As a pathfinder of the SiTian project,the Mini-SiTian(MST)Array,employed three commercial CMOS cameras,represents a next-generation,cost-effective optical time-domain survey project.This paper focuses primarily on the...As a pathfinder of the SiTian project,the Mini-SiTian(MST)Array,employed three commercial CMOS cameras,represents a next-generation,cost-effective optical time-domain survey project.This paper focuses primarily on the precise data processing pipeline designed for wide-field,CMOS-based devices,including the removal of instrumental effects,astrometry,photometry,and flux calibration.When applying this pipeline to approximately3000 observations taken in the Field 02(f02)region by MST,the results demonstrate a remarkable astrometric precision of approximately 70–80 mas(about 0.1 pixel),an impressive calibration accuracy of approximately1 mmag in the MST zero points,and a photometric accuracy of about 4 mmag for bright stars.Our studies demonstrate that MST CMOS can achieve photometric accuracy comparable to that of CCDs,highlighting the feasibility of large-scale CMOS-based optical time-domain surveys and their potential applications for cost optimization in future large-scale time-domain surveys,like the SiTian project.展开更多
Spatial resolution and image-processing methods for full-field X-ray fluorescence(FF-XRF)imaging using X-ray pinhole cameras were studied using Geant4simulations with different geometries and algorithms for image reco...Spatial resolution and image-processing methods for full-field X-ray fluorescence(FF-XRF)imaging using X-ray pinhole cameras were studied using Geant4simulations with different geometries and algorithms for image reconstruction.The main objectives were:(1)calculating the quantum efficiency curves of specific cameras,(2)studying the relationships between the spatial resolution and the pinhole diameter,magnification,and camera binning value,and(3)comparing image-processing methods for pinhole camera systems.Several results were obtained using a point and plane source as the X-ray fluorescence emitter and an array of 100×100 silicon pixel detectors as the X-ray camera.The quantum efficiency of a back-illuminated deep depletion(BI-DD)structure was above 30%for the XRF energies in the 0.8–9 keV range,with the maximum of 93.7%at 4 keV.The best spatial resolution of the pinhole camera was 24.7μm and 31.3 lp/mm when measured using the profile function of the point source,with the diameter of 20μm,magnification of 3.16,and camera bin of 1.A blind deconvolution algorithm with Gaussian filtering performed better than the Wiener filter and Richardson iterative methods on FF-XRF images,with the signal-to-noise ratio of 7.81 dB and improved signalto-noise ratio of 7.24 dB at the diameter of 120μm,magnification of 1.0,and camera bin of 1.展开更多
Diffraction enhanced imaging （DEI） has been widely applied in many fields, especially when imaging low-Z samples or when the difference in the attenuation coefficient between different regions in the sample is too s...Diffraction enhanced imaging （DEI） has been widely applied in many fields, especially when imaging low-Z samples or when the difference in the attenuation coefficient between different regions in the sample is too small to be detected. Recent developments of this technique have presented a need for a new software package for data analysis. Here, the Diffraction Enhanced Image Reconstructor （DEIReconstructor）, developed in Matlab, is presented. DEIReconstructor has a user-friendly graphical user interface and runs under any of the 32~bit or 64- bit Microsoft Windows operating systems including XP and WinT. Many of its features are integrated to support imaging preprocessing, extract absorption, refractive and scattering information of diffraction enhanced imaging and allow for parallel-beam tomography reconstruction for DEI-CT. Furthermore, many other useful functions are also implemented in order to simplify the data analysis and the presentation of results. The compiled software package is freely available.展开更多
Noble metal nanoparticles with localized surface plasmon resonance （LSPR） properties are widely used as optical sensors in biochemical detection and medical diagnosis. In this paper, we propose an effective determin...Noble metal nanoparticles with localized surface plasmon resonance （LSPR） properties are widely used as optical sensors in biochemical detection and medical diagnosis. In this paper, we propose an effective determination method to measure the LSPR absorption intensity of gold nanorods （GNRs）. A near-infrared （NIR） imaging system is established, and an NIR absorption image of the multiple samples of the colloidal GNRs is captured. Then, the LSPR absorption intensities of these samples are obtained by calculating the average grayscale of the target areas based on the NIR image processing technology. By using this method, the LSPR absorption intensities of the multiple samples are determined all at once, and their accuracy is as high as that obtained by using spectrophotometry. These results suggest that this method is an efficient multi-channel determination technique with high-throughput sensing applications.展开更多
Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques...Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques to detect defects,as traditional methods are often prone to human error,and this issue is also addressed through image processing(IP).In addition to IP,automated,accurate,and real-time detection of structural defects,such as cracks,corrosion,and material degradation that conventional inspection techniques may miss,is made possible by Artificial Intelligence(AI)technologies like Machine Learning(ML)and Deep Learning(DL).This review examines the integration of computer vision and AI techniques in Structural Health Monitoring(SHM),investigating their effectiveness in detecting various forms of structural deterioration.Also,it evaluates ML and DL models in SHM for their accuracy in identifying and assessing structural damage,ultimately enhancing safety,durability,and maintenance practices in the field.Key findings reveal that AI-powered approaches,especially those utilizing IP and DL models like CNNs,significantly improve detection efficiency and accuracy,with reported accuracies in various SHM tasks.However,significant research gaps remain,including challenges with the consistency,quality,and environmental resilience of image data,a notable lack of standardized models and datasets for training across diverse structures,and concerns regarding computational costs,model interpretability,and seamless integration with existing systems.Future work should focus on developing more robust models through data augmentation,transfer learning,and hybrid approaches,standardizing protocols,and fostering interdisciplinary collaboration to overcome these limitations and achieve more reliable,scalable,and affordable SHM systems.展开更多
