Meibomian glands segmentation in infrared images with limited annotation

●AIM:To investigate a pioneering framework for the segmentation of meibomian glands(MGs),using limited annotations to reduce the workload on ophthalmologists and enhance the efficiency of clinical diagnosis.●METHODS:Totally 203 infrared meibomian images from 138 patients with dry eye disease,accompanied by corresponding annotations,were gathered for the study.A rectified scribble-supervised gland segmentation(RSSGS)model,incorporating temporal ensemble prediction,uncertainty estimation,and a transformation equivariance constraint,was introduced to address constraints imposed by limited supervision information inherent in scribble annotations.The viability and efficacy of the proposed model were assessed based on accuracy,intersection over union(IoU),and dice coefficient.●RESULTS:Using manual labels as the gold standard,RSSGS demonstrated outcomes with an accuracy of 93.54%,a dice coefficient of 78.02%,and an IoU of 64.18%.Notably,these performance metrics exceed the current weakly supervised state-of-the-art methods by 0.76%,2.06%,and 2.69%,respectively.Furthermore,despite achieving a substantial 80%reduction in annotation costs,it only lags behind fully annotated methods by 0.72%,1.51%,and 2.04%.●CONCLUSION:An innovative automatic segmentation model is developed for MGs in infrared eyelid images,using scribble annotation for training.This model maintains an exceptionally high level of segmentation accuracy while substantially reducing training costs.It holds substantial utility for calculating clinical parameters,thereby greatly enhancing the diagnostic efficiency of ophthalmologists in evaluating meibomian gland dysfunction.

Research on Infrared Image Fusion Technology Based on Road Crack Detection

This study aimed to propose road crack detection method based on infrared image fusion technology.By analyzing the characteristics of road crack images,this method uses a variety of infrared image fusion methods to process different types of images.The use of this method allows the detection of road cracks,which not only reduces the professional requirements for inspectors,but also improves the accuracy of road crack detection.Based on infrared image processing technology,on the basis of in-depth analysis of infrared image features,a road crack detection method is proposed,which can accurately identify the road crack location,direction,length,and other characteristic information.Experiments showed that this method has a good effect,and can meet the requirement of road crack detection.

Model-based deep learning for fiber bundle infrared image restoration

As the representative of flexibility in optical imaging media,in recent years,fiber bundles have emerged as a promising architecture in the development of compact visual systems.Dedicated to tackling the problems of universal honeycomb artifacts and low signal-to-noise ratio(SNR)imaging in fiber bundles,the iterative super-resolution reconstruction network based on a physical model is proposed.Under the constraint of solving the two subproblems of data fidelity and prior regularization term alternately,the network can efficiently“regenerate”the lost spatial resolution with deep learning.By building and calibrating a dual-path imaging system,the real-world dataset where paired low-resolution(LR)-high-resolution(HR)images on the same scene can be generated simultaneously.Numerical results on both the United States Air Force(USAF)resolution target and complex target objects demonstrate that the algorithm can restore high-contrast images without pixilated noise.On the basis of super-resolution reconstruction,compound eye image composition based on fiber bundle is also embedded in this paper for the actual imaging requirements.The proposed work is the first to apply a physical model-based deep learning network to fiber bundle imaging in the infrared band,effectively promoting the engineering application of thermal radiation detection.

Automated Registration for Infrared Image Based on Wavelet Analysis

To develop a quick, accurate and antinoise automated image registration technique for infrared images, the wavelet analysis technique was used to extract the feature points in two images followed by the compensation for input image with angle difference between them. A hi erarchical feature matching algorithm was adopted to get the final transform parameters between the two images. The simulation results for two infrared images show that the method can effectively, quickly and accurately register images and be antinoise to some extent.

