Detecting exercise-induced fatigue using thermal imaging and deep learning

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

doi:10.1109/IPTA.2017.8310151

Detecting exercise-induced fatigue using thermal imaging and deep learning

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

Not published at VTT

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

27 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 language	English
Title of host publication	2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA)
Publisher	IEEE Institute of Electrical and Electronic Engineers
Number of pages	6
ISBN (Electronic)	978-1-5386-1842-4
DOIs	https://doi.org/10.1109/IPTA.2017.8310151
Publication status	Published - 2017
MoE publication type	A4 Article in a conference publication

Keywords

fatigue detection
facial expression
deep learning
thermal imaging

Access to Document

10.1109/IPTA.2017.8310151

Cite this

@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",

}

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 proceeding › Conference article in proceedings › Scientific › peer-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 -

Detecting exercise-induced fatigue using thermal imaging and deep learning

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this