Thermal Vision: Pioneering Non-Invasive Temperature Tracking in Congested Spaces

2024-12-01

arXiv.org

AI Summary

To address the challenge of non-invasive fever screening for individuals in high-density environments (e.g., classrooms, auditoriums), this paper proposes the first edge-deployable thermal-imaging-based body temperature monitoring method tailored for crowded scenes. Methodologically, we design a dedicated multi-scale face detection module—integrating YOLO-family architectures—and a lightweight thermal-radiation-to-skin-temperature regression model, explicitly overcoming the conventional assumption of sparse human distribution. We further construct and publicly release the first thermal-imaging dataset featuring dual-scenario annotations (dense and sparse crowds) along with full implementation code. Experiments demonstrate state-of-the-art performance: cross-dataset face detection achieves 84.2% mAP; temperature estimation attains an MSE of 0.18°C and an R² of 0.96—significantly outperforming existing approaches—while enabling real-time inference on resource-constrained edge devices.

Technology Category

Computer Vision: Biometrics, Face, Gesture & PoseMachine Learning: Learning on the Edge & Model CompressionNatural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

Security and Privacy: Large-scale security measurementsSystems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deploymentsSearch and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Non-invasive temperature monitoring of individuals plays a crucial role in identifying and isolating symptomatic individuals. Temperature monitoring becomes particularly vital in settings characterized by close human proximity, often referred to as dense settings. However, existing research on non-invasive temperature estimation using thermal cameras has predominantly focused on sparse settings. Unfortunately, the risk of disease transmission is significantly higher in dense settings like movie theaters or classrooms. Consequently, there is an urgent need to develop robust temperature estimation methods tailored explicitly for dense settings. Our study proposes a non-invasive temperature estimation system that combines a thermal camera with an edge device. Our system employs YOLO models for face detection and utilizes a regression framework for temperature estimation. We evaluated the system on a diverse dataset collected in dense and sparse settings. Our proposed face detection model achieves an impressive mAP score of over 84 in both in-dataset and cross-dataset evaluations. Furthermore, the regression framework demonstrates remarkable performance with a mean square error of 0.18$^{circ}$C and an impressive $R^2$ score of 0.96. Our experiments' results highlight the developed system's effectiveness, positioning it as a promising solution for continuous temperature monitoring in real-world applications. With this paper, we release our dataset and programming code publicly.

Problem

• Non-invasive temperature tracking in crowded areas
• Improving thermal camera accuracy for dense settings
• Developing robust temperature estimation for disease control

Innovation

• Combines thermal camera with edge device
• Uses YOLO models for face detection
• Employs regression framework for temperature estimation