Infrared machine vision and infrared thermography with deep learning: A review

He, Yunze; Deng, Baoyuan; Wang, Hongjin; Cheng, Liang; Zhou, Ke; Cai, Siyuan; Ciampa, Francesco

doi:10.1016/j.infrared.2021.103754

Cited by 109 publications

(37 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The defect depth is evaluated by matching the relative incremental filtered RIFC curve versus time (please look at upper left part of Figure 12) to the analytical Equation (31) with some assumption on character of expected defects (here air holes) and thermal diffusivity of tested material as included in the equation-visible in the right panel named 'Defect characterization'. The detailed explanation as to how the depth estimation works confirmed by simulations for analytical 1D model of thermal behaviour can be found in paper [56].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Noninvasive Methods of Active Thermographic Investigation: Short Overview of Theoretical Foundations with an Example of Application

Gryś

Minkina

2022

Energies

View full text Add to dashboard Cite

The field of non-destructive testing using thermography (NDT—Non-Destructive Testing and NDE—Non Destructive Evaluation) was established in the 1960s as a competitive and complementary method to ultrasonic or X-ray testing. Non-destructive quality control of objects is essential in modern industry, especially in mass production. It is an integral part of the quality control process. The reason for the introduction of non-destructive testing into diagnostic techniques were disasters and failures of various equipment and structures. Over the years, a division has been drawn between passive and active thermography. The aim of this publication is to present the theoretical basis of non-destructive testing with the use of active infrared thermography methods. It describes selected models of transient heat flow (thermal wave) in objects of various shapes and physical properties. They are the basis for understanding the changes in the surface temperature of the studied objects in time, which are the response to thermal excitation of different nature. An example of their effective application in engineering practice is the author’s software, in which the recorded time response is matched to the analytical solution, and on this basis detected anomalies are parameterized, detected by the fusion of various techniques of thermal image processing and analysis methods.

show abstract

Section: Discussionmentioning

confidence: 99%

“…For this purpose, the Algebraic Reconstruction Technique (ART) and Maximum Likelihood Expectation Maximization (MLEM) algorithms known from X-ray tomography are attempted [28]. The possibilities of using neural networks and machine learning in active thermography have been presented in numerous papers, including [29][30][31][32][33].…”

Section: Introductionmentioning

confidence: 99%

Noninvasive Methods of Active Thermographic Investigation: Short Overview of Theoretical Foundations with an Example of Application

Gryś

Minkina

2022

Energies

View full text Add to dashboard Cite

show abstract

“…They also presented a thermal imaging technique incorporating electromagnetic waves to inspect and diagnose composites utilized in industrial applications. He et al [106,107] performed a study to measure defects and geometrical profiles of motors using non-destructive eddy current pulsed thermography. They described the current status of infrared thermal imaging technology applying deep learning and the progress and trend of fault diagnosis.…”

Section: Active Thermography For Enhanced Detectabilitymentioning

confidence: 99%

Latest Advances in Common Signal Processing of Pulsed Thermography for Enhanced Detectability: A Review

2021

View full text Add to dashboard Cite

Non-destructive testing (NDT) is a broad group of testing and analysis techniques used in science and industry to evaluate the properties of a material, structure, or system for characteristic defects and discontinuities without causing damage. Recently, infrared thermography is one of the most promising technologies as it can inspect a large area quickly using a non-contact and non-destructive method. Moreover, thermography testing has proved to be a valuable approach for non-destructive testing and evaluation of structural stability of materials. Pulsed thermography is one of the active thermography technologies that utilizes external energy heating. However, due to the non-uniform heating, lateral heat diffusion, environmental noise, and limited parameters of the thermal imaging system, there are some difficulties in detecting and characterizing defects. In order to improve this limitation, various signal processing techniques have been developed through many previous studies. This review presents the latest advances and exhaustive summary of representative signal processing techniques used in pulsed thermography according to physical principles and thermal excitation sources. First, the basic concept of infrared thermography non-destructive testing is introduced. Next, the principle of conventional pulsed thermography and signal processing technologies for non-destructive testing are reviewed. Then, we review advances and recent advances in each signal processing. Finally, the latest research trends are reviewed.

show abstract

“…CNNs support the control of possible overfitting and secure invariance to local translation 22 – 24 . For all those reasons, CNN appears as a suitable approach for infrared image processing 25 . Several studies reported the employment of recurrent neural networks (RNN) for image operations, including segmentation and classification 26 – 28 .…”

Section: Introductionmentioning

confidence: 99%

Tomographic reconstruction from planar thermal imaging using convolutional neural network

Ledwoń

Sage

Juszczyk

et al. 2022

Sci Rep

View full text Add to dashboard Cite

In this study, we investigate perspectives for thermal tomography based on planar infrared thermal images. Volumetric reconstruction of temperature distribution inside an object is hardly applicable in a way similar to ionizing-radiation-based modalities due to its non-penetrating character. Here, we aim at employing the autoencoder deep neural network to collect knowledge on the single-source heat transfer model. For that purpose, we prepare a series of synthetic 3D models of a cylindrical phantom with assumed thermal properties with various heat source locations, captured at different times. A set of planar thermal images taken around the model is subjected to initial backprojection reconstruction, then passed to the deep model. This paper reports the training and testing results in terms of five metrics assessing spatial similarity between volumetric models, signal-to-noise ratio, or heat source location accuracy. We also evaluate the assumptions of the synthetic model with an experiment involving thermal imaging of a real object (pork) and a single heat source. For validation, we investigate objects with multiple heat sources of a random location and temperature. Our results show the capability of a deep model to reconstruct the temperature distribution inside the object.

show abstract

Infrared machine vision and infrared thermography with deep learning: A review

Cited by 109 publications

References 78 publications

Noninvasive Methods of Active Thermographic Investigation: Short Overview of Theoretical Foundations with an Example of Application

Noninvasive Methods of Active Thermographic Investigation: Short Overview of Theoretical Foundations with an Example of Application

Latest Advances in Common Signal Processing of Pulsed Thermography for Enhanced Detectability: A Review

Tomographic reconstruction from planar thermal imaging using convolutional neural network

Contact Info

Product

Resources

About