Nostril-Anchored Geometric ROI Projection for Contactless Forehead Skin Temperature Estimation Using Low-Resolution Thermal Imaging
Sensors · 14.08.2026 · 26 (16) · 5147
DOI: 10.3390/s26165147 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 14.08.2026. Verfasst von Riska Analia und 3 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UK. Hauptthemen laut MEDLINE: Skin Temperature, Forehead, Thermography. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Indonesia Endowment Fund for Education, Indonesia Endowment Fund for Education (LPDP), Ministry of Finance of the Republic of Indonesia.
Abstract (Originalsprache)
(1)
Background
Reliable forehead region-of-interest (ROI) localization remains challenging in low-resolution thermal imaging because limited spatial detail increases localization uncertainty. This study develops a lightweight nostril-anchored geometric ROI projection method for contactless forehead skin temperature estimation. (2)
Methods
The forehead ROI was projected from the detected nostril bounding box using anthropometry-guided proportional geometry, followed by 95th-percentile (P95) spatial aggregation and exponential moving average (EMA) stabilization. Direct localization was evaluated against fixed-crop and MediaPipe Pose-based baselines using 120 annotated pilot frames across 0.5–1.5 m, followed by validation on 150 additional annotated frames from ten formal participants. A medical non-contact infrared forehead thermometer targeting the same central forehead region was used as a practical, rather than traceably calibrated, comparator. (3)
Results
The proposed method outperformed the two localization baselines in the pilot evaluation. Formal-cohort validation achieved an overall IoU of 0.714, FIR of 0.870, and NCE of 0.091, with a 0.7% spatial-failure rate. Across 90 temperature measurements, the method achieved an MAE of 0.514 °C, RMSE of 0.614 °C, and mean bias of −0.187 °C, with 95% Bland–Altman limits of agreement from −1.340 °C to 0.966 °C. Real-time implementation achieved 24.12±1.43 FPS on a Jetson Orin Nano. (4)
Conclusions
The proposed method provides a computationally efficient forehead ROI localization approach for low-resolution thermal imaging. Localization was strongest at 0.5 m and lower at farther distances; therefore, its scale adaptation should not be interpreted as distance-invariant performance. The temperature results represent agreement with the practical comparator rather than absolute clinical accuracy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Electronic and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UK.
- Department of Electrical Engineering, Politeknik Negeri Batam, Batam 29461, Indonesia.
- Academic Unit for Ageing and Stroke Research, Leeds Institute of Health Sciences, University of Leeds, Leeds LS2 9LN, UK.
ORCID-Profile: Riska Analia, Anne Forster, Sheng-Quan Xie, Zhiqiang Zhang
Förderung
- Indonesia Endowment Fund for Education
- Indonesia Endowment Fund for Education (LPDP), Ministry of Finance of the Republic of Indonesia
Zitieren
APA
Analia, R., Forster, A., Xie, S. Q., & Zhang, Z. (2026). Nostril-Anchored Geometric ROI Projection for Contactless Forehead Skin Temperature Estimation Using Low-Resolution Thermal Imaging. Sensors, 26(16), 5147. https://doi.org/10.3390/s26165147
Vancouver
Analia R, Forster A, Xie SQ, Zhang Z. Nostril-Anchored Geometric ROI Projection for Contactless Forehead Skin Temperature Estimation Using Low-Resolution Thermal Imaging. Sensors. 2026;26(16):5147. doi:10.3390/s26165147
BibTeX
@article{Analia2026,
author = {Analia, Riska and Forster, Anne and Xie, Sheng-Quan and Zhang, Zhiqiang},
title = {Nostril-Anchored Geometric ROI Projection for Contactless Forehead Skin Temperature Estimation Using Low-Resolution Thermal Imaging},
journal = {Sensors},
year = {2026},
volume = {26},
number = {16},
pages = {5147},
doi = {10.3390/s26165147}
}
EUVIMED