A non-invasive subtle pulse rate extraction method based on Eulerian video magnification

Wei, Y. ORCID: 0000-0001-6195-8595, Gracheva, N. and Tudor, J., 2019. A non-invasive subtle pulse rate extraction method based on Eulerian video magnification. In: Z. Ju, L. Yang, C. Yang, A. Gegov and D. Zhou, eds., Advances in Computational Intelligence Systems: contributions presented at the 19th UK Workshop on Computational Intelligence, September 4-6, 2019, Portsmouth, UK. Advances in intelligent systems and computing (AISC), 1043 . Cham, Switzerland: Springer, pp. 461-471. ISBN 9783030299323

[img]
Preview
Text
15028_Wei.pdf - Pre-print

Download (465kB) | Preview

Abstract

Measuring pulse rate by means of video recording of the wrist area is a non-invasive approach. Eulerian Video Linear Magnification (EVLM) is used in this paper to magnify, and make visible, subtle pulse-induced wrist motions. A series of experiments are conducted to investigate the performance of ELVM under various conditions, such as light intensity, background colour and a set of video recording parameters. The results show that a light intensity of around 224 to 229 lx is optimal; excess or inadequate light significantly impairs the success of amplifying the skin movement resulting from the pulse. It is demonstrated that a white background colour enables both the radial and ulnar areas to be clearly visible in the recorded video, thus improving pulse measurement. In addition, it is shown that a female’s pulse strength is approximately 40 % weaker than that of a male averaged over the participants.

Item Type: Chapter in book
Creators: Wei, Y., Gracheva, N. and Tudor, J.
Publisher: Springer
Place of Publication: Cham, Switzerland
Date: 2019
Volume: 1043
ISBN: 9783030299323
ISSN: 2194-5357
Identifiers:
NumberType
10.1007/978-3-030-29933-0_38DOI
Record created by: Jonathan Gallacher
Date Added: 02 Oct 2019 12:38
Last Modified: 30 Aug 2020 03:00
URI: http://irep.ntu.ac.uk/id/eprint/37894

Actions (login required)

Edit View Edit View

Views

Views per month over past year

Downloads

Downloads per month over past year