This study seeks to establish a novel,semi-automatic system that utilizes Industry 4.0 principles to effectively determine both acceptable and rejectable concrete cubes with regard to their failure modes,significantly...This study seeks to establish a novel,semi-automatic system that utilizes Industry 4.0 principles to effectively determine both acceptable and rejectable concrete cubes with regard to their failure modes,significantly contributing to the dependability of concrete quality evaluations.The study utilizes image processing and machine learning(ML)methods,namely object detectionmodels such as YOLOv8 and Convolutional Neural Networks(CNNs),to evaluate images of concrete cubes.These models are trained and validated on an extensive database of annotated images from real-world and laboratory conditions.Preliminary results indicate a good performance in the classification of concrete cube failure modes.The proposed system accurately identifies cracks,determines the severity of damage to structures,indicating the potential to minimize human errors and discrepancies that might occur through the current techniques to detect the failure mode of concrete cubes.Thedeveloped systemcould significantly improve the reliability of concrete cube assessments,reduce resource wastage,and contribute to more sustainable construction practices.By minimizing material costs and errors,this innovation supports the construction industry’s move towards sustainability.展开更多
Breast cancer remains one of the most pressing global health concerns,and early detection plays a crucial role in improving survival rates.Integrating digital mammography with computational techniques and advanced ima...Breast cancer remains one of the most pressing global health concerns,and early detection plays a crucial role in improving survival rates.Integrating digital mammography with computational techniques and advanced image processing has significantly enhanced the ability to identify abnormalities.However,existing methodologies face persistent challenges,including low image contrast,noise interference,and inaccuracies in segmenting regions of interest.To address these limitations,this study introduces a novel computational framework for analyzing mammographic images,evaluated using the Mammographic Image Analysis Society(MIAS)dataset comprising 322 samples.The proposed methodology follows a structured three-stage approach.Initially,mammographic scans are classified using the Breast Imaging Reporting and Data System(BI-RADS),ensuring systematic and standardized image analysis.Next,the pectoral muscle,which can interfere with accurate segmentation,is effectively removed to refine the region of interest(ROI).The final stage involves an advanced image pre-processing module utilizing Independent Component Analysis(ICA)to enhance contrast,suppress noise,and improve image clarity.Following these enhancements,a robust segmentation technique is employed to delineated abnormal regions.Experimental results validate the efficiency of the proposed framework,demonstrating a significant improvement in the Effective Measure of Enhancement(EME)and a 3 dB increase in Peak Signal-to-Noise Ratio(PSNR),indicating superior image quality.The model also achieves an accuracy of approximately 97%,surpassing contemporary techniques evaluated on the MIAS dataset.Furthermore,its ability to process mammograms across all BI-RADS categories highlights its adaptability and reliability for clinical applications.This study presents an advanced and dependable computational framework for mammographic image analysis,effectively addressing critical challenges in noise reduction,contrast enhancement,and segmentation precision.The proposed approach lays the groundwork for seamless integration into computer-aided diagnostic(CAD)systems,with the potential to significantly enhance early breast cancer detection and contribute to improved patient outcomes.展开更多
In micro milling machining,tool wear directly affects workpiece quality and accuracy,making effective tool wear monitoring a key factor in ensuring product integrity.The use of machine vision-based methods can provide...In micro milling machining,tool wear directly affects workpiece quality and accuracy,making effective tool wear monitoring a key factor in ensuring product integrity.The use of machine vision-based methods can provide an intuitive and efficient representation of tool wear conditions.However,micro milling tools have non-flat flanks,thin coatings can peel off,and spindle orientation is uncertain during downtime.These factors result in low pixel values,uneven illumination,and arbitrary tool position.To address this,we propose an image-based tool wear monitoring method.It combines multiple algorithms to restore lost pixels due to uneven illumination during segmentation and accurately extract wear areas.Experimental results demonstrate that the proposed algorithm exhibits high robustness to such images,effectively addressing the effects of illumination and spindle orientation.Additionally,the algorithm has low complexity,fast execution time,and significantly reduces the detection time in situ.展开更多
All-optical image processing has been viewed as a promising technique for its high computation speed and low power consumption.However,current methods are often restricted to few functionalities and low reconfigurabil...All-optical image processing has been viewed as a promising technique for its high computation speed and low power consumption.However,current methods are often restricted to few functionalities and low reconfigurabilities,which cannot meet the growing demand for device integration and scenario adaptation in next-generation vision regimes.Here,we propose and experimentally demonstrate a bilayer liquid crystal computing platform for reconfigurable image processing.Under different in-situ/ex-situ twisted/untwisted conditions of the layers,our approach allows for eight kinds of image processing functions,including one/two-channel bright field imaging,one/two-channel vortex filtering,horizontally/vertically one-dimensional edge detection,vertex detection,and photonic spin Hall effect-based resolution adjustable edge detection.A unified theoretical framework for this scheme is established on the transfer function theory,which coincides well with the experimental results.The proposed method offers an easily-switchable multi-functional solution to optical image processing by introducing mechanical degrees of freedom,which may enable emerging applications in computer vision,autonomous driving,and biomedical microscopy.展开更多
