Temperature calibration of surface emissivities with an improved thermal image enhancement network

TL;DR

This paper presents a neural network-based method for improving temperature calibration in infrared thermography by jointly optimizing radiometric calibration and image enhancement, accounting for emissivity variations.

Contribution

It introduces a physically guided neural framework with a symmetric skip-CNN and an emissivity-aware attention module for unified temperature correction and image enhancement.

Findings

Achieves accurate temperature calibration across different industrial conditions.

Effectively suppresses emissivity artifacts and enhances structural details.

Demonstrates improved thermal image quality in industrial applications.

Abstract

Infrared thermography faces persistent challenges in temperature accuracy due to material emissivity variations, where existing methods often neglect the joint optimization of radiometric calibration and image degradation. This study introduces a physically guided neural framework that unifies temperature correction and image enhancement through a symmetric skip-CNN architecture and an emissivity-aware attention module. The pre-processing stage segments the ROIs of the image and and initially corrected the firing rate. A novel dual-constrained loss function strengthens the statistical consistency between the target and reference regions through mean-variance alignment and histogram matching based on Kullback-Leibler dispersion. The method works by dynamically fusing thermal radiation features and spatial context, and the model suppresses emissivity artifacts while recovering structural details. After validating the industrial blower system under different conditions, the improved network realizes the dynamic fusion of thermal radiation characteristics and spatial background, with accurate calibration results in various industrial conditions.