Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition

Ramin Irani, Kamal Nasrollahi, Marc Oliu Simon, Ciprian Corneanu, Sergio Escalera Guerrero, Chris Bahnsen, Dennis Holm Lundtoft, Thomas B. Moeslund, Tanja Pedersen, Marie-Louise Klitgaard, Laura Petrini

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

11 Citationer (Scopus)
570 Downloads (Pure)

Resumé

Pain is a vital sign of human health and its automatic detection
can be of crucial importance in many different contexts,
including medical scenarios. While most available
computer vision techniques are based on RGB, in this paper,
we investigate the effect of combining RGB, depth, and thermal
facial images for pain detection and pain intensity level
recognition. For this purpose, we extract energies released
by facial pixels using a spatiotemporal filter. Experiments
on a group of 12 elderly people applying the multimodal approach
show that the proposed method successfully detects
pain and recognizes between three intensity levels in 82%
of the analyzed frames improving more than 6% over RGB
only analysis in similar conditions.
OriginalsprogEngelsk
TitelIEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015
ForlagIEEE Computer Society Press
Publikationsdato7 jun. 2015
Sider88-95
ISBN (Trykt)978-1-4673-6759-2
DOI
StatusUdgivet - 7 jun. 2015
Begivenhed2015 IEEE Conference on Computer Vision and Pattern Recognition Workshop: Looking at People - Boston, USA
Varighed: 6 jun. 201512 jun. 2015

Konference

Konference2015 IEEE Conference on Computer Vision and Pattern Recognition Workshop
LandUSA
ByBoston
Periode06/06/201512/06/2015

Fingerprint

Pixels
Health

Citer dette

Irani, R., Nasrollahi, K., Oliu Simon, M., Corneanu, C., Guerrero, S. E., Bahnsen, C., ... Petrini, L. (2015). Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition. I IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015 (s. 88-95). IEEE Computer Society Press. https://doi.org/10.1109/CVPRW.2015.7301341
Irani, Ramin ; Nasrollahi, Kamal ; Oliu Simon, Marc ; Corneanu, Ciprian ; Guerrero, Sergio Escalera ; Bahnsen, Chris ; Lundtoft, Dennis Holm ; Moeslund, Thomas B. ; Pedersen, Tanja ; Klitgaard, Marie-Louise ; Petrini, Laura. / Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition. IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015. IEEE Computer Society Press, 2015. s. 88-95
@inproceedings{7dd52a91f9a64492a5e0429929f942b4,
title = "Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition",
abstract = "Pain is a vital sign of human health and its automatic detectioncan be of crucial importance in many different contexts,including medical scenarios. While most availablecomputer vision techniques are based on RGB, in this paper,we investigate the effect of combining RGB, depth, and thermalfacial images for pain detection and pain intensity levelrecognition. For this purpose, we extract energies releasedby facial pixels using a spatiotemporal filter. Experimentson a group of 12 elderly people applying the multimodal approachshow that the proposed method successfully detectspain and recognizes between three intensity levels in 82{\%}of the analyzed frames improving more than 6{\%} over RGBonly analysis in similar conditions.",
author = "Ramin Irani and Kamal Nasrollahi and {Oliu Simon}, Marc and Ciprian Corneanu and Guerrero, {Sergio Escalera} and Chris Bahnsen and Lundtoft, {Dennis Holm} and Moeslund, {Thomas B.} and Tanja Pedersen and Marie-Louise Klitgaard and Laura Petrini",
year = "2015",
month = "6",
day = "7",
doi = "10.1109/CVPRW.2015.7301341",
language = "English",
isbn = "978-1-4673-6759-2",
pages = "88--95",
booktitle = "IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Irani, R, Nasrollahi, K, Oliu Simon, M, Corneanu, C, Guerrero, SE, Bahnsen, C, Lundtoft, DH, Moeslund, TB, Pedersen, T, Klitgaard, M-L & Petrini, L 2015, Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition. i IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015. IEEE Computer Society Press, s. 88-95, 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshop, Boston, USA, 06/06/2015. https://doi.org/10.1109/CVPRW.2015.7301341

Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition. / Irani, Ramin; Nasrollahi, Kamal; Oliu Simon, Marc; Corneanu, Ciprian; Guerrero, Sergio Escalera; Bahnsen, Chris; Lundtoft, Dennis Holm; Moeslund, Thomas B.; Pedersen, Tanja; Klitgaard, Marie-Louise; Petrini, Laura.

IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015. IEEE Computer Society Press, 2015. s. 88-95.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition

AU - Irani, Ramin

AU - Nasrollahi, Kamal

AU - Oliu Simon, Marc

AU - Corneanu, Ciprian

AU - Guerrero, Sergio Escalera

AU - Bahnsen, Chris

AU - Lundtoft, Dennis Holm

AU - Moeslund, Thomas B.

AU - Pedersen, Tanja

AU - Klitgaard, Marie-Louise

AU - Petrini, Laura

PY - 2015/6/7

Y1 - 2015/6/7

N2 - Pain is a vital sign of human health and its automatic detectioncan be of crucial importance in many different contexts,including medical scenarios. While most availablecomputer vision techniques are based on RGB, in this paper,we investigate the effect of combining RGB, depth, and thermalfacial images for pain detection and pain intensity levelrecognition. For this purpose, we extract energies releasedby facial pixels using a spatiotemporal filter. Experimentson a group of 12 elderly people applying the multimodal approachshow that the proposed method successfully detectspain and recognizes between three intensity levels in 82%of the analyzed frames improving more than 6% over RGBonly analysis in similar conditions.

AB - Pain is a vital sign of human health and its automatic detectioncan be of crucial importance in many different contexts,including medical scenarios. While most availablecomputer vision techniques are based on RGB, in this paper,we investigate the effect of combining RGB, depth, and thermalfacial images for pain detection and pain intensity levelrecognition. For this purpose, we extract energies releasedby facial pixels using a spatiotemporal filter. Experimentson a group of 12 elderly people applying the multimodal approachshow that the proposed method successfully detectspain and recognizes between three intensity levels in 82%of the analyzed frames improving more than 6% over RGBonly analysis in similar conditions.

U2 - 10.1109/CVPRW.2015.7301341

DO - 10.1109/CVPRW.2015.7301341

M3 - Article in proceeding

SN - 978-1-4673-6759-2

SP - 88

EP - 95

BT - IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015

PB - IEEE Computer Society Press

ER -

Irani R, Nasrollahi K, Oliu Simon M, Corneanu C, Guerrero SE, Bahnsen C et al. Spatiotemporal Analysis of RGB-D-T Facial Images for Multimodal Pain Level Recognition. I IEEE Conference on Computer Vision and Pattern Recognition Workshop (CVPRW), 2015. IEEE Computer Society Press. 2015. s. 88-95 https://doi.org/10.1109/CVPRW.2015.7301341