The increasing demand for high-resolution solar observations has driven the development of advanced data processing and enhancement techniques for ground-based solar telescopes.This study focuses on developing a pytho...The increasing demand for high-resolution solar observations has driven the development of advanced data processing and enhancement techniques for ground-based solar telescopes.This study focuses on developing a python-based package(GT-scopy)for data processing and enhancing for giant solar telescopes,with application to the 1.6 m Goode Solar Telescope(GST)at Big Bear Solar Observatory.The objective is to develop a modern data processing software for refining existing data acquisition,processing,and enhancement methodologies to achieve atmospheric effect removal and accurate alignment at the sub-pixel level,particularly within the processing levels 1.0-1.5.In this research,we implemented an integrated and comprehensive data processing procedure that includes image de-rotation,zone-of-interest selection,coarse alignment,correction for atmospheric distortions,and fine alignment at the sub-pixel level with an advanced algorithm.The results demonstrate a significant improvement in image quality,with enhanced visibility of fine solar structures both in sunspots and quiet-Sun regions.The enhanced data processing package developed in this study significantly improves the utility of data obtained from the GST,paving the way for more precise solar research and contributing to a better understanding of solar dynamics.This package can be adapted for other ground-based solar telescopes,such as the Daniel K.Inouye Solar Telescope(DKIST),the European Solar Telescope(EST),and the 8 m Chinese Giant Solar Telescope,potentially benefiting the broader solar physics community.展开更多
This paper provides a comprehensive introduction to the mini-Si Tian Real-time Image Processing pipeline(STRIP)and evaluates its operational performance.The STRIP pipeline is specifically designed for real-time alert ...This paper provides a comprehensive introduction to the mini-Si Tian Real-time Image Processing pipeline(STRIP)and evaluates its operational performance.The STRIP pipeline is specifically designed for real-time alert triggering and light curve generation for transient sources.By applying the STRIP pipeline to both simulated and real observational data of the Mini-Si Tian survey,it successfully identified various types of variable sources,including stellar flares,supernovae,variable stars,and asteroids,while meeting requirements of reduction speed within 5 minutes.For the real observational data set,the pipeline detected one flare event,127 variable stars,and14 asteroids from three monitored sky regions.Additionally,two data sets were generated:one,a real-bogus training data set comprising 218,818 training samples,and the other,a variable star light curve data set with 421instances.These data sets will be used to train machine learning algorithms,which are planned for future integration into STRIP.展开更多
Radio interferometric imaging samples visibility data in the spatial frequency domain and then reconstructs the image.Because of the limited number of antennas,the sampling is usually sparse and noisy.Compressed sensi...Radio interferometric imaging samples visibility data in the spatial frequency domain and then reconstructs the image.Because of the limited number of antennas,the sampling is usually sparse and noisy.Compressed sensingbased on convex optimization is an effective reconstruction method for sparse sampling conditions.The hyperparameter for the l_(1)regularization term is an important parameter that directly affects the quality of the reconstructed image.If its value is too high,the image structure will be missed.If its value is too low,the image will have a low signal-to-noise ratio.The selection of hyperparameters under different levels of image noise is studied in this paper,and solar radio images are used as examples to analyze the optimization results of compressed sensing algorithms under different noise conditions.The simulation results show that when the salt-and-pepper noise density is between 10%and 30%,the compressed sensing algorithm obtains good reconstruction results.Moreover,the optimal hyperparameter value has a linear relationship with the noise density,and the mean squared error of regression is approximately 8.10×10^(-8).展开更多
In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the qualit...In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the quality information. Abundant weld quality information is contained in weld pool and keyhole. Aiming at Nd：YAG laser welding of stainless steel, a coaxial visual sensing system was constructed. The images of weld pool and keyhole were obtained. Based on the gray character of weld pool and keyhole in images, an image processing algorithm was designed. The search start point and search criteria of weld pool and keyhole edge were determined respectively.展开更多
To restore the sub image in a rosette scanning system and provide target recognition system with a low distorted image, the sub image is processed with morphological filters. Morphological filter can process rosette...To restore the sub image in a rosette scanning system and provide target recognition system with a low distorted image, the sub image is processed with morphological filters. Morphological filter can process rosette scanning sub images more effectively. It can restore the original area and shape of an object effectively, and keep the energy information of the object. To process sub images got by a rosette scanning system, morphological filter is more effective than traditional low pass filter.展开更多
Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in ...Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.展开更多
Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood s...Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.展开更多
Globally,grape cultivation spans vast areas and achieves substantial yields,making grapes and related industries vital economic pillars for many nations.In grape production,efficient and precise management during key ...Globally,grape cultivation spans vast areas and achieves substantial yields,making grapes and related industries vital economic pillars for many nations.In grape production,efficient and precise management during key growth stages is essential for enhancing both yield and quality.In view of the problems that during the grape inflorescences and young fruits stage,the targets are small in size,easily obscured by branches and leaves,and highly similar in color to the background,resulting in poor recognition performance of existing detection methods in complex natural environments,which in turn restricts the application of precision spraying technology.This paper establishes a dedicated dataset for grape inflorescences and young fruits in Xinjiang and proposes an improved lightweight detection model,YOLOv8-FCD.The model incorporates a PConv-based C2f_Faster module to reduce parameter count and computational complexity,replaces the original upsampling method with the CARAFE module to enhance feature extraction capability,and introduces the Detect_SEAM detection head to improve recognition accuracy under occlusion and small-target conditions.Experimental results show that the YOLOv8-FCD model achieves a detection precision(P)of 93.7%and a recall(R)of 87.3%,with a mean average precision(mAP)of 94.6%.Compared to the original YOLOv8n model,P improved by 8.2%,mAP increased by 2.6%,and the model size is reduced to 85.71%of the original.This model provides effective technical support for the identification of grape inflorescences and young fruits in intelligent spraying for plant protection.展开更多
Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown...Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown that incorporating multiscale features is crucial for improving restoration results.In this paper,we propose a multiscale Transformer(MST)that captures cross-scale attention among tokens,thereby effectively leveraging the multiscale patch recurrence prior of natural images.Furthermore,we introduce a channel-gate feed-forward network(CGFN)to enhance inter-channel information aggregation and reduce channel redundancy.To simultaneously utilise global,local and multiscale features,we design a multitype feature integration block(MFIB).Extensive experiments on both image super-resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state-of-the-art performance.Ablation studies further verify the effectiveness of each proposed module.展开更多
With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-...With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-consuming and labor-intensive,but they also struggle to provide consistent,high-precision detection and realtime monitoring of pavement surface defects.To overcome these limitations,we propose an Automatic Recognition of PavementDefect(ARPD)algorithm,which leverages unmanned aerial vehicle(UAV)-based aerial imagery to automate the inspection process.The ARPD framework incorporates a backbone network based on the Selective State Space Model(S3M),which is designed to capture long-range temporal dependencies.This enables effective modeling of dynamic correlations among redundant and often repetitive structures commonly found in road imagery.Furthermore,a neck structure based on Semantics and Detail Infusion(SDI)is introduced to guide cross-scale feature fusion.The SDI module enhances the integration of low-level spatial details with high-level semantic cues,thereby improving feature expressiveness and defect localization accuracy.Experimental evaluations demonstrate that theARPDalgorithm achieves a mean average precision(mAP)of 86.1%on a custom-labeled pavement defect dataset,outperforming the state-of-the-art YOLOv11 segmentation model.The algorithm also maintains strong generalization ability on public datasets.These results confirm that ARPD is well-suited for diverse real-world applications in intelligent,large-scale highway defect monitoring and maintenance planning.展开更多
Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation with...Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation within a very short horizon(second/minute).To achieve the precise forecasting of cloud cover,an image preprocessing method based on total-sky images is proposed to remove the interference and address the image edge distortion issue.An optimal threshold estimation method is further designed to achieve higher cloud identification precision.Considering the cloud's meteorological properties,a random hypersurface model(RHM)based on the Gaussian mixture probability hypothesis density(GM-PHD)filter is applied to track the cloud.The GM-PHD can track the rotation and diffusion of clouds,which helps to estimate sun-cloud collision.Furthermore,a hybrid autoregressive integrated moving average(ARIMA)and backpropagation(BP)neural network-based model is applied for intra-hour PV power forecasting.The experiment results demonstrate that the proposed cloud-tracking-based PV power forecasting model can capture the ramp behavior of PV power,improving forecasting precision.展开更多
基金supported by the National Key Basic R&D Program of China via 2023YFA1608303the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0550103)+3 种基金the National Science Foundation of China 12422303,12403024,12222301,12173007,and 12261141690the Postdoctoral Fellowship Program of CPSF under grant Number GZB20240731the Young Data Scientist Project of the National Astronomical Data Center,and the China Post-doctoral Science Foundation No.2023M743447support from the NSFC through grant No.12303039 and No.12261141690.
文摘As a pathfinder of the SiTian project,the Mini-SiTian(MST)Array,employed three commercial CMOS cameras,represents a next-generation,cost-effective optical time-domain survey project.This paper focuses primarily on the precise data processing pipeline designed for wide-field,CMOS-based devices,including the removal of instrumental effects,astrometry,photometry,and flux calibration.When applying this pipeline to approximately3000 observations taken in the Field 02(f02)region by MST,the results demonstrate a remarkable astrometric precision of approximately 70–80 mas(about 0.1 pixel),an impressive calibration accuracy of approximately1 mmag in the MST zero points,and a photometric accuracy of about 4 mmag for bright stars.Our studies demonstrate that MST CMOS can achieve photometric accuracy comparable to that of CCDs,highlighting the feasibility of large-scale CMOS-based optical time-domain surveys and their potential applications for cost optimization in future large-scale time-domain surveys,like the SiTian project.
基金supported by the Sichuan Science and Technology Program,China(No.2020ZDZX0004)。
文摘Spatial resolution and image-processing methods for full-field X-ray fluorescence(FF-XRF)imaging using X-ray pinhole cameras were studied using Geant4simulations with different geometries and algorithms for image reconstruction.The main objectives were:(1)calculating the quantum efficiency curves of specific cameras,(2)studying the relationships between the spatial resolution and the pinhole diameter,magnification,and camera binning value,and(3)comparing image-processing methods for pinhole camera systems.Several results were obtained using a point and plane source as the X-ray fluorescence emitter and an array of 100×100 silicon pixel detectors as the X-ray camera.The quantum efficiency of a back-illuminated deep depletion(BI-DD)structure was above 30%for the XRF energies in the 0.8–9 keV range,with the maximum of 93.7%at 4 keV.The best spatial resolution of the pinhole camera was 24.7μm and 31.3 lp/mm when measured using the profile function of the point source,with the diameter of 20μm,magnification of 3.16,and camera bin of 1.A blind deconvolution algorithm with Gaussian filtering performed better than the Wiener filter and Richardson iterative methods on FF-XRF images,with the signal-to-noise ratio of 7.81 dB and improved signalto-noise ratio of 7.24 dB at the diameter of 120μm,magnification of 1.0,and camera bin of 1.
