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

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

Kuvaus

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.
Alkuperäiskielienglanti
Otsikko2019 IEEE International Conference on Pervasive Computing and Communications (PerCom)
Sivumäärä9
KustantajaIEEE
Julkaisupäivä2019
ISBN (elektroninen)978-1-5386-9148-9
DOI - pysyväislinkit
TilaJulkaistu - 2019
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisuussa
TapahtumaIEEE International Conference on Pervasive Computing and Communications - Kyoto, Japani
Kesto: 12 maaliskuuta 201914 maaliskuuta 2019

Tieteenalat

  • 113 Tietojenkäsittely- ja informaatiotieteet

Lainaa tätä

Malmivirta, T., Hamberg, J., Lagerspetz, E., Li, X., Peltonen, E., Flores, H., & Nurmi, P. (2019). Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. teoksessa 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom) IEEE. https://doi.org/10.1109/PERCOM.2019.8767423
Malmivirta, Titti ; Hamberg, Jonatan ; Lagerspetz, Eemil ; Li, Xin ; Peltonen, Ella ; Flores, Huber ; Nurmi, Petteri. / Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom). 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.",
keywords = "113 Computer and information sciences",
author = "Titti Malmivirta and Jonatan Hamberg and Eemil Lagerspetz and Xin Li and Ella Peltonen and Huber Flores and Petteri Nurmi",
year = "2019",
doi = "10.1109/PERCOM.2019.8767423",
language = "English",
booktitle = "2019 IEEE International Conference on Pervasive Computing and Communications (PerCom)",
publisher = "IEEE",
address = "United States",

}

Malmivirta, T, Hamberg, J, Lagerspetz, E, Li, X, Peltonen, E, Flores, H & Nurmi, P 2019, Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. julkaisussa 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, IEEE International Conference on Pervasive Computing and Communications, Kyoto, Japani, 12/03/2019. https://doi.org/10.1109/PERCOM.2019.8767423

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

2019 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE, 2019.

Tutkimustuotos: Artikkeli kirjassa/raportissa/konferenssijulkaisussaKonferenssiartikkeliTieteellinenvertaisarvioitu

TY - GEN

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

AU - Malmivirta, Titti

AU - Hamberg, Jonatan

AU - Lagerspetz, Eemil

AU - Li, Xin

AU - Peltonen, Ella

AU - Flores, Huber

AU - Nurmi, Petteri

PY - 2019

Y1 - 2019

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.

KW - 113 Computer and information sciences

U2 - 10.1109/PERCOM.2019.8767423

DO - 10.1109/PERCOM.2019.8767423

M3 - Conference contribution

BT - 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom)

PB - IEEE

ER -

Malmivirta T, Hamberg J, Lagerspetz E, Li X, Peltonen E, Flores H et al. Hot or Not? Robust and Accurate Continuous Thermal Imaging on FLIR cameras. julkaisussa 2019 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE. 2019 https://doi.org/10.1109/PERCOM.2019.8767423