Gergö Galiger, Nazila Azadi, Bernhard Lehner, Mario Huemer, Peter Kovacs,
"Model-based neural networks for thermographic image reconstruction"
: Proceedings of the IEEE 3rd Conference on Information Technology and Data Science (CITDS 2024), IEEE, Seite(n) 51-56, 8-2024, ISBN: 979-8-3503-8788-9
Original Titel:
Model-based neural networks for thermographic image reconstruction
Sprache des Titels:
Englisch
Original Buchtitel:
Proceedings of the IEEE 3rd Conference on Information Technology and Data Science (CITDS 2024)
Original Kurzfassung:
Thermographic imaging is a specific non-destructive evaluation (NDE) approach in which the investigated object is exposed to an initial thermal excitation. The utilization of infrared cameras to detect the induced surface temperature change
enables the deduction of the internal structure of the inspected material. This requires addressing a large-scale ill-posed linear inverse problem, involving regularization and forward modeling of the observed thermal diffusion process.
In this paper, we introduce a hybrid approach for thermographic imaging, which combines a deep unfolded Fast Iterative Shrinkage-Thresholding Algorithm (FISTA) algorithm with a U-Net. Consequently, the resulting network architecture
incorporates established numerical regularization heuristics, such as sparsity and smoothness. Additionally, to mitigate the data demand of DL approaches, we establish a simulated training database containing both point-like defects and line-like cracks. As a case study, we begin by considering applications in nondestructive material testing, starting with 2D problems and progressing towards thermal tomography in 3D.
Forschungs-