基金Supported by National Basic Research Program of China(2012CB825800)National Natural Science Foundation of China(11205189,11375225,81271574,U1332109)Knowledge Innovation Program of Chinese Academy of Sciences(KJCX2-YW-N42)
文摘Diffraction enhanced imaging （DEI） has been widely applied in many fields, especially when imaging low-Z samples or when the difference in the attenuation coefficient between different regions in the sample is too small to be detected. Recent developments of this technique have presented a need for a new software package for data analysis. Here, the Diffraction Enhanced Image Reconstructor （DEIReconstructor）, developed in Matlab, is presented. DEIReconstructor has a user-friendly graphical user interface and runs under any of the 32~bit or 64- bit Microsoft Windows operating systems including XP and WinT. Many of its features are integrated to support imaging preprocessing, extract absorption, refractive and scattering information of diffraction enhanced imaging and allow for parallel-beam tomography reconstruction for DEI-CT. Furthermore, many other useful functions are also implemented in order to simplify the data analysis and the presentation of results. The compiled software package is freely available.
基金Supported by the Natural Science Foundation of Jiangsu Province(SBK201240182)
文摘Noble metal nanoparticles with localized surface plasmon resonance （LSPR） properties are widely used as optical sensors in biochemical detection and medical diagnosis. In this paper, we propose an effective determination method to measure the LSPR absorption intensity of gold nanorods （GNRs）. A near-infrared （NIR） imaging system is established, and an NIR absorption image of the multiple samples of the colloidal GNRs is captured. Then, the LSPR absorption intensities of these samples are obtained by calculating the average grayscale of the target areas based on the NIR image processing technology. By using this method, the LSPR absorption intensities of the multiple samples are determined all at once, and their accuracy is as high as that obtained by using spectrophotometry. These results suggest that this method is an efficient multi-channel determination technique with high-throughput sensing applications.
文摘Structural Health Monitoring(SHM)systems play a key role in managing buildings and infrastructure by delivering vital insights into their strength and structural integrity.There is a need for more efficient techniques to detect defects,as traditional methods are often prone to human error,and this issue is also addressed through image processing(IP).In addition to IP,automated,accurate,and real-time detection of structural defects,such as cracks,corrosion,and material degradation that conventional inspection techniques may miss,is made possible by Artificial Intelligence(AI)technologies like Machine Learning(ML)and Deep Learning(DL).This review examines the integration of computer vision and AI techniques in Structural Health Monitoring(SHM),investigating their effectiveness in detecting various forms of structural deterioration.Also,it evaluates ML and DL models in SHM for their accuracy in identifying and assessing structural damage,ultimately enhancing safety,durability,and maintenance practices in the field.Key findings reveal that AI-powered approaches,especially those utilizing IP and DL models like CNNs,significantly improve detection efficiency and accuracy,with reported accuracies in various SHM tasks.However,significant research gaps remain,including challenges with the consistency,quality,and environmental resilience of image data,a notable lack of standardized models and datasets for training across diverse structures,and concerns regarding computational costs,model interpretability,and seamless integration with existing systems.Future work should focus on developing more robust models through data augmentation,transfer learning,and hybrid approaches,standardizing protocols,and fostering interdisciplinary collaboration to overcome these limitations and achieve more reliable,scalable,and affordable SHM systems.
文摘This study seeks to establish a novel,semi-automatic system that utilizes Industry 4.0 principles to effectively determine both acceptable and rejectable concrete cubes with regard to their failure modes,significantly contributing to the dependability of concrete quality evaluations.The study utilizes image processing and machine learning(ML)methods,namely object detectionmodels such as YOLOv8 and Convolutional Neural Networks(CNNs),to evaluate images of concrete cubes.These models are trained and validated on an extensive database of annotated images from real-world and laboratory conditions.Preliminary results indicate a good performance in the classification of concrete cube failure modes.The proposed system accurately identifies cracks,determines the severity of damage to structures,indicating the potential to minimize human errors and discrepancies that might occur through the current techniques to detect the failure mode of concrete cubes.Thedeveloped systemcould significantly improve the reliability of concrete cube assessments,reduce resource wastage,and contribute to more sustainable construction practices.By minimizing material costs and errors,this innovation supports the construction industry’s move towards sustainability.
基金funded by Deanship of Graduate Studies and Scientific Research at Najran University for supporting the research project through the Nama’a program,with the project code NU/GP/MRC/13/771-4.
