A Mobile-Phone Pose Estimation for Gym-Exercise Form Correction

Matthew Turner; Kofi Essuming Appiah; Sze Chai Kwok

A Mobile-Phone Pose Estimation for Gym-Exercise Form Correction

Matthew Turner, Kofi Essuming Appiah, Sze Chai Kwok

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

People learn to perform exercises with good pose (or form) via research or instruction from an experienced individual such as a personal trainer, but 33.3% of injuries still occur due to incorrect form. It is known that the presence of a personal trainer causes a significant reduction in the rate that injuries occur. There are many possible reasons for this such as cost, scheduling limitations and desire to train alone. However, given that 91% of UK adults use a smartphone, a mobile APP could take on the role of a personal trainer. This paper presents a solution using machine learning and a novel proposed method of form anomaly detection to offer form corrections from live exercise video while only using the capabilities of a mobile device. Overall, the work in this paper is capable detecting incorrect exercise pose and offer valid corrections based on the detected anomalies. Experiments have been conducted on live video to judge the system performance in real-time.
Keywords: Pose Estimation, Deep Learning, Mobile Application, Electronic Gym Instructor.

Original language	English
Title of host publication	Proceedings, Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Pages	559-566
Number of pages	8
Publication status	Published - 29 Feb 2024
Event	Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Rome, Italy Duration: 27 Feb 2024 → 29 Feb 2024 Conference number: 19 https://www.insticc.org/node/technicalprogram/visigrapp/2024/

Conference

Conference	Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Abbreviated title	VISAPP
Country/Territory	Italy
City	Rome
Period	27/02/24 → 29/02/24
Internet address	https://www.insticc.org/node/technicalprogram/visigrapp/2024/

Bibliographical note

This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.

Keywords

Pose Estimation
Deep Learning
Mobile Application
Electronic Gym Instructor

Access to Document

VISAPP_2024_266_CR
This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.
Accepted author manuscript, 10.6 MBLicence: CC BY

Cite this

@inproceedings{103bcc345c8e47f798c8a4481836a822,

title = "A Mobile-Phone Pose Estimation for Gym-Exercise Form Correction",

abstract = "People learn to perform exercises with good pose (or form) via research or instruction from an experienced individual such as a personal trainer, but 33.3% of injuries still occur due to incorrect form. It is known that the presence of a personal trainer causes a significant reduction in the rate that injuries occur. There are many possible reasons for this such as cost, scheduling limitations and desire to train alone. However, given that 91% of UK adults use a smartphone, a mobile APP could take on the role of a personal trainer. This paper presents a solution using machine learning and a novel proposed method of form anomaly detection to offer form corrections from live exercise video while only using the capabilities of a mobile device. Overall, the work in this paper is capable detecting incorrect exercise pose and offer valid corrections based on the detected anomalies. Experiments have been conducted on live video to judge the system performance in real-time.Keywords: Pose Estimation, Deep Learning, Mobile Application, Electronic Gym Instructor.",

keywords = "Pose Estimation, Deep Learning, Mobile Application, Electronic Gym Instructor",

author = "{Matthew Turner} and Appiah, {Kofi Essuming} and {Sze Chai Kwok}",

note = "This is an author-produced version of the published paper. Uploaded in accordance with the University{\textquoteright}s Research Publications and Open Access policy. ; Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, VISAPP ; Conference date: 27-02-2024 Through 29-02-2024",

year = "2024",

month = feb,

day = "29",

language = "English",

pages = "559--566",

booktitle = "Proceedings, Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications",

url = "https://www.insticc.org/node/technicalprogram/visigrapp/2024/",

}

TY - GEN

T1 - A Mobile-Phone Pose Estimation for Gym-Exercise Form Correction

AU - Matthew Turner

AU - Appiah, Kofi Essuming

AU - Sze Chai Kwok

N1 - Conference code: 19

PY - 2024/2/29

Y1 - 2024/2/29

N2 - People learn to perform exercises with good pose (or form) via research or instruction from an experienced individual such as a personal trainer, but 33.3% of injuries still occur due to incorrect form. It is known that the presence of a personal trainer causes a significant reduction in the rate that injuries occur. There are many possible reasons for this such as cost, scheduling limitations and desire to train alone. However, given that 91% of UK adults use a smartphone, a mobile APP could take on the role of a personal trainer. This paper presents a solution using machine learning and a novel proposed method of form anomaly detection to offer form corrections from live exercise video while only using the capabilities of a mobile device. Overall, the work in this paper is capable detecting incorrect exercise pose and offer valid corrections based on the detected anomalies. Experiments have been conducted on live video to judge the system performance in real-time.Keywords: Pose Estimation, Deep Learning, Mobile Application, Electronic Gym Instructor.

AB - People learn to perform exercises with good pose (or form) via research or instruction from an experienced individual such as a personal trainer, but 33.3% of injuries still occur due to incorrect form. It is known that the presence of a personal trainer causes a significant reduction in the rate that injuries occur. There are many possible reasons for this such as cost, scheduling limitations and desire to train alone. However, given that 91% of UK adults use a smartphone, a mobile APP could take on the role of a personal trainer. This paper presents a solution using machine learning and a novel proposed method of form anomaly detection to offer form corrections from live exercise video while only using the capabilities of a mobile device. Overall, the work in this paper is capable detecting incorrect exercise pose and offer valid corrections based on the detected anomalies. Experiments have been conducted on live video to judge the system performance in real-time.Keywords: Pose Estimation, Deep Learning, Mobile Application, Electronic Gym Instructor.

KW - Pose Estimation

KW - Deep Learning

KW - Mobile Application

KW - Electronic Gym Instructor

M3 - Conference contribution

SP - 559

EP - 566

BT - Proceedings, Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

T2 - Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications

Y2 - 27 February 2024 through 29 February 2024

ER -