Automatic metal parts inspection: Use of thermographic images and anomaly detection algorithms

A fully-automatic approach based on the use of induction thermography and detection algorithms is proposed to inspect industrial metallic parts containing different surface and sub-surface anomalies such as open cracks, open and closed notches with different sizes and depths. A practical experimental setup is developed, where lock-in and pulsed thermography (LT and PT, respectively) techniques are used to establish a dataset of thermal images for three different mockups. Data cubes are constructed by stacking up the temporal sequence of thermogram images. After the reduction of the data space dimension by means of denoising and dimensionality reduction methods; anomaly detection algorithms are applied on the reduced data cubes. The dimensions of the reduced data spaces are automatically calculated with arbitrary criterion. The results show that, when reduced data cubes are used, the anomaly detection algorithms originally developed for hyperspectral data, the well-known Reed and Xiaoli Yu detector (RX) and the regularized adaptive RX (RARX), give good detection performances for both surface and sub-surface defects in a non-supervised way.     

A Matlab based interface for infrared thermographic diagnosis of pediatric musculoskeletal injuries

Background and objectiveOne of the main causes of emergency medical consultations done by children are musculoskeletal injures. In such cases, radiological tests are a common practice to diagnose the gravity of the trauma and determine the likely existence of a fracture. In order to avoid, or at least to reduce, the use of ionizing radiations with children, the infrared thermographic technique was studied as an alternative solution, since it is a non-harmful, non-invasive and non-contact technique, without excessive technical complications and moderate cost when compared to other types of imaging tools.MethodologyWhen an infrared thermographic diagnostic test is performed, and once the pictures of the studied limb are taken accordingly to the established methodology, an imaging post-processing protocol becomes necessary to make a correct interpretation and diagnosis. Aimed at performing the analysis in situ and in real time, in this work we present a software tool based on a Matlab interface. The software programming is based on the results obtained in clinical tests, where several variables were took into consideration. The program is able to determine the probability of fracture basing the diagnosis on a non-linear cataloguing approach, using decision trees.ResultsThe tool implemented allows to diagnose musculoskeletal injures in children shortly after taking the infrared thermographic picture.ConclusionsThe diagnosis tool provides the means for the interpretation of the IT pictures, allows to obtain a diagnosis in a fast way, and may help to decrease the radiation doses in children.     

Infrared thermography based defect detection in ferromagnetic specimens using a low frequency alternating magnetic field

A new active infrared thermography based technique is proposed for defect detection in ferromagnetic specimens using a low frequency alternating magnetic field induced heating. The test specimens (four mild steel specimens with artificial rectangular slots of 8.0, 5.0, 3.3 and 3.0 mm depths) are magnetized using a low frequency alternating magnetic field and by using an infrared camera, the surface temperature is remotely monitored in real time. An alternating magnetic field induces an eddy current in the specimen which increases the specimen temperature due to the Joule’s heating. The experimental results show a thermal contrast in the defective region that decays exponentially with the defect depth. The observed thermal contrast is attributed to the reduction in induction heating due to the leakage of magnetic flux caused by magnetic permeability gradient in the defective region. The proposed technique is suitable for rapid non-contact wide area inspection of ferromagnetic materials and offers several advantages over the conventional active thermography techniques like fast direct heating, no frequency optimization, no dependence on the surface absorption coefficient and penetration depth.     

Wavelet subspace decomposition of thermal infrared images for defect detection in artworks

Health of ancient artworks must be routinely monitored for their adequate preservation. Faults in these artworks may develop over time and must be identified as precisely as possible. The classical acoustic testing techniques, being invasive, risk causing permanent damage during periodic inspections. Infrared thermometry offers a promising solution to map faults in artworks. It involves heating the artwork and recording its thermal response using infrared camera. A novel strategy based on pseudo-random binary excitation principle is used in this work to suppress the risks associated with prolonged heating. The objective of this work is to develop an automatic scheme for detecting faults in the captured images. An efficient scheme based on wavelet based subspace decomposition is developed which favors identification of, the otherwise invisible, weaker faults. Two major problems addressed in this work are the selection of the optimal wavelet basis and the subspace level selection. A novel criterion based on regional mutual information is proposed for the latter. The approach is successfully tested on a laboratory based sample as well as real artworks. A new contrast enhancement metric is developed to demonstrate the quantitative efficiency of the algorithm. The algorithm is successfully deployed for both laboratory based and real artworks.     

