Context-aware computing is a new mode originated from ubiquitous computing.Its emergence brings a substantial change to traditional computing and related service.Image is a pervasive tool for context awareness.A large...Context-aware computing is a new mode originated from ubiquitous computing.Its emergence brings a substantial change to traditional computing and related service.Image is a pervasive tool for context awareness.A large number of applications are developed based on images analysis.In this paper,an image acquisition system is presented for agricultural context-aware computing.The potential use of the system includes production evaluation,precise management and assistant control.The system includes four modules:the camera system,the control system,mechanism,and communication.The system can be easily installed in target crop fields.The camera system is composed of a binocular stereo camera and a color camera.Two cubic images and a corresponding texture image are collected for each plant in the process of data acquisition.An accessorial software system is developed to control and manage the capture system.Experiments show that the presented system is effective for image acquisition of agricultural context-aware computing.展开更多
Acquiring deep-space images with high spatial resolution and sensitivity is important for space-debris surveillance and early warning. We propose a novel computational imaging (CI) method for high-sensitivity image ...Acquiring deep-space images with high spatial resolution and sensitivity is important for space-debris surveillance and early warning. We propose a novel computational imaging (CI) method for high-sensitivity image acquisition in this letter. The proposed approach introduces CI into image formation. The proposed capturing process conducts minor modifications for cameras to encode more desirable information during capture, which is practical for hardware implementation. The latent image is reconstructed by formulating a recovery problem into an optimization problem, which is solved with iteratively reweighted least square technique. The experimental results clearly show the effectiveness of the proposed method.展开更多
Picture archiving and communication system (PACS) has played an important role in hospital and developed rapidly in recent years. It is an important part of PACS architecture that X-ray video output connects with PACS...Picture archiving and communication system (PACS) has played an important role in hospital and developed rapidly in recent years. It is an important part of PACS architecture that X-ray video output connects with PACS. In this paper, a method to digitize the video signals of X-ray facility is introduced. By means of the video capture card, we can acquire digital medical images from X-ray facility. The American College of Radiology (ACR) and the National Electrical Manufacturers Association (NEMA) developed a standard for Digital Imaging and Communications in Medicine (DICOM), this DICOM standard introduces a rule of medical image conversion from conventional format to DICOM one. According to abovementioned standard, X-ray video signals can be connected to PACS easily. This project has been applied in some hospitals successfully and there is satisfied result. Key words image acquisition - image compression - format conversion - DICOM - PACS CLC number TP 391 Foundation item: Supported by the Enterprise Innovation Foundation of Wuhan (WS(2001)14)Biography: ZHOU Li (1977-), male, Master, research direction: microelectronics and solid electronics.展开更多
In this work, we propose an approach for the separation of coumarins from thin-layer morphological segmentation based on the acquisition of multicomponent images integrating different types of coumarins. The first ste...In this work, we propose an approach for the separation of coumarins from thin-layer morphological segmentation based on the acquisition of multicomponent images integrating different types of coumarins. The first step is to make a segmentation by region, by thresholding, by contour, etc. of each component of the digital image. Then, we proceeded to the calculations of parameters of the regions such as the color standard deviation, the color entropy, the average color of the pixels, the eccentricity from an algorithm on the matlab software. The mean color values at<sub>R</sub> = 91.20 in red, at<sub>B</sub> = 213.21 in blue showed the presence of samidin in the extract. The color entropy values H<sub>G</sub> = 5.25 in green and H<sub>B</sub> = 4.04 in blue also show the presence of visnadine in the leaves of Desmodium adscendens. These values are used to consolidate the database of separation and discrimination of the types of coumarins. The relevance of our coumarin separation or coumarin recognition method has been highlighted compared to other methods, such as the one based on the calculation of frontal ratios which cannot discriminate between two coumarins having the same frontal ratio. The robustness of our method is proven with respect to the separation and identification of some coumarins, in particular samidin and anglicine.展开更多
With the continuous development of science and technology,artificial intelligence(AI)is coming into our lives and changing our lives.Since China entered the aging society in 2000,the degree of population aging has dee...With the continuous development of science and technology,artificial intelligence(AI)is coming into our lives and changing our lives.Since China entered the aging society in 2000,the degree of population aging has deepened.Comprehensive geriatric assessment(CGA)is now the accepted gold standard for the care of older people in hospitals.However,some problems limit the clinical application,such as complexity and time consuming.Therefore,by analyzing previous studies,we summarize some existing AI tools in order to find a more optimized assessment tool to complete the entire CGA process.展开更多
Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of ...Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of an embedded ARM system and one array of 16 micro-image sensors. The system achieves the synchronization of captured photos in 10 ms,as well as 10 f /s video capture. The software architecture includes the TCP /IP protocol,video capture procedures in"Poll/Read"or"video streaming"modes,thread pool monitoring in multi-threading mutex,synchronization control with the"event""mutex signal"and"critical region"functions,and a synthetic image algorithm characterized by its portability,modularity,and remote transmission. The panoramic imaging system is expected to be a vision sensor for mobile robotics.展开更多
Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native...Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native plants.The accurate and efficient classification of weed seeds is important for the effective management and control of weeds.However,classification remains mainly dependent on destructive sampling-based manual inspection,which has a high cost and rather low flux.We considered that this problem could be solved using a nondestructive intelligent image recognition method.First,on the basis of the establishment of the image acquisition system for weed seeds,images of single weed seeds were rapidly and completely segmented,and a total of 47696 samples of 140 species of weed seeds and foreign materials remained.Then,six popular and novel deep Convolutional Neural Network(CNN)models are compared to identify the best method for intelligently identifying 140 species of weed seeds.Of these samples,33600 samples are randomly selected as the training dataset for model training,and the remaining 14096 samples are used as the testing dataset for model testing.AlexNet and GoogLeNet emerged from the quantitative evaluation as the best methods.AlexNet has strong classification accuracy and efficiency(low time consumption),and GoogLeNet has the best classification accuracy.A suitable CNN model for weed seed classification could be selected according to specific identification accuracy requirements and time costs of applications.This research is beneficial for developing a detection system for weed seeds in various applications.The resolution of taxonomic issues and problems associated with the identi-fication of these weed seeds may allow for more effective management and control.展开更多
In strip surface quality inspection systems based on the machine vision detection technology ,image quality is a key factor affecting the final detection performance. Composite imaging methods, such as bright and dark...In strip surface quality inspection systems based on the machine vision detection technology ,image quality is a key factor affecting the final detection performance. Composite imaging methods, such as bright and dark field imaging or reflection and transmission imaging, can reveal more information by emphasizing different image aspects. Defect detection rates and defect recognition accuracy can be improved by integrating and matching information from different image acquisition settings. Practical application shows that transmission and reflection composite imaging can improve the imaging quality of penetrative defects, while bright and dark field composite imaging can enhance imaging of defects such as color deviation and stains.展开更多
Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but i...Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but in more traditional fields like medical physics,the adoption of AI is still at an early stage.Though AI is anticipated to be better than human in certain tasks,with the rapid growth of AI,there is increasing concerns for its usage.The focus of this paper is on the current landscape and potential future applications of artificial intelligence in medical physics and radiotherapy.Topics on AI for image acquisition,image segmentation,treatment delivery,quality assurance and outcome prediction will be explored as well as the interaction between human and AI.This will give insights into how we should approach and use the technology for enhancing the quality of clinical practice.展开更多
This paper expounds the effect of"Qi"on human body by constructing the model of Qi,classifies the parts according to the category of Yin and Yang on the coordinate frame of 5 models of Yin and Yang,and compa...This paper expounds the effect of"Qi"on human body by constructing the model of Qi,classifies the parts according to the category of Yin and Yang on the coordinate frame of 5 models of Yin and Yang,and compares each kind of parts according to the normal image state of human body.with the running direction of integer instead of Qi,the number of Qi in each part is calculated by the method of modern number theory,and the development and changes of human physiology and diseases are explained by"Qi".To explore the Trasitional Chinese Medicine treatment method of"the morbid Qi state of the human body adjusts the qi mode,the direction of qi operation and the intensity of Qi by means of medicinal taste and acupuncture,and returns to the normal state of qi balance mode in the direction of operation".展开更多