Infrared image segmentation method based on 2D histogram shape modification and optimal objective function

In the methods of image thresholding segmentation, such methods based on two-dimensional （2D） histogram and optimal objective functions are important. However, when they are used for infrared image segmentation, they are weak in suppressing background noises and worse in segmenting targets with non-uniform gray level. The concept of 2D histogram shape modification is proposed, which is realized by target information prior restraint after enhancing target information using plateau histogram equalization. The formula of 2D minimum Renyi entropy is deduced for image segmentation, then the shape-modified 2D histogram is combined wfth four optimal objective functions （i.e., maximum between-class variance, maximum entropy, maximum correlation and minimum Renyi entropy） respectively for the appli- cation of infrared image segmentation. Simultaneously, F-measure is introduced to evaluate the segmentation effects objectively. The experimental results show that F-measure is an effective evaluation index for image segmentation since its value is fully consistent with the subjective evaluation, and after 2D histogram shape modification, the methods of optimal objective functions can overcome their original forms＇ deficiency and their segmentation effects are more or less improvements, where the best one is the maximum entropy method based on 2D histogram shape modification.

Fault diagnosis of electric transformers based on infrared image processing and semi-supervised learning

It is crucial to maintain the safe and stable operation of distribution transformers,which constitute a key part of power systems.In the event of transformer failure,the fault type must be diagnosed in a timely and accurate manner.To this end,a transformer fault diagnosis method based on infrared image processing and semi-supervised learning is proposed herein.First,we perform feature extraction on the collected infrared-image data to extract temperature,texture,and shape features as the model reference vectors.Then,a generative adversarial network(GAN)is constructed to generate synthetic samples for the minority subset of labelled samples.The proposed method can learn information from unlabeled sample data,unlike conventional supervised learning methods.Subsequently,a semi-supervised graph model is trained on the entire dataset,i.e.,both labeled and unlabeled data.Finally,we test the proposed model on an actual dataset collected from a Chinese electricity provider.The experimental results show that the use of feature extraction,sample generation,and semi-supervised learning model can improve the accuracy of transformer fault classification.This verifies the effectiveness of the proposed method.

Utilization of Thermal Infrared Image for Inversion of Winter Wheat Yield and Biomass

The present paper utilizes thermal infrared image for inversion of winter wheat yield and biomass with different technology of irrigation(drip irrigation,sprinkler irrigation,flood irrigation).It is the first time that thermal infrared image is used for predicting the winter wheat yield and biomass.The temperature of crop and background was measured by thermal infrared image.It is necessary to get the crop background separation index(CBSIL,CBSIH),which can be used for distinguishing the crop value from the image.CBSIL and CBSIH(the temperature when the leaves are wet adequately;the temperature when the stomata of leaf is closed completely) are the threshold values.The temperature of crop ranged from CBSIL to CBSIH.Then the ICWSI was calculated based on relevant theoretical method.The value of stomata leaf has strong negative correlation with ICWSI proving the reliable value of ICWSI.In order to construct the high accuracy simulation model,the samples were divided into two parts.One was used for constructing the simulation model,the other for checking the accuracy of the model.Such result of the model was concluded as:(1) As for the simulation model of soil moisture,the correlation coefficient(R2) is larger than 0.887 6,the average of relative error(Er) ranges from 13.33% to 16.88%;(2) As for the simulation model of winter wheat yield,drip irrigation(0.887 6,16.89%,-0.12),sprinkler irrigation(0.970 0,14.85%,-0.12),flood irrigation(0.969 0,18.87%,0.18),with the values of R2,Er and CRM listed in the parentheses followed by the individual term.(3) As for winter wheat biomass,drip irrigation(0.980 0,13.70%,0.13),sprinkler irrigation(0.95,13.15%,-0.14),flood irrigation(0.970 0,14.48%,-0.13),and the values in the parentheses are demonstrated the same as above.Both the CRM and Er are shown to be very low values,which points to the accuracy and reliability of the model investigated.The accuracy of model is high and reliable.The results indicated that thermal infrared image can be used potentially for inversion of winter wheat yield and biomass.

Infrared Image Real-time Enhancement Based on DSP

Since image real-time processing requires vast amount of computation and high-speed hardware,it is difficult to be implemented with general microcomputer system. In order to solve the problem,a powerful digital signal processing (DSP) hardware system is proposed,which is able to meet needs of image real-time processing.There are many approaches to enhance infrared image.But only histogram equalization is discussed because it is the most common and effective way.On the basis of histogram equalization principle,the specific procedures implemented in DSP are shown.At last the experimental results are given.