一种基于Mumford-Shah模型的红外图像边缘检测方法

 Chan-Vese模型是一种优秀的简化Mumford-Shah模型。然而Chan-Vese模型是以两个同质区域为基础建立的,这并不符合红外图像的特点,导致直接应用该模型处理红外图像时可能失败。针对这一问题,提出了一种适用于红外图像边缘检测的改进Mumford-Shah模型,并对该模型中目标边缘的保持、停止准则的建立及算法速度的提高作了详细讨论。实验表明,改进Mumford-Shah模型能够克服Chan-Vese模型在对红外图像边缘检测时不能跨越过渡区域的缺点,有效地检测出目标边缘。     

基于相对失真测度的感兴趣区域编码

提出了一种基于相对失真测度的率失真斜率提升感兴趣区域编码算法.通过计算感兴趣区域与背景之间的相对失真确定感兴趣区域的率失真斜率提升幅度,使得实际感兴趣区域与背景的相对失真尽可能逼近给定值.本算法不需要对小波域的系数进行比特平面提升,而是通过提升率失真斜率实现.解码器不需要进行小波域系数的逆提升,且提升大小不受比特平面限制, 可以精确到步骤.适合给定感兴趣区域与背景之间的相对失真,也适合交互式图像等感兴趣区域编码.相对失真改变时,不需要重新对图像进行比特平面编码,只要提升感兴趣区域斜率然后重新组织码流即可, 避免了比特平面提升的感兴趣区域编码算法缺陷.仿真结果表明,本算法能够精确根据给定感兴趣区域与背景的平均相对失真组织码流,实际结果十分接近给定值.     

The detection and prediction for oil spill on the sea based on the infrared images

Detection for oil pollution is an important part of the marine environment protection in maritime security. In order to realize all-weather, rapid and accurate oil spill area detection, infrared images of oil spill on the sea is processed on account of infrared thermal imaging’s visual capacity in darkness and frog. The detection for oil spill is realized and the location as well as the area of oil spill is calculated. The prediction integrated model of oil spill spreading is established and the prediction simulation for oil spill area is realized by changing the oil varieties, environmental factors and time, etc. The results show that this simulation is accurate, fast, intuitive and simple. It has certain significance for realizing the early warning of oil spill area detection automatically, intelligently and quickly.     

A novel infrared small moving target detection method based on tracking interest points under complicated background

Infrared moving target detection is an important part of infrared technology. We introduce a novel infrared small moving target detection method based on tracking interest points under complicated background. Firstly, Difference of Gaussians (DOG) filters are used to detect a group of interest points (including the moving targets). Secondly, a sort of small targets tracking method inspired by Human Visual System (HVS) is used to track these interest points for several frames, and then the correlations between interest points in the first frame and the last frame are obtained. Last, a new clustering method named as R-means is proposed to divide these interest points into two groups according to the correlations, one is target points and another is background points. In experimental results, the target-to-clutter ratio (TCR) and the receiver operating characteristics (ROC) curves are computed experimentally to compare the performances of the proposed method and other five sophisticated methods. From the results, the proposed method shows a better discrimination of targets and clutters and has a lower false alarm rate than the existing moving target detection methods.     

Design of mini-multi-gas monitoring system based on IR absorption

In this paper, a novel non-dispersive infrared ray (IR) gas detection system is described. Conventional devices typically include several primary components: a broadband source (usually an incandescent filament), a rotating chopper shutter, a narrow-band filter, a sample tube and a detector. But we mainly use the mini-multi-channel detector, electrical modulation means and mini-gas-cell structure. To solve the problems of gas accidents in coal mines, and for family safety that results from using gas, this new IR detection system with integration, miniaturization and non-moving parts has been developed. It is based on the principle that certain gases absorb infrared radiation at specific (and often unique) wavelengths. The infrared detection optics principle used in developing this system is mainly analyzed. The idea of multi-gas detection is introduced and guided through the analysis of the single-gas detection. Through researching the design of cell structure, a cell with integration and miniaturization has been devised. By taking a single-chip microcomputer (SCM) as intelligence handling, the functional block diagram of a gas detection system is designed with the analyzing and devising of its hardware and software system. The way of data transmission on a controller area network (CAN) bus and wireless data transmission mode is explained. This system has reached the technology requirement of lower power consumption, mini-volume, wide measure range, and is able to realize multi-gas detection.     