Ferrograph-based wear debris analysis(WDA)provides significant information for wear fault analysis of mechanical equipment.After decades of offline application,this conventional technology is being driven by the onlin...Ferrograph-based wear debris analysis(WDA)provides significant information for wear fault analysis of mechanical equipment.After decades of offline application,this conventional technology is being driven by the online ferrograph sensor for real-time wear state monitoring.However,online ferrography has been greatly limited by the low imaging quality and segmentation accuracy of particle chains when analyzing degraded lubricant oils in practical applications.To address this issue,an integrated optimization method is developed that focuses on two aspects:the structural re-design of the online ferrograph sensor and the intelligent segmentation of particle chains.For enhancing the imaging quality of wear particles,the magnetic pole of the online ferrograph sensor is optimized to enable the imaging system directly observe wear particles without penetrating oils.Furthermore,a light source simulation model is established based on the light intensity distribution theory,and the LED installation parameters are determined for particle illumination uniformity in the online ferrograph sensor.On this basis,a Mask-RCNN-based segmentation model of particle chains is constructed by specifically establishing the region of interest(ROI)generation layer and the ROI align layer for the irregular particle morphology.With these measures,a new online ferrograph sensor is designed to enhance the image acquisition and information extraction of wear particles.For verification,the developed sensor is tested to collect particle images from different degraded oils,and the images are further handled with the Mask-RCNN-based model for particle feature extraction.Experimental results reveal that the optimized online ferrography can capture clear particle images even in highly-degraded lubricant oils,and the illumination uniformity reaches 90%in its imaging field.Most importantly,the statistical accuracy of wear particles has been improved from 67.2%to 94.1%.展开更多
In order to pay more attention to the quality of construction concrete and accurately judge whether concrete material meets the standard,a nondestructive testing algorithm of building concrete material defects based o...In order to pay more attention to the quality of construction concrete and accurately judge whether concrete material meets the standard,a nondestructive testing algorithm of building concrete material defects based on machine learning is proposed.Through the ray tracing algorithm of Snell’s theorem,the shortest path between two random punctuation marks of building concrete is calculated.The original coordinate system and grid size were set,the trend and length of the line in the grid were calculated,and the coordinates between the grid corner points and the transmitting probe were calculated so as to obtain the position of the intermediate refractive points of the two probes.Finally,the vector dot product of the local defects is obtained by the optimal hyperplane calculation of the binary classification in the support vector machine.Experimental results show that the proposed method has the advantages of high precision.展开更多
A crop monitoring system was developed to nondestructively monitor the crop growth status in the field.With a two channel multispectral camera with one lens,controlling platform,wireless remote control module and cont...A crop monitoring system was developed to nondestructively monitor the crop growth status in the field.With a two channel multispectral camera with one lens,controlling platform,wireless remote control module and control software,the system was able to synchronously acquire visible image(red(R),green(G),blue(B):400-700 nm)and near-infrared(NIR)image(760-1000 nm).The tomato seedlings multi-spectral images collection experiment in the greenhouse was conducted by using the developed system from the seeding stage to fruiting stage.More than 240 couples of tomato seedlings pictures were acquired with the Soil and Plant Analyzer Development(SPAD)value measured at the same time.The obtained images were available to process,and some vegetation indexes,such as normalized difference vegetation index(NDVI),ratio vegetation index(RVI)and normalized difference green index(NDGI),were calculated.Considering the SPAD value and the correlation coefficient between SPAD and other parameters in different fertilization treatments,the multiple linear regressions(MLR)model for estimating tomato seedlings chlorophyll content was built based on the average gray value in red,green,blue and NIR,vegetable indexes,NDVI,RVI and NDGI in the 33.3%(N1),66.6%(N2),and 100%(N3)nutrient levels during seeding stage and blossom and fruit stage.The R2 of the model is 0.88.The results revealed that the developed crop monitoring system provided a feasible tool to detect the growth status of tomato.More filed experiments and multi-spectral image analysis will be investigated to evaluate the crop growth status in the near future.展开更多
High speed pseudorandom modulation and photon counting techniques are applied to a three-dimensional imaging lidar system.The specific structure and working principle of the lidar system is described.The actual detect...High speed pseudorandom modulation and photon counting techniques are applied to a three-dimensional imaging lidar system.The specific structure and working principle of the lidar system is described.The actual detector efficiency of a single-photon detector in an imaging system is discussed,and the result shows that a variety of reasons lead to the decrease in detection efficiency.A series of ranging and imaging experiments are conducted,and a series of high-resolution three-dimensional images and a distance value of 1200 m of noncooperative targets are acquired.展开更多
