To evaluate the performance of the proposed algorithm, a dataset containing 112 videos including the challenges of various skin tones, body motion and HR recovery after exercise was created from 28 participants. SIGNIFICANCE: The results show that Project_ICA, when evaluated by several criteria, provides a more accurate and robust estimate of HR than most existing methods, although problems remain in obtaining reliable measurements from dark-skinned subjects.

Entities:  

Mesh:

Year:  2019        PMID: 31479423     DOI: 10.1088/1361-6579/ab2c9f

Source DB:  PubMed          Journal:  Physiol Meas        ISSN: 0967-3334            Impact factor:   2.833


  3 in total

Review 1.  Continuous Monitoring of Vital Signs Using Cameras: A Systematic Review.

Authors:  Vinothini Selvaraju; Nicolai Spicher; Ju Wang; Nagarajan Ganapathy; Joana M Warnecke; Steffen Leonhardt; Ramakrishnan Swaminathan; Thomas M Deserno
Journal:  Sensors (Basel)       Date:  2022-05-28       Impact factor: 3.847

2.  Non-Contact Heart Rate Detection When Face Information Is Missing during Online Learning.

Authors:  Kun Zheng; Kangyi Ci; Jinling Cui; Jiangping Kong; Jing Zhou
Journal:  Sensors (Basel)       Date:  2020-12-08       Impact factor: 3.576

3.  Heart rate prediction from facial video with masks using eye location and corrected by convolutional neural networks.

Authors:  Kun Zheng; Kangyi Ci; Hui Li; Lei Shao; Guangmin Sun; Junhua Liu; Jinling Cui
Journal:  Biomed Signal Process Control       Date:  2022-03-09       Impact factor: 3.880

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.