No Cover Image

Journal article 304 views 29 downloads

Energy expenditure estimation using visual and inertial sensors / Adeline, Paiement

IET Computer Vision

Swansesa University Authors: Adeline, Paiement, Adeline, Paiement

Abstract

Deriving a person’s energy expenditure accurately forms the foundation for tracking physical activity levels across many health and lifestyle monitoring tasks. In this work, we present a method for estimating calorific expenditure from combined visual and accelerometer sensors by way of an RGB-Depth...

Full description

Published in: IET Computer Vision
ISSN: 1751-9632 1751-9640
Published: 2017
Online Access: Check full text

URI: https://cronfa.swan.ac.uk/Record/cronfa36266
Tags: Add Tag
No Tags, Be the first to tag this record!
first_indexed 2017-10-25T19:11:58Z
last_indexed 2018-02-09T05:28:20Z
id cronfa36266
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2017-12-11T14:22:12.1122263</datestamp><bib-version>v2</bib-version><id>36266</id><entry>2017-10-25</entry><title>Energy expenditure estimation using visual and inertial sensors</title><swanseaauthors><author><sid>f50adf4186d930e3a2a0f9a6d643cf53</sid><ORCID>0000-0001-5114-1514</ORCID><firstname>Adeline</firstname><surname>Paiement</surname><name>Adeline Paiement</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>f50adf4186d930e3a2a0f9a6d643cf53</sid><firstname>Adeline</firstname><surname>Paiement</surname><name>Adeline Paiement</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2017-10-25</date><deptcode>SCS</deptcode><abstract>Deriving a person&#x2019;s energy expenditure accurately forms the foundation for tracking physical activity levels across many health and lifestyle monitoring tasks. In this work, we present a method for estimating calorific expenditure from combined visual and accelerometer sensors by way of an RGB-Depth camera and a wearable inertial sensor. The proposed individual independent framework fuses information from both modalities which leads to improved estimates beyond the accuracy of single modality and manual metabolic lookup table (MET) based methods. For evaluation, we introduce a new dataset called SPHERE_RGBD+Inertial_calorie, for which visual and inertial data is simultaneously obtained with indirect calorimetry ground truth measurements based on gas exchange. Experiments show that the fusion of visual and inertial data reduces the estimation error by 8% and 18% compared to the use of visual only and inertial sensor only, respectively, and by 33% compared to a MET-based approach. We conclude from our results that the proposed approach is suitable for home monitoring in a controlled environment.</abstract><type>Journal Article</type><journal>IET Computer Vision</journal><publisher/><issnPrint>1751-9632</issnPrint><issnElectronic>1751-9640</issnElectronic><keywords/><publishedDay>28</publishedDay><publishedMonth>9</publishedMonth><publishedYear>2017</publishedYear><publishedDate>2017-09-28</publishedDate><doi>10.1049/iet-cvi.2017.0112</doi><url>http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2017.0112</url><notes/><college>COLLEGE NANME</college><department>Computer Science</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>SCS</DepartmentCode><institution>Swansea University</institution><lastEdited>2017-12-11T14:22:12.1122263</lastEdited><Created>2017-10-25T16:00:28.8717691</Created><path><level id="1">College of Science</level><level id="2">Computer Science</level></path><authors><author><firstname>Lili</firstname><surname>Tao</surname><order>1</order></author><author><firstname>Tilo</firstname><surname>Burghardt</surname><order>2</order></author><author><firstname>Majid</firstname><surname>Mirmehdi</surname><order>3</order></author><author><firstname>Dima</firstname><surname>Damen</surname><order>4</order></author><author><firstname>Ashley</firstname><surname>Cooper</surname><order>5</order></author><author><firstname>Massimo</firstname><surname>Camplani</surname><order>6</order></author><author><firstname>Sion</firstname><surname>Hannuna</surname><order>7</order></author><author><firstname>Adeline</firstname><surname>Paiement</surname><order>8</order></author><author><firstname>Ian</firstname><surname>Craddock</surname><order>9</order></author></authors><documents><document><filename>0036266-06122017174611.pdf</filename><originalFilename>IET-CVIv3.pdf</originalFilename><uploaded>2017-12-06T17:46:11.1930000</uploaded><type>Output</type><contentLength>7045360</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><action/><embargoDate>2017-12-06T00:00:00.0000000</embargoDate><documentNotes>CC-BY</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language></document></documents></rfc1807>