A very high frame rate camera is designed based on an innovative CCD driving method. The CCD driving method is mainly implemented on frame transfer CCDs. Asynchronous drive timing sequences are applied in the image an...A very high frame rate camera is designed based on an innovative CCD driving method. The CCD driving method is mainly implemented on frame transfer CCDs. Asynchronous drive timing sequences are applied in the image and storage section of the CCDs. Several rows of the charge in the image section are binned onto the same row in the storage section, and there are the same number of images to be stored in the storage section before they are read out. Based on the new driving method, the frame transfer CCDs can work at a very high frame rate in acquiring burst images though the reading speed remains at a lower level. A very high frame rate camera is designed in this paper. The innovative CCD driving method is mainly of concern. An e2v’s CCD60 is adopted in the camera system, whose full size resolution is 128×128, and the up most frame rate is 1000 Hz in the conventional CCD driving method. By using the presented method, the CCD60 based imager is capable of operating at up to 40000 frames per second (fps) at a recognizable resolution of 128×32. Comparing cameras using traditional binning and region of interest technologies, the frame rate is normally less than 5000 fps while the resolution is only 32×32 left.展开更多
Conventional semi-active laser guidance takes advantage of the laser designator to illuminate the stable and uniform laser spot on target precisely.The seeker collects the reflected light by a quadrant detector and ou...Conventional semi-active laser guidance takes advantage of the laser designator to illuminate the stable and uniform laser spot on target precisely.The seeker collects the reflected light by a quadrant detector and outputs the relative position information to guide the missile to the illuminating laser spot.However,the designation and guidance accuracy could be jeopardized by the randomly drifting of laser spot caused by the instability of designation platform and air turbulence.In this work,ghost imaging technique is adapted to a quadrant detector semi-active seeker by utilizing structured illumination on the target.With a series of structured illumination masks,the signals from the quadrant detector are multiplexed to perform calculation of the target relative position as well as image reconstruction of the illuminated area simultaneously.Automatic target recognition methods could be further applied to the reconstructed image to calculate the designating error and correct the guidance.The results of simulation and experiment demonstrate that the proposed method could improve the guidance accuracy in many circumstances which would lead to attacking deviation if conventional semi-active laser guidance is used.展开更多
Face-centered orthorhombic(FCO) sampling can be implemented more easily on CMOS image sensors than on other video acquisition devices.The sampling efficiency of FCO is the highest among all threedimensional(3D) sa...Face-centered orthorhombic(FCO) sampling can be implemented more easily on CMOS image sensors than on other video acquisition devices.The sampling efficiency of FCO is the highest among all threedimensional(3D) sampling schemes.However,interpolation of FCO-sampled data is inevitable in bridging human perception and machine-vision algorithms.In this letter,the concept of motion compensation is borrowed from deinterlacing,which displays interlaced videos on progressively scanned devices.The combination of motion estimation based on intrafield interpolated frames and motion-compensated interfield interpolation is found to provide the best performance by evaluating different combinations of motion estimation and interpolation.展开更多
3D imaging techniques such as computed tomography,ultrasonography,and magnetic resonance imaging usually combine many scans computationally.Here,we report a 3D imaging approach using an optical-laser diffraction micro...3D imaging techniques such as computed tomography,ultrasonography,and magnetic resonance imaging usually combine many scans computationally.Here,we report a 3D imaging approach using an optical-laser diffraction microscope with two different wavelength lasers in the same orientation.A double-layered sample constructed of silica spheres is used for coherent diffraction imaging;with two lasers at 543 and 432 nm.The diffraction patterns obtained using a planar detector at a high numerical a pert are arc projected onto the Ewald spheres.3D images of the double-layered sample are successfully reconstructed from the two-color spherical diffraction patterns.展开更多
In this Letter,a method for shape visualization of small objects(microscopic)in the form of a hologram is presented.It consists of a standard optical set-up for small object registration(i.e.,stereoscopic or biologica...In this Letter,a method for shape visualization of small objects(microscopic)in the form of a hologram is presented.It consists of a standard optical set-up for small object registration(i.e.,stereoscopic or biological microscope).The focus stacking technique is used to obtain a series of images with increased depth of field and on them a shape reconstruction procedure(structure from motion,SfM)is made.With use of a dense cloud of points,a sequence of parallax-related images suitable for Geola’s digital holographic printing is generated.The holographic printer produces single-parallax holographic(full three-dimensional)images of real or virtual objects.展开更多
The evaluation of regional cerebral vascular reserve (rCVR) with single-photon emission computed tomography (SPECT) is useful for predicting cerebral hyperperfusion following carotid artery stenting (CAS) and ca...The evaluation of regional cerebral vascular reserve (rCVR) with single-photon emission computed tomography (SPECT) is useful for predicting cerebral hyperperfusion following carotid artery stenting (CAS) and carotidendarterectomy (CEA).展开更多
基金National High Technology R&D Program(“863”Program)of China(Grant No.2013AA102404-02)National Natural Science Foundation of China(Grant No.31171454,61300079)+1 种基金Beijing Municipal Natural Science Foundation(Grant No.4132028)Special Fund for S&T Innovation of Beijing Academy of Agriculture,and Forestry Sciences Grant(No.KJCX201204007).