文摘Breast cancer remains one of the most pressing global health concerns,and early detection plays a crucial role in improving survival rates.Integrating digital mammography with computational techniques and advanced image processing has significantly enhanced the ability to identify abnormalities.However,existing methodologies face persistent challenges,including low image contrast,noise interference,and inaccuracies in segmenting regions of interest.To address these limitations,this study introduces a novel computational framework for analyzing mammographic images,evaluated using the Mammographic Image Analysis Society(MIAS)dataset comprising 322 samples.The proposed methodology follows a structured three-stage approach.Initially,mammographic scans are classified using the Breast Imaging Reporting and Data System(BI-RADS),ensuring systematic and standardized image analysis.Next,the pectoral muscle,which can interfere with accurate segmentation,is effectively removed to refine the region of interest(ROI).The final stage involves an advanced image pre-processing module utilizing Independent Component Analysis(ICA)to enhance contrast,suppress noise,and improve image clarity.Following these enhancements,a robust segmentation technique is employed to delineated abnormal regions.Experimental results validate the efficiency of the proposed framework,demonstrating a significant improvement in the Effective Measure of Enhancement(EME)and a 3 dB increase in Peak Signal-to-Noise Ratio(PSNR),indicating superior image quality.The model also achieves an accuracy of approximately 97%,surpassing contemporary techniques evaluated on the MIAS dataset.Furthermore,its ability to process mammograms across all BI-RADS categories highlights its adaptability and reliability for clinical applications.This study presents an advanced and dependable computational framework for mammographic image analysis,effectively addressing critical challenges in noise reduction,contrast enhancement,and segmentation precision.The proposed approach lays the groundwork for seamless integration into computer-aided diagnostic(CAD)systems,with the potential to significantly enhance early breast cancer detection and contribute to improved patient outcomes.
基金Supported by National Natural Science Foundation of China(Grant No.52175528)。
文摘In micro milling machining,tool wear directly affects workpiece quality and accuracy,making effective tool wear monitoring a key factor in ensuring product integrity.The use of machine vision-based methods can provide an intuitive and efficient representation of tool wear conditions.However,micro milling tools have non-flat flanks,thin coatings can peel off,and spindle orientation is uncertain during downtime.These factors result in low pixel values,uneven illumination,and arbitrary tool position.To address this,we propose an image-based tool wear monitoring method.It combines multiple algorithms to restore lost pixels due to uneven illumination during segmentation and accurately extract wear areas.Experimental results demonstrate that the proposed algorithm exhibits high robustness to such images,effectively addressing the effects of illumination and spindle orientation.Additionally,the algorithm has low complexity,fast execution time,and significantly reduces the detection time in situ.
基金supported in part by the National Natural Science Foundation of China(12421005,12374273,and 61805077)in part by the Natural Science Foundation of Hunan Province(2025JJ50046)in part by the Hunan Provincial Major Sci-Tech Program(2023ZJ1010)。
文摘All-optical image processing has been viewed as a promising technique for its high computation speed and low power consumption.However,current methods are often restricted to few functionalities and low reconfigurabilities,which cannot meet the growing demand for device integration and scenario adaptation in next-generation vision regimes.Here,we propose and experimentally demonstrate a bilayer liquid crystal computing platform for reconfigurable image processing.Under different in-situ/ex-situ twisted/untwisted conditions of the layers,our approach allows for eight kinds of image processing functions,including one/two-channel bright field imaging,one/two-channel vortex filtering,horizontally/vertically one-dimensional edge detection,vertex detection,and photonic spin Hall effect-based resolution adjustable edge detection.A unified theoretical framework for this scheme is established on the transfer function theory,which coincides well with the experimental results.The proposed method offers an easily-switchable multi-functional solution to optical image processing by introducing mechanical degrees of freedom,which may enable emerging applications in computer vision,autonomous driving,and biomedical microscopy.
基金supported by the National Natural Science Foundation of China(NSFC,12173012 and 12473050)the Guangdong Natural Science Funds for Distinguished Young Scholars(2023B1515020049)+2 种基金the Shenzhen Science and Technology Project(JCYJ20240813104805008)the Shenzhen Key Laboratory Launching Project(No.ZDSYS20210702140800001)the Specialized Research Fund for State Key Laboratory of Solar Activity and Space Weather。
文摘The increasing demand for high-resolution solar observations has driven the development of advanced data processing and enhancement techniques for ground-based solar telescopes.This study focuses on developing a python-based package(GT-scopy)for data processing and enhancing for giant solar telescopes,with application to the 1.6 m Goode Solar Telescope(GST)at Big Bear Solar Observatory.The objective is to develop a modern data processing software for refining existing data acquisition,processing,and enhancement methodologies to achieve atmospheric effect removal and accurate alignment at the sub-pixel level,particularly within the processing levels 1.0-1.5.In this research,we implemented an integrated and comprehensive data processing procedure that includes image de-rotation,zone-of-interest selection,coarse alignment,correction for atmospheric distortions,and fine alignment at the sub-pixel level with an advanced algorithm.The results demonstrate a significant improvement in image quality,with enhanced visibility of fine solar structures both in sunspots and quiet-Sun regions.The enhanced data processing package developed in this study significantly improves the utility of data obtained from the GST,paving the way for more precise solar research and contributing to a better understanding of solar dynamics.This package can be adapted for other ground-based solar telescopes,such as the Daniel K.Inouye Solar Telescope(DKIST),the European Solar Telescope(EST),and the 8 m Chinese Giant Solar Telescope,potentially benefiting the broader solar physics community.
