Infant Monitoring System for Real-Time and Remote Discomfort Detection

• Published in: 2020 IEEE International Conference on Consumer Electronics (ICCE) pp. 1 - 2
• Main Authors: Li, C., Pourtaherian, A., Tjon a Ten, W. E., de With, P. H. N.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01-01-2020
• Subjects: Faces; Fast R-CNN; Infant monitoring; Monitoring; Pain; Pediatrics; real-time application; Real-time systems; Training; Video sequences
• ISSN: 2158-4001
• DOI: 10.1109/ICCE46568.2020.9043065

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.