Detecting exercise-induced fatigue using thermal imaging and deep learning

Miguel Bordallo Lopez, Carlos R del-Blanco, Narciso Garcia

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

3 Citations (Scopus)

Abstract

Fatigue has adverse effects in both physical and cognitive abilities. Hence, automatically detecting exercise-induced fatigue is of importance, especially in order to assist in the planning of effort and resting during exercise sessions. Thermal imaging and facial analysis provide a mean to detect changes in the human body unobtrusively and in variant conditions of pose and illumination. In this context, this paper proposes the automatic detection of exercise-induced fatigue using thermal cameras and facial images, analyzing them using deep convolutional neural networks. Our results indicate that classification of fatigued individuals is possible, obtaining an accuracy that reaches over 80% when utilizing single thermal images.
Original languageEnglish
Title of host publication 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)
PublisherIEEE Institute of Electrical and Electronic Engineers
Number of pages6
ISBN (Electronic)978-1-5386-1842-4
DOIs
Publication statusPublished - 2017
MoE publication typeA4 Article in a conference publication

Fingerprint

Infrared imaging
Fatigue of materials
Thermal fatigue
Lighting
Cameras
Neural networks
Planning
Deep learning
Hot Temperature

Keywords

  • fatigue detection
  • facial expression
  • deep learning
  • thermal imaging

Cite this

Bordallo Lopez, M., del-Blanco, C. R., & Garcia, N. (2017). Detecting exercise-induced fatigue using thermal imaging and deep learning. In 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA) IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/IPTA.2017.8310151
Bordallo Lopez, Miguel ; del-Blanco, Carlos R ; Garcia, Narciso. / Detecting exercise-induced fatigue using thermal imaging and deep learning. 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE Institute of Electrical and Electronic Engineers , 2017.
@inproceedings{43a8c8e033474e35861792150d15403c,
title = "Detecting exercise-induced fatigue using thermal imaging and deep learning",
abstract = "Fatigue has adverse effects in both physical and cognitive abilities. Hence, automatically detecting exercise-induced fatigue is of importance, especially in order to assist in the planning of effort and resting during exercise sessions. Thermal imaging and facial analysis provide a mean to detect changes in the human body unobtrusively and in variant conditions of pose and illumination. In this context, this paper proposes the automatic detection of exercise-induced fatigue using thermal cameras and facial images, analyzing them using deep convolutional neural networks. Our results indicate that classification of fatigued individuals is possible, obtaining an accuracy that reaches over 80{\%} when utilizing single thermal images.",
keywords = "fatigue detection, facial expression, deep learning, thermal imaging",
author = "{Bordallo Lopez}, Miguel and del-Blanco, {Carlos R} and Narciso Garcia",
year = "2017",
doi = "10.1109/IPTA.2017.8310151",
language = "English",
booktitle = "2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)",
publisher = "IEEE Institute of Electrical and Electronic Engineers",
address = "United States",

}

Bordallo Lopez, M, del-Blanco, CR & Garcia, N 2017, Detecting exercise-induced fatigue using thermal imaging and deep learning. in 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE Institute of Electrical and Electronic Engineers . https://doi.org/10.1109/IPTA.2017.8310151

Detecting exercise-induced fatigue using thermal imaging and deep learning. / Bordallo Lopez, Miguel; del-Blanco, Carlos R; Garcia, Narciso.

2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE Institute of Electrical and Electronic Engineers , 2017.

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - Detecting exercise-induced fatigue using thermal imaging and deep learning

AU - Bordallo Lopez, Miguel

AU - del-Blanco, Carlos R

AU - Garcia, Narciso

PY - 2017

Y1 - 2017

N2 - Fatigue has adverse effects in both physical and cognitive abilities. Hence, automatically detecting exercise-induced fatigue is of importance, especially in order to assist in the planning of effort and resting during exercise sessions. Thermal imaging and facial analysis provide a mean to detect changes in the human body unobtrusively and in variant conditions of pose and illumination. In this context, this paper proposes the automatic detection of exercise-induced fatigue using thermal cameras and facial images, analyzing them using deep convolutional neural networks. Our results indicate that classification of fatigued individuals is possible, obtaining an accuracy that reaches over 80% when utilizing single thermal images.

AB - Fatigue has adverse effects in both physical and cognitive abilities. Hence, automatically detecting exercise-induced fatigue is of importance, especially in order to assist in the planning of effort and resting during exercise sessions. Thermal imaging and facial analysis provide a mean to detect changes in the human body unobtrusively and in variant conditions of pose and illumination. In this context, this paper proposes the automatic detection of exercise-induced fatigue using thermal cameras and facial images, analyzing them using deep convolutional neural networks. Our results indicate that classification of fatigued individuals is possible, obtaining an accuracy that reaches over 80% when utilizing single thermal images.

KW - fatigue detection

KW - facial expression

KW - deep learning

KW - thermal imaging

UR - http://www.scopus.com/inward/record.url?scp=85050631616&partnerID=8YFLogxK

U2 - 10.1109/IPTA.2017.8310151

DO - 10.1109/IPTA.2017.8310151

M3 - Conference article in proceedings

BT - 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)

PB - IEEE Institute of Electrical and Electronic Engineers

ER -

Bordallo Lopez M, del-Blanco CR, Garcia N. Detecting exercise-induced fatigue using thermal imaging and deep learning. In 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA). IEEE Institute of Electrical and Electronic Engineers . 2017 https://doi.org/10.1109/IPTA.2017.8310151