文摘Context-aware computing is a new mode originated from ubiquitous computing.Its emergence brings a substantial change to traditional computing and related service.Image is a pervasive tool for context awareness.A large number of applications are developed based on images analysis.In this paper,an image acquisition system is presented for agricultural context-aware computing.The potential use of the system includes production evaluation,precise management and assistant control.The system includes four modules:the camera system,the control system,mechanism,and communication.The system can be easily installed in target crop fields.The camera system is composed of a binocular stereo camera and a color camera.Two cubic images and a corresponding texture image are collected for each plant in the process of data acquisition.An accessorial software system is developed to control and manage the capture system.Experiments show that the presented system is effective for image acquisition of agricultural context-aware computing.
基金supported by the National Natural Science Foundation Key Project(No.61231016)theNational Natural Science Foundation of China Youth Science Fund Project(No.61301193)
文摘Acquiring deep-space images with high spatial resolution and sensitivity is important for space-debris surveillance and early warning. We propose a novel computational imaging (CI) method for high-sensitivity image acquisition in this letter. The proposed approach introduces CI into image formation. The proposed capturing process conducts minor modifications for cameras to encode more desirable information during capture, which is practical for hardware implementation. The latent image is reconstructed by formulating a recovery problem into an optimization problem, which is solved with iteratively reweighted least square technique. The experimental results clearly show the effectiveness of the proposed method.
文摘Picture archiving and communication system (PACS) has played an important role in hospital and developed rapidly in recent years. It is an important part of PACS architecture that X-ray video output connects with PACS. In this paper, a method to digitize the video signals of X-ray facility is introduced. By means of the video capture card, we can acquire digital medical images from X-ray facility. The American College of Radiology (ACR) and the National Electrical Manufacturers Association (NEMA) developed a standard for Digital Imaging and Communications in Medicine (DICOM), this DICOM standard introduces a rule of medical image conversion from conventional format to DICOM one. According to abovementioned standard, X-ray video signals can be connected to PACS easily. This project has been applied in some hospitals successfully and there is satisfied result. Key words image acquisition - image compression - format conversion - DICOM - PACS CLC number TP 391 Foundation item: Supported by the Enterprise Innovation Foundation of Wuhan (WS(2001)14)Biography: ZHOU Li (1977-), male, Master, research direction: microelectronics and solid electronics.
文摘In this work, we propose an approach for the separation of coumarins from thin-layer morphological segmentation based on the acquisition of multicomponent images integrating different types of coumarins. The first step is to make a segmentation by region, by thresholding, by contour, etc. of each component of the digital image. Then, we proceeded to the calculations of parameters of the regions such as the color standard deviation, the color entropy, the average color of the pixels, the eccentricity from an algorithm on the matlab software. The mean color values at<sub>R</sub> = 91.20 in red, at<sub>B</sub> = 213.21 in blue showed the presence of samidin in the extract. The color entropy values H<sub>G</sub> = 5.25 in green and H<sub>B</sub> = 4.04 in blue also show the presence of visnadine in the leaves of Desmodium adscendens. These values are used to consolidate the database of separation and discrimination of the types of coumarins. The relevance of our coumarin separation or coumarin recognition method has been highlighted compared to other methods, such as the one based on the calculation of frontal ratios which cannot discriminate between two coumarins having the same frontal ratio. The robustness of our method is proven with respect to the separation and identification of some coumarins, in particular samidin and anglicine.