A study on detection of micro-cracks in the dissimilar metal weld through ultrasound infrared thermography

This study was conducted to investigate a possibility of detecting stress corrosion crack defects in a pipe welded with dissimilar metals (STS304 and SA106 Gr. b) through infrared ultrasound thermography and lock-in phase method. The ultrasound generator was set as 250 W in output and 19.8 kHz in frequency. With experiment results, this study could detect, cracks located inside the dissimilar metal weld pipe through lock-in infrared thermography and compare thermography images obtained from both the inside and the outside when the ultrasound vibration was applied to the outer part of the pipe. Besides, after cutting off the pipe in the axial direction, this study conducted PT inspection. As a result, it was found there existed more than a single crack in a certain range inside the pipe, which made hot spots appear in a wide range on the thermography image. Moreover, through ultrasound infrared thermography and lock-in phase method this study verified the possibility of detecting micro-sized shattered cracks through ultrasound thermography, which were not easy to detect with the existing techniques.     

A new measurement method of coatings thickness based on lock-in thermography

Coatings have been widely used in modern industry and it plays an important role. Coatings thickness is directly related to the performance of the functional coatings, therefore, rapid and accurate coatings thickness inspection has great significance. Existing coatings thickness measurement method is difficult to achieve fast and accurate on-site non-destructive coatings inspection due to cost, accuracy, destruction during inspection and other reasons. This paper starts from the introduction of the principle of lock-in thermography, and then performs an in-depth study on the application of lock-in thermography in coatings inspection through numerical modeling and analysis. The numerical analysis helps explore the relationship between coatings thickness and phase, and the relationship lays the foundation for accurate calculation of coatings thickness. The author sets up a lock-in thermography inspection system and uses thermal barrier coatings specimens to conduct an experiment. The specimen coatings thickness is measured and calibrated to verify the quantitative inspection. Experiment results show that the lock-in thermography method can perform fast coatings inspection and the inspection accuracy is about 95%. Therefore, the method can meet the field testing requirements for engineering projects.     

Evaluation of paint coating thickness variations based on pulsed Infrared thermography laser technique

In this paper, a pulsed Infrared thermography technique using a homogeneous heat provided by a laser source is used for the non-destructive evaluation of paint coating thickness variations. Firstly, numerical simulations of the thermal response of a paint coated sample are performed. By analyzing the thermal responses as a function of thermal properties and thickness of both coating and substrate layers, optimal excitation parameters of the heating source are determined. Two characteristic parameters were studied with respect to the paint coating layer thickness variations. Results obtained using an experimental test bench based on the pulsed Infrared thermography laser technique are compared with those given by a classical Eddy current technique for paint coating variations from 5 to 130 μm. These results demonstrate the efficiency of this approach and suggest that the pulsed Infrared thermography technique presents good perspectives to characterize the heterogeneity of paint coating on large scale samples with other heating sources.     

Fusion method of infrared and visible images based on neighborhood characteristic and regionalization in NSCT domain

On fusing infrared and visible image, the traditional fusion method cannot get the better image quality. Based on neighborhood characteristic and regionalization in NSCT (Nonsubsampled Contourlet Transform) domain, the fusion algorithm was proposed. Firstly, NSCT was adopted to decompose infrared and visible images at different scales and directions for the low and high frequency coefficients, the low frequency coefficients which were fused with improving regional weighted fusion method based on neighborhood energy, and the high-frequency coefficients were fused with multi-judgment rule based on neighborhood characteristic regional process. Finally, the coefficients were reconstructed to obtain the fused image. The experimental results show that, compared with the other three related methods, the proposed method can get the biggest value of IE (information entropy), MI(VI,F) (mutual information from visible image), MI(VI,F) (mutual information from infrared image), MI (sum of mutual information), and Q^AB/F (edge retention). The proposed method can leave enough information in the original images and its details, and the fused images have better visual effects.     