Experimental study of weld position detection based on keyhole infrared image during high power fiber laser welding

Keyhole is one of the important phenomena in high-power laser welding process. By studying the keyhole characteristic and detecting the seam offset during high-power fiber laser welding, an infrared sensitive high-speed camera arranged off-axis orientation of laser beam was applied to capture the dynamic thermal images of a molten pool. The 304 austenitic stainless steel plate butt joint welding experiment with laser power 10 kW was carried out. Through analyzing the keyhole infrared image, the weld position was calculated. Least squares method was used to determine the actual weld position. Image filtering technique was used to process the keyhole image, and the keyhole centroid coordinate were calculated. Also, least squares method was used to fit the keyhole centroid curve equation and establish a nonlinear continuous model which described the deviation between keyhole centroid and weld seam. The heat accumulation effect affected by the infrared radiation was analyzed to determine whether the laser beam focus spot deviated from the desired welding seam. Experimental results showed that the keyhole centroid has related to the seam offset, and can reflect the welding quality.

Geometry model construction in infrared image theory simulation of buildings

Geometric model construction is the basis of infrared image theory simulation. Taking the construction of the geometric model of one building in Harbin as an example, this paper analyzes the theoretical groundings of simplification and principles of geometric model construction of buildings. It then discusses some particular treatment methods in calculating the radiation transfer coefficient in geometric model construction using the Monte Carlo Method.

Infrared image simulation of ground maneuver target and scene

Infrared scene simulation has extensive applications in military and civil fields. Based on a certain experimental environment,object-oriented graphics rendering engine（ OGRE） is utilized to simulate a real three-dimensional infrared complex scene. First,the target radiation of each part is calculated based on our experimental data. Then through the analysis of the radiation characteristics of targets and related material,an infrared texture library is established and the 3ds Max software is applied to establish an infrared radiation model.Finally,a real complex infrared scene is created by using the OGRE engine image rendering technology and graphic processing unit（ GPU） programmable pipeline technology. The results show that the simulation images are very similar to real images and are good supplements to real data.

DIGITAL CONTOUR ENHANCEMENT OF INFRARED IMAGE

The digital contour enhancement techniques of infrared image are discussed. Emphasis is laid the thermal spread compensation method. On the basis of describing the theory of the method, a model is suggested. The concrete project based on the model for realizing digital contour enhancement of the infrared thermal image is put forward, and some test results are shown.

Automatic infrared image recognition method for substation equipment based on a deep self-attention network and multi-factor similarity calculation

Infrared image recognition plays an important role in the inspection of power equipment.Existing technologies dedicated to this purpose often require manually selected features,which are not transferable and interpretable,and have limited training data.To address these limitations,this paper proposes an automatic infrared image recognition framework,which includes an object recognition module based on a deep self-attention network and a temperature distribution identification module based on a multi-factor similarity calculation.First,the features of an input image are extracted and embedded using a multi-head attention encoding-decoding mechanism.Thereafter,the embedded features are used to predict the equipment component category and location.In the located area,preliminary segmentation is performed.Finally,similar areas are gradually merged,and the temperature distribution of the equipment is obtained to identify a fault.Our experiments indicate that the proposed method demonstrates significantly improved accuracy compared with other related methods and,hence,provides a good reference for the automation of power equipment inspection.

Color Estimation for Thermal Infrared Imagery Based on Kernel PCA and Sparse Representation

Adding colors to monochrome thermal infrared images can help observers understand the scenery better. A nonlinear color estimation method for single-band thermal infrared imagery based on kernel principal component analysis (KPCA) and sparse representation was proposed. Nonlinear features of infrared image were extracted using KPCA. The relationship between image features and chromatic values was learned using sparse representation and a color estimation model was obtained. The thermal infrared images can be rendered automatically using the color estimation model. The experimental results show that the proposed method can render infrared image with an accurate color appearance. The proposed idea can also be used in other color estimation problem.

