Infant monitoring system for real-time and remote discomfort detection

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

Samenvatting

Discomfort detection for young infants is essential, since they lack the ability to verbalize their pain and discomfort. In this paper, we propose a novel infant monitoring system, enabling continuous monitoring for infant discomfort detection. The proposed algorithm is robust to arbitrary head rotations, occlusions and face profiles. For this purpose, a Faster RCNN architecture is first pre-trained with the ImageNet dataset, and then fine-tuned with a training dataset of different infant expressions. Our proposed method obtains a mean average precision of 74.4% and 87.4% for classifying infant expressions. The presented system enables reflux disease analysis and remote home monitoring in a more relaxed environment, which is largely preferred by pediatricians and parents.

Originele taal-2Engels
Titel2020 IEEE International Conference on Consumer Electronics, ICCE 2020
UitgeverijInstitute of Electrical and Electronics Engineers
Hoofdstuk2
ISBN van elektronische versie9781728151861
DOI's
StatusGepubliceerd - jan 2020
Evenement2020 IEEE International Conference on Consumer Electronics, ICCE 2020 - Las Vegas, Verenigde Staten van Amerika
Duur: 4 jan 20206 jan 2020

Congres

Congres2020 IEEE International Conference on Consumer Electronics, ICCE 2020
LandVerenigde Staten van Amerika
StadLas Vegas
Periode4/01/206/01/20

Vingerafdruk Duik in de onderzoeksthema's van 'Infant monitoring system for real-time and remote discomfort detection'. Samen vormen ze een unieke vingerafdruk.

  • Citeer dit

    Li, C., Pourtaherian, A., Tjon Ten, W. E. A., & De With, P. H. N. (2020). Infant monitoring system for real-time and remote discomfort detection. In 2020 IEEE International Conference on Consumer Electronics, ICCE 2020 [9043065] Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICCE46568.2020.9043065