Two-color pyrometry for backface temperature and emissivity measurement of burning materials

Pelzmann, Tanja; Dupont, Fabien; Sauté, Benjamin; Robert, Étienne

doi:10.1016/j.ijthermalsci.2022.107894

Cited by 5 publications

(1 citation statement)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Infrared thermal imagers in the domain of image temperature measurement utilize the blackbody radiation correlation formula to determine the color-temperature correspondence for each pixel [24]. However, existing color temperature measurement algorithms designed for high temperatures, such as two-color method [25], laser speckle photography [26], and image fusion techniques [27], often demand sophisticated and costly optical devices along with stable, vibration-free systems. Their intricate setup and restrictive measurement requirements pose significant challenges for direct application in high-temperature environments.…”

Section: Introductionmentioning

confidence: 99%

Super-Resolution Reconstruction and High-Precision Temperature Measurement of Thermal Images Under High- Temperature Scenes Based on Neural Network

2024

View full text Add to dashboard Cite

Accurate temperature readings are vital in fire resistance tests, but conventional thermal imagers often lack sufficient resolution, and applying super-resolution algorithms can disrupt the temperature and color correspondence, leading to limited efficiency. To address these issues, a convolutional network tailored for high-temperature scenes is designed for image super-resolution with the internal joint attention sub-residual blocks (JASRB) efficiently integrating channel, spatial attention mechanisms, and convolutional modules. Furthermore, a segmented method is developed for predicting thermal image temperature using color temperature measurements and an interpretable artificial neural network. This approach predicts temperatures in super-resolution thermal images ranging from 400 to 1200°C. Through comparative validation, it is found that the three-neuron neural network approach demonstrates superior prediction accuracy compared to other machine learning methods. The seamlessly combined proposed super-resolution architecture with the temperature measurement method has a predicted RMSE of 20°C for the whole temperature range with over 85% of samples falling within errors of 30°C.

show abstract