Infrared and Visible Image Fusion Based on Res2Net-Transformer Automatic Encoding and Decoding

A novel image fusion network framework with an autonomous encoder and decoder is suggested to increase thevisual impression of fused images by improving the quality of infrared and visible light picture fusion. The networkcomprises an encoder module, fusion layer, decoder module, and edge improvementmodule. The encoder moduleutilizes an enhanced Inception module for shallow feature extraction, then combines Res2Net and Transformerto achieve deep-level co-extraction of local and global features from the original picture. An edge enhancementmodule (EEM) is created to extract significant edge features. A modal maximum difference fusion strategy isintroduced to enhance the adaptive representation of information in various regions of the source image, therebyenhancing the contrast of the fused image. The encoder and the EEM module extract features, which are thencombined in the fusion layer to create a fused picture using the decoder. Three datasets were chosen to test thealgorithmproposed in this paper. The results of the experiments demonstrate that the network effectively preservesbackground and detail information in both infrared and visible images, yielding superior outcomes in subjectiveand objective evaluations.

Double-ended passivator enables dark-current-suppressed colloidal quantum dot photodiodes for CMOS-integrated infrared imagers

Lead sulfide(PbS)colloidal quantum dot(CQD)photodiodes integrated with silicon-based readout integrated circuits(ROICs)offer a promising solution for the next-generation short-wave infrared(SWIR)imaging technology.Despite their potential,large-size CQD photodiodes pose a challenge due to high dark currents resulting from surface states on nonpassivated(100)facets and trap states generated by CQD fusion.In this work,we present a novel approach to address this issue by introducing double-ended ligands that supplementally passivate(100)facets of halidecapped large-size CQDs,leading to suppressed bandtail states and reduced defect concentration.Our results demonstrate that the dark current density is highly suppressed by about an order of magnitude to 9.6 nA cm^(2) at -10 mV,which is among the lowest reported for PbS CQD photodiodes.Furthermore,the performance of the photodiodes is exemplary,yielding an external quantum efficiency of 50.8%(which corresponds to a responsivity of 0.532 A W^(-1))and a specific detectivity of 2.5×10^(12) Jones at 1300 nm.By integrating CQD photodiodes with CMOS ROICs,the CQD imager provides high-resolution(640×512)SWIR imaging for infrared penetration and material discrimination.

Advancing automated pupillometry:a practical deep learning model utilizing infrared pupil images

AIM:To establish pupil diameter measurement algorithms based on infrared images that can be used in real-world clinical settings.METHODS:A total of 188 patients from outpatient clinic at He Eye Specialist Shenyang Hospital from Spetember to December 2022 were included,and 13470 infrared pupil images were collected for the study.All infrared images for pupil segmentation were labeled using the Labelme software.The computation of pupil diameter is divided into four steps:image pre-processing,pupil identification and localization,pupil segmentation,and diameter calculation.Two major models are used in the computation process:the modified YoloV3 and Deeplabv 3+models,which must be trained beforehand.RESULTS:The test dataset included 1348 infrared pupil images.On the test dataset,the modified YoloV3 model had a detection rate of 99.98% and an average precision(AP)of 0.80 for pupils.The DeeplabV3+model achieved a background intersection over union(IOU)of 99.23%,a pupil IOU of 93.81%,and a mean IOU of 96.52%.The pupil diameters in the test dataset ranged from 20 to 56 pixels,with a mean of 36.06±6.85 pixels.The absolute error in pupil diameters between predicted and actual values ranged from 0 to 7 pixels,with a mean absolute error(MAE)of 1.06±0.96 pixels.CONCLUSION:This study successfully demonstrates a robust infrared image-based pupil diameter measurement algorithm,proven to be highly accurate and reliable for clinical application.

