Camera Setup and OpenPose Software without GPU for Calibration and Recording in Telerehabilitation Use
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21460%2F21%3A00354734" target="_blank" >RIV/68407700:21460/21:00354734 - isvavai.cz</a>
Alternative codes found
RIV/68407700:21730/21:00354734
Result on the web
<a href="https://doi.org/10.1109/EHB52898.2021.9657743" target="_blank" >https://doi.org/10.1109/EHB52898.2021.9657743</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/EHB52898.2021.9657743" target="_blank" >10.1109/EHB52898.2021.9657743</a>
Alternative languages
Result language
angličtina
Original language name
Camera Setup and OpenPose Software without GPU for Calibration and Recording in Telerehabilitation Use
Original language description
Home exercises are significant in the rehabilitation process of physiotherapy patients, which lack immediate feedback as to the proper movement and therefore might humper patient treatment. In this paper we are proposing an algorithm for fast tracking of human body movements performed during physiotherapeutic exercises using a simple webcam home setup and common domestically available CPU computing resources. We use OpenPose for detecting body vertices in key frames and a novel vertex tracking algorithm between video frames, which leverages encoded video Motion Vectors (MVs). We show excellent tracking accuracy between frames and x15 reduction in time, as compared to native OpenPose, which would require a Graphical Processing Unit (GPU) to perform in real time. We further provide a design and implementation of a precision camera system consisting of two cameras in the frontal and lateral direction, which were precisely positioned using a laser cross. This system will be also used to verify whether the webcam is able to record with sufficient quality to further image processing analysis. As part of this work, a camera system including supporting calibration and recording scripts was designed and implemented. The cameras triggers were synchronized by wire interconnection and set up by proposed script. In this work we synchronize two cameras and align their frames such that the OpenPose can be applied independently to each of the two channels to measure movements from two different body projections (3D).
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
20601 - Medical engineering
Result continuities
Project
<a href="/en/project/LTAIZ19008" target="_blank" >LTAIZ19008: Enhancing Robotic Physiotherapeutic Treatments using Machine Learning</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2021
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
2021 International Conference on e-Health and Bioengineering (EHB)
ISBN
978-1-6654-4000-4
ISSN
2575-5137
e-ISSN
2575-5145
Number of pages
4
Pages from-to
1-4
Publisher name
IEEE Industrial Electronic Society
Place of publication
Vienna
Event location
Iasi
Event date
Nov 18, 2021
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000802227900203