Temperature calibration of surface emissivities with an improved thermal image enhancement network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916802701819904 |
|---|---|
| author | Chu, Ning Zheng, Siya Zhang, Shanqing Li, Li Cai, Caifang Mohammad-Djafari, Ali Zhao, Feng Song, Yuanbo |
| author_facet | Chu, Ning Zheng, Siya Zhang, Shanqing Li, Li Cai, Caifang Mohammad-Djafari, Ali Zhao, Feng Song, Yuanbo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_16803 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Temperature calibration of surface emissivities with an improved thermal image enhancement network Chu, Ning Zheng, Siya Zhang, Shanqing Li, Li Cai, Caifang Mohammad-Djafari, Ali Zhao, Feng Song, Yuanbo Image and Video Processing Computer Vision and Pattern Recognition 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. |
| title | Temperature calibration of surface emissivities with an improved thermal image enhancement network |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.16803 |