Research on Defect Detection of Wind Turbine Blades Based on Morphology and Improved Otsu Algorithm Using Infrared Images

To address the issues of low accuracy and high false positive rate in traditional Otsu algorithm for defect detection on infrared images of wind turbine blades(WTB),this paper proposes a technique that combines morphological image enhancement with an improved Otsu algorithm.First,mathematical morphology’s differential multi-scale white and black top-hat operations are applied to enhance the image.The algorithm employs entropy as the objective function to guide the iteration process of image enhancement,selecting appropriate structural element scales to execute differential multi-scale white and black top-hat transformations,effectively enhancing the detail features of defect regions and improving the contrast between defects and background.Afterwards,grayscale inversion is performed on the enhanced infrared defect image to better adapt to the improved Otsu algorithm.Finally,by introducing a parameter K to adjust the calculation of inter-class variance in the Otsu method,the weight of the target pixels is increased.Combined with the adaptive iterative threshold algorithm,the threshold selection process is further fine-tuned.Experimental results show that compared to traditional Otsu algorithms and other improvements,the proposed method has significant advantages in terms of defect detection accuracy and reducing false positive rates.The average defect detection rate approaches 1,and the average Hausdorff distance decreases to 0.825,indicating strong robustness and accuracy of the method.

Enhanced target tracking algorithm for autonomous driving based on visible and infrared image fusion

In autonomous driving,target tracking is essential to environmental perception.The study of target tracking algorithms can improve the accuracy of an autonomous driving vehicle’s perception,which is of great significance in ensuring the safety of autonomous driving and promoting the landing of technical applications.This study focuses on the fusion tracking algorithm based on visible and infrared images.The proposed approach utilizes a feature-level image fusion method,dividing the tracking process into two components:image fusion and target tracking.An unsupervised network,Visible and Infrared image Fusion Network(VIF-net),is employed for visible and infrared image fusion in the image fusion part.In the target tracking part,Siamese Region Proposal Network(SiamRPN),based on deep learning,tracks the target with fused images.The fusion tracking algorithm is trained and evaluated on the visible infrared image dataset RGBT234.Experimental results demonstrate that the algorithm outperforms training networks solely based on visible images,proving that the fusion of visible and infrared images in the target tracking algorithm can improve the accuracy of the target tracking even if it is like tracking-based visual images.This improvement is also attributed to the algorithm’s ability to extract infrared image features,augmenting the target tracking accuracy.

IR-YOLO: Real-Time Infrared Vehicle and Pedestrian Detection

Road traffic safety can decrease when drivers drive in a low-visibility environment.The application of visual perception technology to detect vehicles and pedestrians in infrared images proves to be an effective means of reducing the risk of accidents.To tackle the challenges posed by the low recognition accuracy and the substan-tial computational burden associated with current infrared pedestrian-vehicle detection methods,an infrared pedestrian-vehicle detection method A proposal is presented,based on an enhanced version of You Only Look Once version 5(YOLOv5).First,A head specifically designed for detecting small targets has been integrated into the model to make full use of shallow feature information to enhance the accuracy in detecting small targets.Second,the Focal Generalized Intersection over Union(GIoU)is employed as an alternative to the original loss function to address issues related to target overlap and category imbalance.Third,the distribution shift convolution optimization feature extraction operator is used to alleviate the computational burden of the model without significantly compromising detection accuracy.The test results of the improved algorithm show that its average accuracy(mAP)reaches 90.1%.Specifically,the Giga Floating Point Operations Per second(GFLOPs)of the improved algorithm is only 9.1.In contrast,the improved algorithms outperformed the other algorithms on similar GFLOPs,such as YOLOv6n(11.9),YOLOv8n(8.7),YOLOv7t(13.2)and YOLOv5s(16.0).The mAPs that are 4.4%,3%,3.5%,and 1.7%greater than those of these algorithms show that the improved algorithm achieves higher accuracy in target detection tasks under similar computational resource overhead.On the other hand,compared with other algorithms such as YOLOv8l(91.1%),YOLOv6l(89.5%),YOLOv7(90.8%),and YOLOv3(90.1%),the improved algorithm needs only 5.5%,2.3%,8.6%,and 2.3%,respectively,of the GFLOPs.The improved algorithm has shown significant advancements in balancing accuracy and computational efficiency,making it promising for practical use in resource-limited scenarios.