spelling 2017-12-11T14:22:12.1122263 v2 36266 2017-10-25 Energy expenditure estimation using visual and inertial sensors f50adf4186d930e3a2a0f9a6d643cf53 0000-0001-5114-1514 Adeline Paiement Adeline Paiement true false f50adf4186d930e3a2a0f9a6d643cf53 Adeline Paiement Adeline Paiement true false 2017-10-25 SCS Deriving a person’s energy expenditure accurately forms the foundation for tracking physical activity levels across many health and lifestyle monitoring tasks. In this work, we present a method for estimating calorific expenditure from combined visual and accelerometer sensors by way of an RGB-Depth camera and a wearable inertial sensor. The proposed individual independent framework fuses information from both modalities which leads to improved estimates beyond the accuracy of single modality and manual metabolic lookup table (MET) based methods. For evaluation, we introduce a new dataset called SPHERE_RGBD+Inertial_calorie, for which visual and inertial data is simultaneously obtained with indirect calorimetry ground truth measurements based on gas exchange. Experiments show that the fusion of visual and inertial data reduces the estimation error by 8% and 18% compared to the use of visual only and inertial sensor only, respectively, and by 33% compared to a MET-based approach. We conclude from our results that the proposed approach is suitable for home monitoring in a controlled environment. Journal Article IET Computer Vision 1751-9632 1751-9640 28 9 2017 2017-09-28 10.1049/iet-cvi.2017.0112 http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2017.0112 COLLEGE NANME Computer Science COLLEGE CODE SCS Swansea University 2017-12-11T14:22:12.1122263 2017-10-25T16:00:28.8717691 College of Science Computer Science Lili Tao 1 Tilo Burghardt 2 Majid Mirmehdi 3 Dima Damen 4 Ashley Cooper 5 Massimo Camplani 6 Sion Hannuna 7 Adeline Paiement 8 Ian Craddock 9 0036266-06122017174611.pdf IET-CVIv3.pdf 2017-12-06T17:46:11.1930000 Output 7045360 application/pdf Version of Record true 2017-12-06T00:00:00.0000000 CC-BY true eng
title Energy expenditure estimation using visual and inertial sensors
spellingShingle Energy expenditure estimation using visual and inertial sensors
Adeline, Paiement
Adeline, Paiement
title_short Energy expenditure estimation using visual and inertial sensors
title_full Energy expenditure estimation using visual and inertial sensors
title_fullStr Energy expenditure estimation using visual and inertial sensors
title_full_unstemmed Energy expenditure estimation using visual and inertial sensors
title_sort Energy expenditure estimation using visual and inertial sensors
author_id_str_mv f50adf4186d930e3a2a0f9a6d643cf53
f50adf4186d930e3a2a0f9a6d643cf53
author_id_fullname_str_mv f50adf4186d930e3a2a0f9a6d643cf53_***_Adeline, Paiement
f50adf4186d930e3a2a0f9a6d643cf53_***_Adeline, Paiement
author Adeline, Paiement
Adeline, Paiement
format Journal article
container_title IET Computer Vision
publishDate 2017
institution Swansea University
issn 1751-9632
1751-9640
doi_str_mv 10.1049/iet-cvi.2017.0112
college_str College of Science
hierarchytype
hierarchy_top_id collegeofscience
hierarchy_top_title College of Science
hierarchy_parent_id collegeofscience
hierarchy_parent_title College of Science
department_str Computer Science{{{_:::_}}}College of Science{{{_:::_}}}Computer Science
url http://digital-library.theiet.org/content/journals/10.1049/iet-cvi.2017.0112
document_store_str 1
active_str 0
description Deriving a person’s energy expenditure accurately forms the foundation for tracking physical activity levels across many health and lifestyle monitoring tasks. In this work, we present a method for estimating calorific expenditure from combined visual and accelerometer sensors by way of an RGB-Depth camera and a wearable inertial sensor. The proposed individual independent framework fuses information from both modalities which leads to improved estimates beyond the accuracy of single modality and manual metabolic lookup table (MET) based methods. For evaluation, we introduce a new dataset called SPHERE_RGBD+Inertial_calorie, for which visual and inertial data is simultaneously obtained with indirect calorimetry ground truth measurements based on gas exchange. Experiments show that the fusion of visual and inertial data reduces the estimation error by 8% and 18% compared to the use of visual only and inertial sensor only, respectively, and by 33% compared to a MET-based approach. We conclude from our results that the proposed approach is suitable for home monitoring in a controlled environment.
published_date 2017-09-28T03:53:45Z
_version_ 1650691434863394816
score 10.8683