基金supported by the Foundation of Aerospace Center Hospital(No.YN202107)the Foundation of Aerospace Medical Health Technology Group(No.2021YK02)。
文摘With the continuous development of science and technology,artificial intelligence(AI)is coming into our lives and changing our lives.Since China entered the aging society in 2000,the degree of population aging has deepened.Comprehensive geriatric assessment(CGA)is now the accepted gold standard for the care of older people in hospitals.However,some problems limit the clinical application,such as complexity and time consuming.Therefore,by analyzing previous studies,we summarize some existing AI tools in order to find a more optimized assessment tool to complete the entire CGA process.
基金Supported by the National Natural Science Foundation of China(61233014)the China Postdoctoral Science Foundation(2012M5210711,20123218110031)the National Natural Science Major International Cooperation Projects(61161120323)
文摘Inspired by the unique structure of insect compound eyes,a multi-channel image acquisition system is designed to photograph a cylindrical panorama of its surroundings with one shot. The hardware structure consists of an embedded ARM system and one array of 16 micro-image sensors. The system achieves the synchronization of captured photos in 10 ms,as well as 10 f /s video capture. The software architecture includes the TCP /IP protocol,video capture procedures in"Poll/Read"or"video streaming"modes,thread pool monitoring in multi-threading mutex,synchronization control with the"event""mutex signal"and"critical region"functions,and a synthetic image algorithm characterized by its portability,modularity,and remote transmission. The panoramic imaging system is expected to be a vision sensor for mobile robotics.
基金the National Natural Science Foundation for Young Scientists of China(No.31801804)the projects subsidized by the Special Funds for Science Technology Innovation and Industrial Development of Shenzhen Dapeng New District(No.PT202001-06)+1 种基金the Key Research and Development Program of Nanning(No.20192065)Science Foundation of Nanjing Customs District P.R.China(No.2020KJ10).
文摘Weeds are mainly spread by weed seeds being mixed with agricultural and forestry crop seeds,grain,animal hair,and other plant products,and disturb the growing environment of target plants such as crops and wild native plants.The accurate and efficient classification of weed seeds is important for the effective management and control of weeds.However,classification remains mainly dependent on destructive sampling-based manual inspection,which has a high cost and rather low flux.We considered that this problem could be solved using a nondestructive intelligent image recognition method.First,on the basis of the establishment of the image acquisition system for weed seeds,images of single weed seeds were rapidly and completely segmented,and a total of 47696 samples of 140 species of weed seeds and foreign materials remained.Then,six popular and novel deep Convolutional Neural Network(CNN)models are compared to identify the best method for intelligently identifying 140 species of weed seeds.Of these samples,33600 samples are randomly selected as the training dataset for model training,and the remaining 14096 samples are used as the testing dataset for model testing.AlexNet and GoogLeNet emerged from the quantitative evaluation as the best methods.AlexNet has strong classification accuracy and efficiency(low time consumption),and GoogLeNet has the best classification accuracy.A suitable CNN model for weed seed classification could be selected according to specific identification accuracy requirements and time costs of applications.This research is beneficial for developing a detection system for weed seeds in various applications.The resolution of taxonomic issues and problems associated with the identi-fication of these weed seeds may allow for more effective management and control.
文摘In strip surface quality inspection systems based on the machine vision detection technology ,image quality is a key factor affecting the final detection performance. Composite imaging methods, such as bright and dark field imaging or reflection and transmission imaging, can reveal more information by emphasizing different image aspects. Defect detection rates and defect recognition accuracy can be improved by integrating and matching information from different image acquisition settings. Practical application shows that transmission and reflection composite imaging can improve the imaging quality of penetrative defects, while bright and dark field composite imaging can enhance imaging of defects such as color deviation and stains.
文摘Artificial intelligence(AI)has seen tremendous growth over the past decade and stands to disrupts the medical industry.In medicine,this has been applied in medical imaging and other digitised medical disciplines,but in more traditional fields like medical physics,the adoption of AI is still at an early stage.Though AI is anticipated to be better than human in certain tasks,with the rapid growth of AI,there is increasing concerns for its usage.The focus of this paper is on the current landscape and potential future applications of artificial intelligence in medical physics and radiotherapy.Topics on AI for image acquisition,image segmentation,treatment delivery,quality assurance and outcome prediction will be explored as well as the interaction between human and AI.This will give insights into how we should approach and use the technology for enhancing the quality of clinical practice.
