Dense-Hog-based 3D face tracking for infant pain monitoring

Ronald W.J.J. Saeijs; Walther E. Tjon A Ten; Peter H.N. de With

doi:10.1109/ICIP.2016.7532652

Dense-Hog-based 3D face tracking for infant pain monitoring

Ronald W.J.J. Saeijs, Walther E. Tjon A Ten, Peter H.N. de With

Video Coding & Architectures

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

3 Citations (Scopus)

2 Downloads (Pure)

Abstract

This paper presents a new algorithm for 3D face tracking intended for clinical infant pain monitoring under challenging conditions. The algorithm uses a cylinder head model and head pose recovery by alignment of dynamically extracted templates based on dense-HOG features. The algorithm is motivated from the application context and compared with a variant based on intensities. The paper reports experimental results on videos of moving infants in hospital who are relaxed or in pain. Results show good short-term tracking behavior for poses up to 50 degrees from upright-frontal, with significantly higher accuracy resulting from the use of dense-HOG features.

Original language	English
Title of host publication	2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, Arizona, USA
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	1719-1723
Number of pages	5
ISBN (Print)	978-1-4673-9961-6
DOIs	https://doi.org/10.1109/ICIP.2016.7532652
Publication status	Published - 19 Aug 2016
Event	23rd IEEE International Conference on Image Processing (ICIP 2016) - Phoenix Convention Center, Phoenix, AZ, United States Duration: 25 Sept 2016 → 28 Sept 2016 Conference number: 23 http://2016.ieeeicip.org/

Conference

Conference	23rd IEEE International Conference on Image Processing (ICIP 2016)
Abbreviated title	ICIP 2016
Country/Territory	United States
City	Phoenix, AZ
Period	25/09/16 → 28/09/16
Internet address	http://2016.ieeeicip.org/

Keywords

face tracking, pain monitoring, cylinder head model, dense HOG

Access to Document

10.1109/ICIP.2016.7532652Licence: Unspecified

Cite this

@inproceedings{79ce04af5e794dd4b62eace6143cfffa,

title = "Dense-Hog-based 3D face tracking for infant pain monitoring",

abstract = "This paper presents a new algorithm for 3D face tracking intended for clinical infant pain monitoring under challenging conditions. The algorithm uses a cylinder head model and head pose recovery by alignment of dynamically extracted templates based on dense-HOG features. The algorithm is motivated from the application context and compared with a variant based on intensities. The paper reports experimental results on videos of moving infants in hospital who are relaxed or in pain. Results show good short-term tracking behavior for poses up to 50 degrees from upright-frontal, with significantly higher accuracy resulting from the use of dense-HOG features.",

keywords = "face tracking, pain monitoring, cylinder head model, dense HOG",

author = "Saeijs, {Ronald W.J.J.} and {Tjon A Ten}, {Walther E.} and {de With}, {Peter H.N.}",

year = "2016",

month = aug,

day = "19",

doi = "10.1109/ICIP.2016.7532652",

language = "English",

isbn = "978-1-4673-9961-6",

pages = "1719--1723",

booktitle = "2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, Arizona, USA",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "23rd IEEE International Conference on Image Processing (ICIP 2016), ICIP 2016 ; Conference date: 25-09-2016 Through 28-09-2016",

url = "http://2016.ieeeicip.org/",

}

Saeijs, RWJJ, Tjon A Ten, WE & de With, PHN 2016, Dense-Hog-based 3D face tracking for infant pain monitoring. in 2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, Arizona, USA. Institute of Electrical and Electronics Engineers, Piscataway, pp. 1719-1723, 23rd IEEE International Conference on Image Processing (ICIP 2016), Phoenix, AZ, Arizona, United States, 25/09/16. https://doi.org/10.1109/ICIP.2016.7532652

Dense-Hog-based 3D face tracking for infant pain monitoring. / Saeijs, Ronald W.J.J.; Tjon A Ten, Walther E.; de With, Peter H.N.
2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, Arizona, USA. Piscataway: Institute of Electrical and Electronics Engineers, 2016. p. 1719-1723.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Dense-Hog-based 3D face tracking for infant pain monitoring

AU - Saeijs, Ronald W.J.J.

AU - Tjon A Ten, Walther E.

AU - de With, Peter H.N.

N1 - Conference code: 23

PY - 2016/8/19

Y1 - 2016/8/19

N2 - This paper presents a new algorithm for 3D face tracking intended for clinical infant pain monitoring under challenging conditions. The algorithm uses a cylinder head model and head pose recovery by alignment of dynamically extracted templates based on dense-HOG features. The algorithm is motivated from the application context and compared with a variant based on intensities. The paper reports experimental results on videos of moving infants in hospital who are relaxed or in pain. Results show good short-term tracking behavior for poses up to 50 degrees from upright-frontal, with significantly higher accuracy resulting from the use of dense-HOG features.

AB - This paper presents a new algorithm for 3D face tracking intended for clinical infant pain monitoring under challenging conditions. The algorithm uses a cylinder head model and head pose recovery by alignment of dynamically extracted templates based on dense-HOG features. The algorithm is motivated from the application context and compared with a variant based on intensities. The paper reports experimental results on videos of moving infants in hospital who are relaxed or in pain. Results show good short-term tracking behavior for poses up to 50 degrees from upright-frontal, with significantly higher accuracy resulting from the use of dense-HOG features.

KW - face tracking, pain monitoring, cylinder head model, dense HOG

U2 - 10.1109/ICIP.2016.7532652

DO - 10.1109/ICIP.2016.7532652

M3 - Conference contribution

SN - 978-1-4673-9961-6

SP - 1719

EP - 1723

BT - 2016 IEEE International Conference on Image Processing (ICIP), September 25-28, 2016, Phoenix, Arizona, USA

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 23rd IEEE International Conference on Image Processing (ICIP 2016)

Y2 - 25 September 2016 through 28 September 2016

ER -

Dense-Hog-based 3D face tracking for infant pain monitoring

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this