DeepPerfusion: Camera-based Blood Volume Pulse Extraction Using a 3D Convolutional Neural Network

Research output: Contribution to book/conference proceedings/anthology/reportConference contributionContributedpeer-review

Abstract

Imaging photoplethysmography (iPPG) is a camera-based approach for the remote extraction of the blood volume pulse (BVP) most commonly applied to facial video recordings. The major challenges of this promising technique are the low amplitude of BVP signals and their superposition with artifacts as well as physiological and non-physiological movement induced distortions. We addressed this complexity with a 3D convolutional neural network, which we called DeepPerfusion, to improve BVP extraction from iPPG. Our approach is based on the idea of enabling DeepPerfusion to learn the extraction of the BVP from videos by understanding their relation to the ground truth signals. First results show that DeepPer-fusion outperforms state-of-the-art algorithms for remote BVP extraction demonstrating a mean absolute error of 0.66 beats per minute (up to 60 % improvement) regarding the BVP based pulse rate estimation for 21 randomly chosen held out test subjects of the UBFC dataset.

Details

Original languageEnglish
Title of host publication47th Conference Computing in Cardiology (CinC)
PublisherIEEE Computer Society, Washington
ISBN (electronic)9781728173825
Publication statusPublished - 13 Sept 2020
Peer-reviewedYes

Conference

Title2020 Computing in Cardiology
Abbreviated titleCinC 2020
Conference number47
Duration13 - 16 September 2020
Website
Degree of recognitionInternational event
LocationRimini Palacongressi & online
CityRimini
CountryItaly

External IDs

ORCID /0000-0001-6754-5257/work/142232818
ORCID /0000-0003-4012-0608/work/142235697