文摘This paper expounds the effect of"Qi"on human body by constructing the model of Qi,classifies the parts according to the category of Yin and Yang on the coordinate frame of 5 models of Yin and Yang,and compares each kind of parts according to the normal image state of human body.with the running direction of integer instead of Qi,the number of Qi in each part is calculated by the method of modern number theory,and the development and changes of human physiology and diseases are explained by"Qi".To explore the Trasitional Chinese Medicine treatment method of"the morbid Qi state of the human body adjusts the qi mode,the direction of qi operation and the intensity of Qi by means of medicinal taste and acupuncture,and returns to the normal state of qi balance mode in the direction of operation".
基金the National Natural Science Foundation of China(Nos.51975455,52105159 and 52275126)the China Postdoctoral Science Foundation(No.2021M702594)the Open Foundation of State Key Laboratory of Compressor Technology(Compressor Technology Laboratory of Anhui Province),No.SKL-YSJ202102.
文摘Ferrograph-based wear debris analysis(WDA)provides significant information for wear fault analysis of mechanical equipment.After decades of offline application,this conventional technology is being driven by the online ferrograph sensor for real-time wear state monitoring.However,online ferrography has been greatly limited by the low imaging quality and segmentation accuracy of particle chains when analyzing degraded lubricant oils in practical applications.To address this issue,an integrated optimization method is developed that focuses on two aspects:the structural re-design of the online ferrograph sensor and the intelligent segmentation of particle chains.For enhancing the imaging quality of wear particles,the magnetic pole of the online ferrograph sensor is optimized to enable the imaging system directly observe wear particles without penetrating oils.Furthermore,a light source simulation model is established based on the light intensity distribution theory,and the LED installation parameters are determined for particle illumination uniformity in the online ferrograph sensor.On this basis,a Mask-RCNN-based segmentation model of particle chains is constructed by specifically establishing the region of interest(ROI)generation layer and the ROI align layer for the irregular particle morphology.With these measures,a new online ferrograph sensor is designed to enhance the image acquisition and information extraction of wear particles.For verification,the developed sensor is tested to collect particle images from different degraded oils,and the images are further handled with the Mask-RCNN-based model for particle feature extraction.Experimental results reveal that the optimized online ferrography can capture clear particle images even in highly-degraded lubricant oils,and the illumination uniformity reaches 90%in its imaging field.Most importantly,the statistical accuracy of wear particles has been improved from 67.2%to 94.1%.
文摘In order to pay more attention to the quality of construction concrete and accurately judge whether concrete material meets the standard,a nondestructive testing algorithm of building concrete material defects based on machine learning is proposed.Through the ray tracing algorithm of Snell’s theorem,the shortest path between two random punctuation marks of building concrete is calculated.The original coordinate system and grid size were set,the trend and length of the line in the grid were calculated,and the coordinates between the grid corner points and the transmitting probe were calculated so as to obtain the position of the intermediate refractive points of the two probes.Finally,the vector dot product of the local defects is obtained by the optimal hyperplane calculation of the binary classification in the support vector machine.Experimental results show that the proposed method has the advantages of high precision.
基金948 Project(No.2011-G32)High Technology Research and Development Research Fund(No.2013AA102303).
文摘A crop monitoring system was developed to nondestructively monitor the crop growth status in the field.With a two channel multispectral camera with one lens,controlling platform,wireless remote control module and control software,the system was able to synchronously acquire visible image(red(R),green(G),blue(B):400-700 nm)and near-infrared(NIR)image(760-1000 nm).The tomato seedlings multi-spectral images collection experiment in the greenhouse was conducted by using the developed system from the seeding stage to fruiting stage.More than 240 couples of tomato seedlings pictures were acquired with the Soil and Plant Analyzer Development(SPAD)value measured at the same time.The obtained images were available to process,and some vegetation indexes,such as normalized difference vegetation index(NDVI),ratio vegetation index(RVI)and normalized difference green index(NDGI),were calculated.Considering the SPAD value and the correlation coefficient between SPAD and other parameters in different fertilization treatments,the multiple linear regressions(MLR)model for estimating tomato seedlings chlorophyll content was built based on the average gray value in red,green,blue and NIR,vegetable indexes,NDVI,RVI and NDGI in the 33.3%(N1),66.6%(N2),and 100%(N3)nutrient levels during seeding stage and blossom and fruit stage.The R2 of the model is 0.88.The results revealed that the developed crop monitoring system provided a feasible tool to detect the growth status of tomato.More filed experiments and multi-spectral image analysis will be investigated to evaluate the crop growth status in the near future.
