Accurate through-thickness measurement of subsurface delamination depth in Carbon Fiber Reinforced Polymer (CFRP) is important for structural assessment because defect location determines affected load-bearing layers. Optical pulsed thermography (OPT) provides a two-dimensional thermal video rather than volumetric measurements, so depth must be inferred from temporal heat-diffusion responses. A challenge is spatial dataset bias: when calibration defects follow regular grids, regression models may memorize their geometry instead of learning physical relationship between thermal decay and depth. This work introduces a spatio-temporal decoupling architecture that separates spatial defect localization from temporal depth measurement. Defect regions are first localized using segmentation methods, after which thermal responses are spatially averaged and converted into sixteen physics-informed temporal, energy, statistical, and geometric features. These features expose the one-dimensional heat-conduction relationship while withholding pixel coordinates from the depth model. Four regression models are evaluated using specimen-level cross-validation: Random Forest (RF), Gradient Boosting Machine (GBM), Advanced Multi-Layer Perceptron (Adv-MLP), and XGBoost. Unregularized trees and over-parameterized Adv-MLP exhibit calibration collapse under geometric shifts, with errors exceeding 0.5 mm. In contrast, regularized XGBoost with L1/L2 penalties and column sampling maintains cross-specimen calibration, achieving a mean absolute error (MAE) of 0.056 mm and root mean square error (RMSE) of 0.085 mm. Predicted depths are merged with masks to generate Delaunay-triangulated three-dimensional defect models in three to five seconds per specimen. Results show that mathematical regularization and spatio-temporal decoupling reduce spatial memorization in thermal-video depth regression.
Figures & tables
Fig. 1: Spatio-temporal decoupling architecture for depth estimation from thermographic video. The pipeline separates spatial localization from temporal measurement to avoid geometric memorization.
Fig. 2: Predicted binary defect masks for the six CFRP specimens obtained from the best segmentation architecture. Square and circular defects are reliably detected, providing spatial support for subsequent temporal measurement.
Fig. 3: Mean thermal responses after spatial averaging. Deeper defects exhibit delayed peak times and lower amplitudes, confirming that temporal features encode depth information.
Category
Feature
Formula
Physical / measurement interpretation
Temporal
tpk
argmaxtTk(t)
Peak time; primary depth-related temporal measurement through ( 1 ).
τr
tpk−tonset
Rise duration associated with the transient response.
Tmax
maxtTk(t)
Maximum surface temperature within the response window.
T˙max
maxtΔTk(t)/Δt
Maximum thermal change rate.
drel
tpk
Linearized depth proxy derived from ( 1 ).
Energy
Aauc
∑t=1TTk(t)Δt
Integrated thermal response over the acquisition window.
TABLE I: Sixteen Physics-Informed Features Used for Depth Regression
Fig. 4: Pearson correlation matrix for the sixteen features and depth. Temporal features exhibit the strongest correlation, confirming the physics-informed design.
Fig. 5: Scatter plots of actual versus predicted depth across the three specimen-level cross-validation folds. Fold 1 (a) displays the calibration of the Gradient Boosting control, while Fold 2 (b) and Fold 3 (c) demonstrate the robust generalization of the regularized XGBoost model under distribution shifts from rigid square grids to columnless circular layouts.
Fold
Test
RF
GBM
XGBoost
Adv-MLP
MAE
RMSE
R2
MAE
RMSE
R2
MAE
RMSE
R2
MAE
RMSE
R2
1
SQ_03
0.0102
0.0171
0.996
0.0125
0.0184
0.996
0.0099
0.0169
0.996
0.1458
0.1725
0.628
CI_03
0.0647
0.1021
−0.042
0.0400
0.0861
0.259
0.1154
0.1309
−0.714
0.3385
0.3665
−12.43
Overall
0.0207
0.0475
0.995
0.0178
0.0413
0.996
0.0303
0.0596
0.992
0.1831
0.2236
0.880
2
SQ_02
0.0120
0.0158
0.997
0.0162
0.0199
0.995
0.0359
0.0461
0.973
0.5221
0.5730
−3.103
CI_02
0.5209
0.5326
−27.37
0.6834
0.7232
−51.29
0.0756
0.0967
0.066
0.1370
0.1622
−1.632
TABLE III: Depth Regression Results Across All Folds
Fig. 6: Three-dimensional structural reconstructions from XGBoost depth predictions. Green surfaces denote the true delamination boundaries, while red surfaces represent the computational predictions, demonstrating accurate spatial registration and clear resolution of closely spaced layers.
