Computational Depth Measurement in Thermographic Video: Overcoming Spatial Overfitting via Spatio-Temporal Decoupling

• URL: http://arxiv.org/abs/2608.29223v1
• Date: Sat, 29 Aug 2026 12:26:27 GMT
• Title: Computational Depth Measurement in Thermographic Video: Overcoming Spatial Overfitting via Spatio-Temporal Decoupling
• Abstract summary: Optical pulsed thermography (OPTOPT) provides a two-dimensional thermal video rather than volumetric measurements.<n>This work introduces architecture that separates spatial defect localization from temporal depth measurement.<n>Four regression models are evaluated using specimen-level cross-validation.
• Score: 2.5621346794752724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Beyond Control Points: Arcsecond Relative-Motion Estimation of Vision Measurement Platforms With Incomplete or Absent Control Fields [43.43572961146893]
  We develop a control-adaptive differential framework that estimates platform motion directly from image displacements and known 3D points.<n>We derive the rotation observability condition, a leakage bound for unmodeled translation and nonrigid point motion, and the single-point axial-prior bias law.
  arXiv  Detail & Related papers  (2026-08-14T03:41:30Z)
• ReFP-AD: Rectified Flow Preconditioning for Energy-Based Anomaly Detection [5.928947106987821]
  Unified anomaly detection requires modeling highly heterogeneous normal data without access to anomalous samples.<n>We introduce ReFP-AD (Rectified Flow Preconditioning for Anomaly Detection), which maps high-dimensional embeddings into a well-conditioned latent space.<n>Under a strict unified protocol, ReFP-AD achieves 98.6%/97.9% Image/Pixel AUROC on MVTec-AD and 97.3%/99.0% on VisA, outperforming prior unified EBM baselines by up to +10.8% in Image AUROC.
  arXiv  Detail & Related papers  (2026-08-03T07:03:51Z)
• Data-Driven Forward and Inverse Modeling of V-Beam Thermal Sensors [0.764671395172401]
  This paper presents a machine learning framework for data-driven inverse design of V-beam thermal sensors.<n>The goal is to determine the optimal sensor geometry that achieves a target displacement under a given temperature.<n>The proposed pipeline utilizes a 3000-sample dataset and achieves a MAPE of 4.76% for predicting the displacement.
  arXiv  Detail & Related papers  (2026-07-04T12:50:19Z)
• Fault tolerant computation of the static structure factor and finite size effects [43.936586633107396]
  We develop a quantum post-processing strategy for the leading two-body finite-size correction.<n>After one-body shell effects are reduced by twist averaging, the dominant residual error is controlled by long-wavelength density fluctuations.<n>We also introduce adaptive global and local binary search procedures for identifying the infrared fitting window used to reconstruct the two-body finite size error correction.
  arXiv  Detail & Related papers  (2026-06-26T05:31:08Z)
• A skin-like conformal sensor for real-time shape mapping [2.128937994248034]
  Real-time 3D shape sensing is essential for robust control and interpretation of deformable systems during motion.<n>Here, we introduce a scalable, skin-like sensor that reconstructs its continuous 3D deformation in real time from distributed strain measurements.<n>A 5-by-5 array with a 12 mm pitch achieves a mean surface reconstruction error of 0.62 mm with 0.1s latency across all tested scenarios.
  arXiv  Detail & Related papers  (2026-05-02T00:19:19Z)
• Convolutional Surrogate for 3D Discrete Fracture-Matrix Tensor Upscaling [0.0]
  We develop a surrogate model that predicts the equivalent hydraulic conductivity tensor Keq from a voxelized 3D domain.<n>Three surrogates are trained on data generated by DFM simulations, each corresponding to a different fracture-to-matrix conductivity contrast.<n>The trained models achieve high accuracy, with normalized root-mean-square errors below 0.22 across most test cases.
  arXiv  Detail & Related papers  (2026-01-19T23:53:58Z)
• Probabilistic Predictions of Process-Induced Deformation in Carbon/Epoxy Composites Using a Deep Operator Network [7.616136432212582]
  Fiber reinforcement and polymer matrix respond differently to manufacturing conditions due to mismatch in coefficient of thermal expansion and matrix shrinkage during curing of thermosets.<n>This study considers a unidirectional AS4 carbon fiber/amine bi-functional epoxy prepreg and models process-induced deformation (PID) using a two-mechanism framework.
  arXiv  Detail & Related papers  (2025-12-15T03:04:45Z)
• ReconMOST: Multi-Layer Sea Temperature Reconstruction with Observations-Guided Diffusion [48.540756751934836]
  ReconMOST is a data-driven guided diffusion model framework for multi-layer sea temperature reconstruction.<n>Our method extends ML-based SST reconstruction to a global, multi-layer setting, handling over 92.5% missing data.
  arXiv  Detail & Related papers  (2025-06-12T06:27:22Z)
• Deep Learning for Melt Pool Depth Contour Prediction From Surface Thermal Images via Vision Transformers [40.80426609561942]
  Insufficient overlap between the melt pools produced during Laser Powder Bed Fusion (L-PBF) can lead to lack-of-fusion defects. We introduce a machine learning framework to correlate in-situ two-color thermal images observed via high-speed color imaging to the two-dimensional profile of the melt pool cross-section.
  arXiv  Detail & Related papers  (2024-04-26T20:55:39Z)
• Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation [71.24808323646167]
  We propose textbfDiffusionPose, a new scheme for learning keypoints heatmaps by a neural network. During training, the keypoints are diffused to random distribution by adding noises and the diffusion model learns to recover ground-truth heatmaps from noised heatmaps. Experiments show the prowess of our scheme with improvements of 1.6, 1.2, and 1.2 mAP on widely-used COCO, CrowdPose, and AI Challenge datasets.
  arXiv  Detail & Related papers  (2023-06-29T16:24:32Z)
• Information Entropy Initialized Concrete Autoencoder for Optimal Sensor Placement and Reconstruction of Geophysical Fields [58.720142291102135]
  We propose a new approach to the optimal placement of sensors for reconstructing geophysical fields from sparse measurements. We demonstrate our method on the two examples: (a) temperature and (b) salinity fields around the Barents Sea and the Svalbard group of islands. We find out that the obtained optimal sensor locations have clear physical interpretation and correspond to the boundaries between sea currents.
  arXiv  Detail & Related papers  (2022-06-28T12:43:38Z)
• Heatmap Regression via Randomized Rounding [105.75014893647538]
  We propose a simple yet effective quantization system to address the sub-pixel localization problem. The proposed system encodes the fractional part of numerical coordinates into the ground truth heatmap using a probabilistic approach during training.
  arXiv  Detail & Related papers  (2020-09-01T04:54:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.