Main content

Home

Menu

Loading wiki pages...

View
Wiki Version:
**Dataset Description** This thermal image dataset was collected using the FLIR Lepton 3.5 thermal camera module integrated with a Raspberry Pi 4B board. The data collection was carried out in two distinct indoor environments — a classroom and a research lab — representing varying occupant densities and interaction patterns. - The classroom setting represents a dense environment, where students are seated close to one another. - The lab setting represents a sparse environment, where occupants are more spread out and typically engaged in individual or small-group activities. In both environments, the thermal camera setup was wall-mounted, with occupants maintaining a reasonable distance from the device to simulate realistic deployment scenarios. In the classroom environment, the camera’s field-of-view (FOV) typically captured 12 to 15 students. The data includes a diverse set of conditions such as: - Varying crowd densities - Different head orientations - Occlusion scenarios - Students with and without eyeglasses In the lab environment, the camera’s FOV captured a maximum of 6 occupants performing different activities, including sitting, standing, and walking. The dataset captures varying distances from the camera, diverse head poses, and the presence or absence of eyeglasses. A summary of the dataset size is provided in the table below. Please refer to the [**accompanying paper**][1] for detailed information on data collection methodology, experimental setup, and potential use cases. Raw classroom data: 2735 Resized classroom data: 2735 Resized and augmented classroom data: 4799 Raw lab data: 2844 Resized lab data: 2844 Resized and augmented lab data: 4962 Resized combined data: 5579 Resized and augmented combined data: 9761 **Citation** If you use this dataset in your research or analysis, please cite the following paper: Arijit Samal, Haroon R. Lone. Thermal Vision: Pioneering Non-Invasive Temperature Tracking in Congested Spaces. Smart Health, Elsevier (2025). [1]: https://www.sciencedirect.com/science/article/pii/S2352648325000376
OSF does not support the use of Internet Explorer. For optimal performance, please switch to another browser.
Accept
This website relies on cookies to help provide a better user experience. By clicking Accept or continuing to use the site, you agree. For more information, see our Privacy Policy and information on cookie use.
Accept
×

Start managing your projects on the OSF today.

Free and easy to use, the Open Science Framework supports the entire research lifecycle: planning, execution, reporting, archiving, and discovery.