Active infrared thermography (AIRT) is currently witnessing a surge of artificial intelligence (AI) methodologies being deployed for automated subsurface defect analysis of high performance carbon fiber-reinforced polymers (CFRP). Deploying AI-based AIRT methodologies for inspecting CFRPs requires the creation of time consuming and expensive datasets of CFRP inspection sequences to train neural networks. To address this challenge, this work introduces a novel language-guided framework for cognitive defect analysis in CFRPs using AIRT and vision-language models (VLMs). Unlike conventional learning-based approaches, the proposed framework does not require developing training datasets for extensive training of defect detectors, instead it relies solely on pretrained multimodal VLM encoders coupled with a lightweight adapter to enable generative zero-shot understanding and localization of subsurface defects. By leveraging pretrained multimodal encoders, the proposed system enables generative zero-shot understanding of thermographic patterns and automatic detection of subsurface defects. Given the domain gap between thermographic data and natural images used to train VLMs, an AIRT-VLM Adapter is proposed to enhance the visibility of defects while aligning the thermographic domain with the learned representations of VLMs. The proposed framework is validated using three representative VLMs; specifically, GroundingDINO, Qwen-VL-Chat, and CogVLM. Validation is performed on 25 CFRP inspection sequences with impacts introduced at different energy levels, reflecting realistic defects encountered in industrial scenarios. Experimental results demonstrate that the AIRT-VLM adapter achieves signal-to-noise ratio (SNR) gains exceeding 10 dB compared with conventional thermographic dimensionality-reduction methods, while enabling zero-shot defect detection with intersection-over-union values reaching 70%.
Mohammed Salah, Eman Ouda, Giuseppe Dell'Avvocato +6
Full-field measurement techniques such as digital image correlation and infrared thermography are prevalent in experimental solid mechanics. Digital image correlation is used to analyze surface deformation, while infrared thermography quantifies surface temperature fields. However, sophisticated procedures are necessary to express both datasets in the same Lagrangian frame, especially when analyzing non-flat surfaces. In this study, we propose an external projection-based coupling that uses the pinhole camera model to relate two-dimensional temperature data measured by infrared thermography to three-dimensional point coordinates from stereocorrelation-based digital image correlation. Unlike existing multiview approaches, we utilize two independently calibrated industrial-grade systems and augment the experimental evaluation with the pinhole camera model. The projection matrix of the camera model is calibrated using a single image of a reference object. Through this projection, temperature fields are accurately represented at material points. Our method is particularly suited for, but not restricted to, curved surfaces and is straightforward to embed in existing experimental protocols, as the image registration is kept as is. Additionally, we use radial basis functions as a global interpolation ansatz in both space and time to compute in-plane temperature gradients and even temperature rates on curved surfaces, thereby providing an extensive and information-rich full-field dataset.
Jendrik-Alexander Tröger, Lutz Müller-Lohse, Stefan Hartmann
Institute of Applied Mechanics, Clausthal University of Technology, Adolph-Roemer-Straße 2a, 38678 Clausthal-Zellerfeld, Germany
Depth estimation from thermal images is highly valuable for robotic applications in adverse conditions, such as nighttime and rainy weather. Recent studies have sought to transfer knowledge from RGB-based foundation models to thermal modalities, yet the rich hierarchical representations these models encode remain underutilized. To address this limitation, we propose RGB-HS, a novel framework for thermal-image depth estimation that leverages hierarchical supervision from an RGB-based foundation model. Specifically, we first replace the baseline thermal encoder with a foundational model and introduce a parallel RGB branch that also employs a foundational model as an encoder of the same architecture, taking RGB images as input. The alignment is then performed across multiple levels between the tokens of the two encoders, allowing the thermal student branch to capture both structural precision and semantic abstraction from the RGB teacher branch. Furthermore, we introduce verification to refine the alignment process by weighting tokens from the RGB branch based on RGB image quality. Extensive experiments on the popular benchmark demonstrate that RGB-HS achieves competitive performance and more effectively exploits the representational capacity of RGB-based foundation models for depth estimation on thermal images.
Jie Hong, Tingtian Li, Xuesong Li +1
CI3 Lab, Department of Civil Engineering, The University of Hong Kong, Hong Kong SAR, China · Commonwealth Scientific and Industrial Research Organisation (CSIRO), Canberra, ACT, Australia