Sensor Fusion for the Robust Detection of Facial Regions of Neonates Using Neural Networks
Author:
Gleichauf Johanna1ORCID, Hennemann Lukas1ORCID, Fahlbusch Fabian B.23ORCID, Hofmann Oliver1ORCID, Niebler Christine1ORCID, Koelpin Alexander4ORCID
Affiliation:
1. Nuremberg Institute of Technology, 90489 Nuremberg, Germany 2. Division of Neonatology and Pediatric Intensive Care, Department of Pediatrics and Adolescent Medicine, Friedrich-Alexander-Universität Erlangen-Nürnberg, 91054 Erlangen, Germany 3. University Children’s Hospital Augsburg, Neonatal and Pediatric Intensive Care Unit, 86156 Augsburg, Germany 4. Hamburg University of Technology, 21073 Hamburg, Germany
Abstract
The monitoring of vital signs and increasing patient comfort are cornerstones of modern neonatal intensive care. Commonly used monitoring methods are based on skin contact which can cause irritations and discomfort in preterm neonates. Therefore, non-contact approaches are the subject of current research aiming to resolve this dichotomy. Robust neonatal face detection is essential for the reliable detection of heart rate, respiratory rate and body temperature. While solutions for adult face detection are established, the unique neonatal proportions require a tailored approach. Additionally, sufficient open-source data of neonates on the NICU is lacking. We set out to train neural networks with the thermal-RGB-fusion data of neonates. We propose a novel indirect fusion approach including the sensor fusion of a thermal and RGB camera based on a 3D time-of-flight (ToF) camera. Unlike other approaches, this method is tailored for close distances encountered in neonatal incubators. Two neural networks were used with the fusion data and compared to RGB and thermal networks. For the class “head” we reached average precision values of 0.9958 (RetinaNet) and 0.9455 (YOLOv3) for the fusion data. Compared with the literature, similar precision was achieved, but we are the first to train a neural network with fusion data of neonates. The advantage of this approach is in calculating the detection area directly from the fusion image for the RGB and thermal modality. This increases data efficiency by 66%. Our results will facilitate the future development of non-contact monitoring to further improve the standard of care for preterm neonates.
Funder
Federal Ministry of Education and Research
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference81 articles.
1. Larsen, R. (2016). Anästhesie und Intensivmedizin für die Fachpflege, Springer. 2. Hausmann, J., Salekin, M.S., Zamzmi, G., Goldgof, D., and Sun, Y. (2022). Robust Neonatal Face Detection in Real-world Clinical Settings. arXiv. 3. St-Laurent, L., Prévost, D., and Maldague, X. (2010, January 24–29). Fast and accurate calibration-based thermal/colour sensors registration. Proceedings of the 2010 International Conference on Quantitative InfraRed Thermography, Quebec, QC, Canada. 4. Shivakumar, S.S., Rodrigues, N., Zhou, A., Miller, I.D., Kumar, V., and Taylor, C.J. (August, January 31). PST900: RGB-Thermal Calibration, Dataset and Segmentation Network. Proceedings of the IEEE International Conference on Robotics and Automation, Paris, France. 5. Yang, M.D., Su, T.C., and Lin, H.Y. (2018). Fusion of infrared thermal image and visible image for 3D thermal model reconstruction using smartphone sensors. Sensors, 18.
|
|