Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

Wearable thermal imaging is emerging as a powerful and increasingly affordable sensing technology. Current thermal imaging solutions are mostly based on uncooled forward looking infrared (FLIR), which is susceptible to errors resulting from warming of the camera and the device casing it. To mitigate these errors, a blackbody calibration technique where a shutter whose thermal parameters are known is periodically used to calibrate the measurements. This technique, however, is only accurate when the shutter's temperature remains constant over time, which rarely is the case. In this paper, we contribute by developing a novel deep learning based calibration technique that uses battery temperature measurements to learn a model that allows adapting to changes in the internal thermal calibration parameters. Our method is particularly effective in continuous sensing where the device casing the camera is prone to heating. We demonstrate the effectiveness of our technique through controlled benchmark experiments which show significant improvements in thermal monitoring accuracy and robustness.
Original languageEnglish
Title of host publicationProceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019)
Number of pages9
PublisherIEEE
Publication date12 Jan 2019
Publication statusPublished - 12 Jan 2019
MoE publication typeA4 Article in conference proceedings

Cite this

Malmivirta, T. M. K., Hamberg, J. C., Lagerspetz, E., Li, X., Peltonen, E., Flores Macario, H. R., & Nurmi, P. T. (2019). Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. In Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019) IEEE.
Malmivirta, Titti Maria Kristiina ; Hamberg, Jonatan Christian ; Lagerspetz, Eemil ; Li, Xin ; Peltonen, Ella ; Flores Macario, Huber Raul ; Nurmi, Petteri Tapio. / Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019). IEEE, 2019.
@inproceedings{3dafc13a767a4975a93ed77718745203,
title = "Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras",
abstract = "Wearable thermal imaging is emerging as a powerful and increasingly affordable sensing technology. Current thermal imaging solutions are mostly based on uncooled forward looking infrared (FLIR), which is susceptible to errors resulting from warming of the camera and the device casing it. To mitigate these errors, a blackbody calibration technique where a shutter whose thermal parameters are known is periodically used to calibrate the measurements. This technique, however, is only accurate when the shutter's temperature remains constant over time, which rarely is the case. In this paper, we contribute by developing a novel deep learning based calibration technique that uses battery temperature measurements to learn a model that allows adapting to changes in the internal thermal calibration parameters. Our method is particularly effective in continuous sensing where the device casing the camera is prone to heating. We demonstrate the effectiveness of our technique through controlled benchmark experiments which show significant improvements in thermal monitoring accuracy and robustness.",
author = "Malmivirta, {Titti Maria Kristiina} and Hamberg, {Jonatan Christian} and Eemil Lagerspetz and Xin Li and Ella Peltonen and {Flores Macario}, {Huber Raul} and Nurmi, {Petteri Tapio}",
year = "2019",
month = "1",
day = "12",
language = "English",
booktitle = "Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019)",
publisher = "IEEE",
address = "United States",

}

Malmivirta, TMK, Hamberg, JC, Lagerspetz, E, Li, X, Peltonen, E, Flores Macario, HR & Nurmi, PT 2019, Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. in Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019). IEEE.

Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. / Malmivirta, Titti Maria Kristiina; Hamberg, Jonatan Christian; Lagerspetz, Eemil; Li, Xin; Peltonen, Ella; Flores Macario, Huber Raul; Nurmi, Petteri Tapio.

Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019). IEEE, 2019.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

TY - GEN

T1 - Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras

AU - Malmivirta, Titti Maria Kristiina

AU - Hamberg, Jonatan Christian

AU - Lagerspetz, Eemil

AU - Li, Xin

AU - Peltonen, Ella

AU - Flores Macario, Huber Raul

AU - Nurmi, Petteri Tapio

PY - 2019/1/12

Y1 - 2019/1/12

N2 - Wearable thermal imaging is emerging as a powerful and increasingly affordable sensing technology. Current thermal imaging solutions are mostly based on uncooled forward looking infrared (FLIR), which is susceptible to errors resulting from warming of the camera and the device casing it. To mitigate these errors, a blackbody calibration technique where a shutter whose thermal parameters are known is periodically used to calibrate the measurements. This technique, however, is only accurate when the shutter's temperature remains constant over time, which rarely is the case. In this paper, we contribute by developing a novel deep learning based calibration technique that uses battery temperature measurements to learn a model that allows adapting to changes in the internal thermal calibration parameters. Our method is particularly effective in continuous sensing where the device casing the camera is prone to heating. We demonstrate the effectiveness of our technique through controlled benchmark experiments which show significant improvements in thermal monitoring accuracy and robustness.

AB - Wearable thermal imaging is emerging as a powerful and increasingly affordable sensing technology. Current thermal imaging solutions are mostly based on uncooled forward looking infrared (FLIR), which is susceptible to errors resulting from warming of the camera and the device casing it. To mitigate these errors, a blackbody calibration technique where a shutter whose thermal parameters are known is periodically used to calibrate the measurements. This technique, however, is only accurate when the shutter's temperature remains constant over time, which rarely is the case. In this paper, we contribute by developing a novel deep learning based calibration technique that uses battery temperature measurements to learn a model that allows adapting to changes in the internal thermal calibration parameters. Our method is particularly effective in continuous sensing where the device casing the camera is prone to heating. We demonstrate the effectiveness of our technique through controlled benchmark experiments which show significant improvements in thermal monitoring accuracy and robustness.

M3 - Conference contribution

BT - Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019)

PB - IEEE

ER -

Malmivirta TMK, Hamberg JC, Lagerspetz E, Li X, Peltonen E, Flores Macario HR et al. Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. In Proceedings of the 17th IEEE International Conference on Pervasive Computing and Communications (PerCom 2019). IEEE. 2019