基金supported from the Strategic Pioneer Program of the Astronomy Large-Scale Scientific FacilityChinese Academy of Sciences and the Science and Education Integration Funding of University of Chinese Academy of Sciences+9 种基金the supports from the National Key Basic R&D Program of China via 2023YFA1608303the Strategic Priority Research Program of the Chinese Academy of Sciences(XDB0550103)the supports from the Strategic Priority Research Program of the Chinese Academy of Sciences under grant No.XDB0550000the National Natural Science Foundation of China(NSFC,grant Nos.12422303 and12261141690)the supports from the NSFC(grant No.12403024)supports from the NSFC through grant Nos.11988101 and 11933004the Postdoctoral Fellowship Program of CPSF under grant No.GZB20240731the Young Data Scientist Project of the National Astronomical Data Centerthe China Post-doctoral Science Foundation(No.2023M743447)supports from the New Cornerstone Science Foundation through the New Cornerstone Investigator Program and the XPLORER PRIZE。
文摘This paper provides a comprehensive introduction to the mini-Si Tian Real-time Image Processing pipeline(STRIP)and evaluates its operational performance.The STRIP pipeline is specifically designed for real-time alert triggering and light curve generation for transient sources.By applying the STRIP pipeline to both simulated and real observational data of the Mini-Si Tian survey,it successfully identified various types of variable sources,including stellar flares,supernovae,variable stars,and asteroids,while meeting requirements of reduction speed within 5 minutes.For the real observational data set,the pipeline detected one flare event,127 variable stars,and14 asteroids from three monitored sky regions.Additionally,two data sets were generated:one,a real-bogus training data set comprising 218,818 training samples,and the other,a variable star light curve data set with 421instances.These data sets will be used to train machine learning algorithms,which are planned for future integration into STRIP.
文摘Radio interferometric imaging samples visibility data in the spatial frequency domain and then reconstructs the image.Because of the limited number of antennas,the sampling is usually sparse and noisy.Compressed sensingbased on convex optimization is an effective reconstruction method for sparse sampling conditions.The hyperparameter for the l_(1)regularization term is an important parameter that directly affects the quality of the reconstructed image.If its value is too high,the image structure will be missed.If its value is too low,the image will have a low signal-to-noise ratio.The selection of hyperparameters under different levels of image noise is studied in this paper,and solar radio images are used as examples to analyze the optimization results of compressed sensing algorithms under different noise conditions.The simulation results show that when the salt-and-pepper noise density is between 10%and 30%,the compressed sensing algorithm obtains good reconstruction results.Moreover,the optimal hyperparameter value has a linear relationship with the noise density,and the mean squared error of regression is approximately 8.10×10^(-8).
基金Project (10776020) supported by the Joint Foundation of the National Natural Science Foundation of China and China Academy of Engineering Physics
文摘In order to obtain good welding quality, it is necessary to apply quality control because there are many influencing factors in laser welding process. The key to realize welding quality control is to obtain the quality information. Abundant weld quality information is contained in weld pool and keyhole. Aiming at Nd：YAG laser welding of stainless steel, a coaxial visual sensing system was constructed. The images of weld pool and keyhole were obtained. Based on the gray character of weld pool and keyhole in images, an image processing algorithm was designed. The search start point and search criteria of weld pool and keyhole edge were determined respectively.
文摘To restore the sub image in a rosette scanning system and provide target recognition system with a low distorted image, the sub image is processed with morphological filters. Morphological filter can process rosette scanning sub images more effectively. It can restore the original area and shape of an object effectively, and keep the energy information of the object. To process sub images got by a rosette scanning system, morphological filter is more effective than traditional low pass filter.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2026R765),Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Human Activity Recognition(HAR)is a novel area for computer vision.It has a great impact on healthcare,smart environments,and surveillance while is able to automatically detect human behavior.It plays a vital role in many applications,such as smart home,healthcare,human computer interaction,sports analysis,and especially,intelligent surveillance.In this paper,we propose a robust and efficient HAR system by leveraging deep learning paradigms,including pre-trained models,CNN architectures,and their average-weighted fusion.However,due to the diversity of human actions and various environmental influences,as well as a lack of data and resources,achieving high recognition accuracy remain elusive.In this work,a weighted average ensemble technique is employed to fuse three deep learning models:EfficientNet,ResNet50,and a custom CNN.The results of this study indicate that using a weighted average ensemble strategy for developing more effective HAR models may be a promising idea for detection and classification of human activities.Experiments by using the benchmark dataset proved that the proposed weighted ensemble approach outperformed existing approaches in terms of accuracy and other key performance measures.The combined average-weighted ensemble of pre-trained and CNN models obtained an accuracy of 98%,compared to 97%,96%,and 95%for the customized CNN,EfficientNet,and ResNet50 models,respectively.
基金supported by the National Research Foundation of Korea(NRF)grant funded by theKorea government(MSIT)(No.RS-2024-00405278)partially supported by the Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperationfunded by the Ministry of Trade,Industry and Energy(MOTIE,Korea)[Project Name:Jeju Industry-University Convergence District Project for Promoting Industry-Campus Cooperation/Project Number:P0029950].
文摘Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery.However,conventional convolutional neural networks(CNNs)often struggle in complex flood scenarios involving reflections,occlusions,or indistinct boundaries due to limited contextual modeling.To address these challenges,we propose a hybrid flood segmentation framework that integrates a Vision Transformer(ViT)encoder with a U-Net decoder,enhanced by a novel Flood-Aware Refinement Block(FARB).The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms.We evaluate our model on a UAV-acquired flood imagery dataset,demonstrating that the proposed ViTUNet+FARB architecture outperforms existing CNN and Transformer-based models in terms of accuracy and mean Intersection over Union(mIoU).Detailed ablation studies further validate the contribution of each component,confirming that the FARB design significantly enhances segmentation quality.To its better performance and computational efficiency,the proposed framework is well-suited for flood monitoring and disaster response applications,particularly in resource-constrained environments.
基金The Major Science and Technology Special Project of Xinjiang Uygur Autonomous Region of China“Research,development,and integrated promotion of technologies for enhancing quality and efficiency across the entire industrial chain of Xinjiang honeydew melons”(2024A02007).
