Dual-camera facial landmark tracking for clinical infant monitoring

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

doi:10.1109/SITIS.2018.00032

Dual-camera facial landmark tracking for clinical infant monitoring

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

Video Coding & Architectures

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

Abstract

This paper presents a new algorithm for dual-camera facial landmark tracking, intended for clinical infant monitoring. For landmark tracking of in-the-wild faces, state-of-the-art solutions use deep networks for face detection and landmark localization. For clinical infant monitoring, however, there is currently not enough data to reliably train such networks. The proposed algorithm overcomes this by incorporating 3D head tracking, to supplement face detection and to enable a refinement version of landmark localization that is more easily learned from less data. The paper reports experimental results on real-life video of infants in bed in hospital (in visual light or near-infrared light), showing good landmark tracking behavior. For challenging sequences without severe occlusions, the mean tracking error, in terms of the RMS error measured for a subset of landmarks and divided by the maximum eye-philtrum distance, remains below 20%. The proposed algorithm is used successfully in an infant monitoring system under development.

Original language	English
Title of host publication	Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018
Editors	Richard Chbeir, Gabriella Sanniti di Baja, Luigi Gallo, Kokou Yetongnon, Albert Dipanda, Modesto Castrillon-Santana
Place of Publication	Piscataway
Publisher	Institute of Electrical and Electronics Engineers
Pages	151-158
Number of pages	8
ISBN (Electronic)	978-1-5386-9385-8
DOIs	https://doi.org/10.1109/SITIS.2018.00032
Publication status	Published - 2 Jul 2018
Event	14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 - Las Palmas de Gran Canaria, Spain Duration: 26 Nov 2018 → 29 Nov 2018

Conference

Conference	14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018
Country/Territory	Spain
City	Las Palmas de Gran Canaria
Period	26/11/18 → 29/11/18

Keywords

Dense HOG
Dual camera
Face alignment
Facial landmark tracking
Infant monitoring
dense HOG
infant monitoring
facial landmark tracking
dual camera
face alignment

Access to Document

10.1109/SITIS.2018.00032

Cite this

Saeijs, R. W. J. J., Tjona Ten, W. E., & de With, P. H. N. (2018). Dual-camera facial landmark tracking for clinical infant monitoring. In R. Chbeir, G. S. di Baja, L. Gallo, K. Yetongnon, A. Dipanda, & M. Castrillon-Santana (Eds.), Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 (pp. 151-158). [8706162] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/SITIS.2018.00032

Saeijs, Ronald W.J.J. ; Tjona Ten, Walther E. ; de With, Peter H.N. / Dual-camera facial landmark tracking for clinical infant monitoring. Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018. editor / Richard Chbeir ; Gabriella Sanniti di Baja ; Luigi Gallo ; Kokou Yetongnon ; Albert Dipanda ; Modesto Castrillon-Santana. Piscataway : Institute of Electrical and Electronics Engineers, 2018. pp. 151-158

@inproceedings{6a2e96cc131d4232bea23b63f83a76d3,

title = "Dual-camera facial landmark tracking for clinical infant monitoring",

abstract = "This paper presents a new algorithm for dual-camera facial landmark tracking, intended for clinical infant monitoring. For landmark tracking of in-the-wild faces, state-of-the-art solutions use deep networks for face detection and landmark localization. For clinical infant monitoring, however, there is currently not enough data to reliably train such networks. The proposed algorithm overcomes this by incorporating 3D head tracking, to supplement face detection and to enable a refinement version of landmark localization that is more easily learned from less data. The paper reports experimental results on real-life video of infants in bed in hospital (in visual light or near-infrared light), showing good landmark tracking behavior. For challenging sequences without severe occlusions, the mean tracking error, in terms of the RMS error measured for a subset of landmarks and divided by the maximum eye-philtrum distance, remains below 20%. The proposed algorithm is used successfully in an infant monitoring system under development.",

keywords = "Dense HOG, Dual camera, Face alignment, Facial landmark tracking, Infant monitoring, dense HOG, infant monitoring, facial landmark tracking, dual camera, face alignment",

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

year = "2018",

month = jul,

day = "2",

doi = "10.1109/SITIS.2018.00032",

language = "English",

pages = "151--158",

editor = "Richard Chbeir and {di Baja}, {Gabriella Sanniti} and Luigi Gallo and Kokou Yetongnon and Albert Dipanda and Modesto Castrillon-Santana",

booktitle = "Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018 ; Conference date: 26-11-2018 Through 29-11-2018",