A fusion algorithm for infrared and visible images based on RDU-PCNN and ICA-bases in NSST domain

The aim of infrared and visible image fusion is to enhance the feature in infrared image and preserve abundant detail information in visible image. Based on the fact that the human sense system accepts external stimulation only when the stimulus intensity is greater than a certain value and the reaction of neuronal cells have obvious regional characters, an image fusion algorithm based on region dual-channel unit-linking pulse coupled neural networks (RDU-PCNN) and independent component analysis (ICA) bases in non-subsampled shearlet transform (NSST) domain for infrared and visible images is proposed. RDU-PCNN we constructed has obvious regional characters and much lower computational costs. We trained ICA-bases using a number of images that the content and statistical properties are similar with the fusion images but applied it as low-frequency ICA-bases, which can reduce calculation complexity. Experimental results demonstrate that the proposed method can significantly improved the fusion quality and need less computational costs.     

基于多信号温度模型的机载电子板卡故障检测研究

在利用红外热像仪进行机载电子板卡故障检测中,针对电子板卡结构复杂,解析建模困难的特点,提出了一种基于多信号温度模型的分析诊断方法。通过将机载电子板卡正常工作时的红外温度图像与故障时的进行对比,建立了系统的多信号温度模型,针对多信号温度模型的缺点,提出一种基于贝叶斯网络的测试性建模方法,并给出贝叶斯网络模型的测试性分析方法与指标计算方法,得到模型相关矩阵并进一步进行故障诊断分析,为检测电子元器件故障及老化程度提供了一种有效途径。     

Multiscale top-hat selection transform based infrared and visual image fusion with emphasis on extracting regions of interest

To effectively combine regions of interest in original infrared and visual images, an adaptively weighted infrared and visual image fusion algorithm is developed based on the multiscale top-hat selection transform. First, the multiscale top-hat selection transform using multiscale structuring elements with increasing sizes is discussed. Second, the image regions of the original infrared and visual images at each scale are extracted by using the multiscale top-hat selection transform. Third, the final fusion regions are constructed from the extracted multiscale image regions. Finally, the final fusion regions are combined into a base image calculated from the original images to form the final fusion result. The combination of the final fusion regions uses the adaptive weight strategy, and the weights are adaptively obtained based on the importance of the extracted features. In the paper, we compare seven image fusion methods: wavelet pyramid algorithm (WP), shift invariant discrete wavelet transform algorithm (SIDWT), Laplacian pyramid algorithm (LP), morphological pyramid algorithm (MP), multiscale morphology based algorithm (MSM), center-surround top-hat transform based algorithm (CSTHT), and the proposed multiscale top-hat selection transform based algorithm. These seven methods are compared over five different publicly available image sets using three metrics of spatial frequency, mean gradient, and Q. The results show that the proposed algorithm is effective and may be useful for the applications related to the infrared and visual image fusion.     

基于光谱图像的森林病虫害自动检测方法

我国天然林区分布范围广,地形复杂,依靠传统的护林员巡检方式进行林木病虫害防治,效率较低,难于及时发现早期的林木病虫害,可能因此错过防治的最佳时机。针对该问题,设计了一种基于多光谱图像检测林木病虫害的深度学习网络,研发了一套检测软件,通过无人机挂飞实验,利用搭建的深度学习网络,完成林区染病区检测,对检测结果进行了分析。     

Analysis of the features and reconstruction of a high resolution infrared image based on a multi-aperture imaging system

Infrared images of good quality are strictly important for such applications as targets detection, tracking and identifying. Traditional single aperture infrared imaging system brings in some defects for its imaging scheme. Multi-aperture imaging system shows promising characteristic of improving image quality and reducing size of optical instruments. We reconstruct a high resolution infrared image from the low resolution sub-images collected by the compact multi-aperture imaging system. A novel reconstruction method called pixels closely arrange (PCA) is proposed based on analyzing the compound eye imaging process, and this method is verified in a simulated 3D infrared scene to capture sub-images. An evaluation of the reconstructed image quality is presented to discuss the significant factors that affect the final result. Experimental results show that the PCA method can be efficiently applied to the multi-aperture infrared imaging system as long as the structure of the micro-lens array is specifically designed to be adaptive to the infrared focal plane array (IFPA).