文摘Globally,grape cultivation spans vast areas and achieves substantial yields,making grapes and related industries vital economic pillars for many nations.In grape production,efficient and precise management during key growth stages is essential for enhancing both yield and quality.In view of the problems that during the grape inflorescences and young fruits stage,the targets are small in size,easily obscured by branches and leaves,and highly similar in color to the background,resulting in poor recognition performance of existing detection methods in complex natural environments,which in turn restricts the application of precision spraying technology.This paper establishes a dedicated dataset for grape inflorescences and young fruits in Xinjiang and proposes an improved lightweight detection model,YOLOv8-FCD.The model incorporates a PConv-based C2f_Faster module to reduce parameter count and computational complexity,replaces the original upsampling method with the CARAFE module to enhance feature extraction capability,and introduces the Detect_SEAM detection head to improve recognition accuracy under occlusion and small-target conditions.Experimental results show that the YOLOv8-FCD model achieves a detection precision(P)of 93.7%and a recall(R)of 87.3%,with a mean average precision(mAP)of 94.6%.Compared to the original YOLOv8n model,P improved by 8.2%,mAP increased by 2.6%,and the model size is reduced to 85.71%of the original.This model provides effective technical support for the identification of grape inflorescences and young fruits in intelligent spraying for plant protection.
基金supported in part by the National Natural Science Foundation of China under Grants 62101346 and 62301330the Guangdong Basic and Applied Basic Research Foundation under Grants 2021A1515011702 and 2022A1515110101+1 种基金the Shenzhen Science and Technology Programme under Grants JCYJ20240813141358076 and 20231121103807001the Guangdong Provincial Key Laboratory under Grant 2023B1212060076.
文摘Although Transformer-based image restoration methods have demonstrated impressive performance,existing Transformers still insufficiently exploit multiscale information.Previous non-Transformer-based studies have shown that incorporating multiscale features is crucial for improving restoration results.In this paper,we propose a multiscale Transformer(MST)that captures cross-scale attention among tokens,thereby effectively leveraging the multiscale patch recurrence prior of natural images.Furthermore,we introduce a channel-gate feed-forward network(CGFN)to enhance inter-channel information aggregation and reduce channel redundancy.To simultaneously utilise global,local and multiscale features,we design a multitype feature integration block(MFIB).Extensive experiments on both image super-resolution and HEVC compressed video artefact reduction demonstrate that the proposed MST achieves state-of-the-art performance.Ablation studies further verify the effectiveness of each proposed module.
基金supported in part by the Technical Service for the Development and Application of an Intelligent Visual Management Platformfor Expressway Construction Progress Based on BIM Technology(grant NO.JKYZLX-2023-09)in partby the Technical Service for the Development of an Early Warning Model in the Research and Application of Key Technologies for Tunnel Operation Safety Monitoring and Early Warning Based on Digital Twin(grant NO.JK-S02-ZNGS-202412-JISHU-FA-0035)sponsored by Yunnan Transportation Science Research Institute Co.,Ltd.
文摘With the rapid development of transportation infrastructure,ensuring road safety through timely and accurate highway inspection has become increasingly critical.Traditional manual inspection methods are not only time-consuming and labor-intensive,but they also struggle to provide consistent,high-precision detection and realtime monitoring of pavement surface defects.To overcome these limitations,we propose an Automatic Recognition of PavementDefect(ARPD)algorithm,which leverages unmanned aerial vehicle(UAV)-based aerial imagery to automate the inspection process.The ARPD framework incorporates a backbone network based on the Selective State Space Model(S3M),which is designed to capture long-range temporal dependencies.This enables effective modeling of dynamic correlations among redundant and often repetitive structures commonly found in road imagery.Furthermore,a neck structure based on Semantics and Detail Infusion(SDI)is introduced to guide cross-scale feature fusion.The SDI module enhances the integration of low-level spatial details with high-level semantic cues,thereby improving feature expressiveness and defect localization accuracy.Experimental evaluations demonstrate that theARPDalgorithm achieves a mean average precision(mAP)of 86.1%on a custom-labeled pavement defect dataset,outperforming the state-of-the-art YOLOv11 segmentation model.The algorithm also maintains strong generalization ability on public datasets.These results confirm that ARPD is well-suited for diverse real-world applications in intelligent,large-scale highway defect monitoring and maintenance planning.
基金supported by National Natural Science Foundation of China(U1909201,62206062).
文摘Clouds are one of the leading causes of sun shading,which reduces the direct horizontal irradiance and curtails the photovoltaic(PV)power.It is critical to estimate cloud cover to accurately predict PV generation within a very short horizon(second/minute).To achieve the precise forecasting of cloud cover,an image preprocessing method based on total-sky images is proposed to remove the interference and address the image edge distortion issue.An optimal threshold estimation method is further designed to achieve higher cloud identification precision.Considering the cloud's meteorological properties,a random hypersurface model(RHM)based on the Gaussian mixture probability hypothesis density(GM-PHD)filter is applied to track the cloud.The GM-PHD can track the rotation and diffusion of clouds,which helps to estimate sun-cloud collision.Furthermore,a hybrid autoregressive integrated moving average(ARIMA)and backpropagation(BP)neural network-based model is applied for intra-hour PV power forecasting.The experiment results demonstrate that the proposed cloud-tracking-based PV power forecasting model can capture the ramp behavior of PV power,improving forecasting precision.