}

Saeijs, RWJJ, Tjona Ten, WE & de With, PHN 2018, Dual-camera facial landmark tracking for clinical infant monitoring. in R Chbeir, GS di Baja, L Gallo, K Yetongnon, A Dipanda & M Castrillon-Santana (eds), Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018., 8706162, Institute of Electrical and Electronics Engineers, Piscataway, pp. 151-158, 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018, Las Palmas de Gran Canaria, Spain, 26/11/18. https://doi.org/10.1109/SITIS.2018.00032

Dual-camera facial landmark tracking for clinical infant monitoring. / Saeijs, Ronald W.J.J.; Tjona Ten, Walther E.; de With, Peter H.N.

Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018. ed. / Richard Chbeir; Gabriella Sanniti di Baja; Luigi Gallo; Kokou Yetongnon; Albert Dipanda; Modesto Castrillon-Santana. Piscataway : Institute of Electrical and Electronics Engineers, 2018. p. 151-158 8706162.

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

TY - GEN

T1 - Dual-camera facial landmark tracking for clinical infant monitoring

AU - Saeijs, Ronald W.J.J.

AU - Tjona Ten, Walther E.

AU - de With, Peter H.N.

PY - 2018/7/2

Y1 - 2018/7/2

N2 - This paper presents a new algorithm for dual-camera facial landmark tracking, intended for clinical infant monitoring. For landmark tracking of in-the-wild faces, state-of-the-art solutions use deep networks for face detection and landmark localization. For clinical infant monitoring, however, there is currently not enough data to reliably train such networks. The proposed algorithm overcomes this by incorporating 3D head tracking, to supplement face detection and to enable a refinement version of landmark localization that is more easily learned from less data. The paper reports experimental results on real-life video of infants in bed in hospital (in visual light or near-infrared light), showing good landmark tracking behavior. For challenging sequences without severe occlusions, the mean tracking error, in terms of the RMS error measured for a subset of landmarks and divided by the maximum eye-philtrum distance, remains below 20%. The proposed algorithm is used successfully in an infant monitoring system under development.

AB - This paper presents a new algorithm for dual-camera facial landmark tracking, intended for clinical infant monitoring. For landmark tracking of in-the-wild faces, state-of-the-art solutions use deep networks for face detection and landmark localization. For clinical infant monitoring, however, there is currently not enough data to reliably train such networks. The proposed algorithm overcomes this by incorporating 3D head tracking, to supplement face detection and to enable a refinement version of landmark localization that is more easily learned from less data. The paper reports experimental results on real-life video of infants in bed in hospital (in visual light or near-infrared light), showing good landmark tracking behavior. For challenging sequences without severe occlusions, the mean tracking error, in terms of the RMS error measured for a subset of landmarks and divided by the maximum eye-philtrum distance, remains below 20%. The proposed algorithm is used successfully in an infant monitoring system under development.

KW - Dense HOG

KW - Dual camera

KW - Face alignment

KW - Facial landmark tracking

KW - Infant monitoring

KW - dense HOG

KW - infant monitoring

KW - facial landmark tracking

KW - dual camera

KW - face alignment

UR - http://www.scopus.com/inward/record.url?scp=85065903611&partnerID=8YFLogxK

U2 - 10.1109/SITIS.2018.00032

DO - 10.1109/SITIS.2018.00032

M3 - Conference contribution

AN - SCOPUS:85065903611

SP - 151

EP - 158

BT - Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018

A2 - Chbeir, Richard

A2 - di Baja, Gabriella Sanniti

A2 - Gallo, Luigi

A2 - Yetongnon, Kokou

A2 - Dipanda, Albert

A2 - Castrillon-Santana, Modesto

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

T2 - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018

Y2 - 26 November 2018 through 29 November 2018

ER -

Saeijs RWJJ, Tjona Ten WE, de With PHN. Dual-camera facial landmark tracking for clinical infant monitoring. In Chbeir R, di Baja GS, Gallo L, Yetongnon K, Dipanda A, Castrillon-Santana M, editors, Proceedings - 14th International Conference on Signal Image Technology and Internet Based Systems, SITIS 2018. Piscataway: Institute of Electrical and Electronics Engineers. 2018. p. 151-158. 8706162 https://doi.org/10.1109/SITIS.2018.00032

Dual-camera facial landmark tracking for clinical infant monitoring

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this