基金supported by the Innovation Fund(No.CXJJ16M102)the National 973 Program of China (No.613192)
文摘High speed pseudorandom modulation and photon counting techniques are applied to a three-dimensional imaging lidar system.The specific structure and working principle of the lidar system is described.The actual detector efficiency of a single-photon detector in an imaging system is discussed,and the result shows that a variety of reasons lead to the decrease in detection efficiency.A series of ranging and imaging experiments are conducted,and a series of high-resolution three-dimensional images and a distance value of 1200 m of noncooperative targets are acquired.
基金Supported by National Defense Pre-research Foundation
文摘A very high frame rate camera is designed based on an innovative CCD driving method. The CCD driving method is mainly implemented on frame transfer CCDs. Asynchronous drive timing sequences are applied in the image and storage section of the CCDs. Several rows of the charge in the image section are binned onto the same row in the storage section, and there are the same number of images to be stored in the storage section before they are read out. Based on the new driving method, the frame transfer CCDs can work at a very high frame rate in acquiring burst images though the reading speed remains at a lower level. A very high frame rate camera is designed in this paper. The innovative CCD driving method is mainly of concern. An e2v’s CCD60 is adopted in the camera system, whose full size resolution is 128×128, and the up most frame rate is 1000 Hz in the conventional CCD driving method. By using the presented method, the CCD60 based imager is capable of operating at up to 40000 frames per second (fps) at a recognizable resolution of 128×32. Comparing cameras using traditional binning and region of interest technologies, the frame rate is normally less than 5000 fps while the resolution is only 32×32 left.
基金co-supported by National Natural Science Foundation of China(Nos.61922011 and 61675016)the Fundamental Research Funds for the Central Universities。
文摘Conventional semi-active laser guidance takes advantage of the laser designator to illuminate the stable and uniform laser spot on target precisely.The seeker collects the reflected light by a quadrant detector and outputs the relative position information to guide the missile to the illuminating laser spot.However,the designation and guidance accuracy could be jeopardized by the randomly drifting of laser spot caused by the instability of designation platform and air turbulence.In this work,ghost imaging technique is adapted to a quadrant detector semi-active seeker by utilizing structured illumination on the target.With a series of structured illumination masks,the signals from the quadrant detector are multiplexed to perform calculation of the target relative position as well as image reconstruction of the illuminated area simultaneously.Automatic target recognition methods could be further applied to the reconstructed image to calculate the designating error and correct the guidance.The results of simulation and experiment demonstrate that the proposed method could improve the guidance accuracy in many circumstances which would lead to attacking deviation if conventional semi-active laser guidance is used.
基金supported by the National Natural Science Foundation of China (Nos. 60877035, 61076023,and 90820002)the National "863" Program of China(Nos. 2011CB933203 and 2011CB933102)
文摘Face-centered orthorhombic(FCO) sampling can be implemented more easily on CMOS image sensors than on other video acquisition devices.The sampling efficiency of FCO is the highest among all threedimensional(3D) sampling schemes.However,interpolation of FCO-sampled data is inevitable in bridging human perception and machine-vision algorithms.In this letter,the concept of motion compensation is borrowed from deinterlacing,which displays interlaced videos on progressively scanned devices.The combination of motion estimation based on intrafield interpolated frames and motion-compensated interfield interpolation is found to provide the best performance by evaluating different combinations of motion estimation and interpolation.
基金supported by the Major State Basic Research Development Program of China(No.2014CB910401)the National Natural Science Foundation of China(Nos.31430031,21390414,and U1332118)
文摘3D imaging techniques such as computed tomography,ultrasonography,and magnetic resonance imaging usually combine many scans computationally.Here,we report a 3D imaging approach using an optical-laser diffraction microscope with two different wavelength lasers in the same orientation.A double-layered sample constructed of silica spheres is used for coherent diffraction imaging;with two lasers at 543 and 432 nm.The diffraction patterns obtained using a planar detector at a high numerical a pert are arc projected onto the Ewald spheres.3D images of the double-layered sample are successfully reconstructed from the two-color spherical diffraction patterns.
文摘In this Letter,a method for shape visualization of small objects(microscopic)in the form of a hologram is presented.It consists of a standard optical set-up for small object registration(i.e.,stereoscopic or biological microscope).The focus stacking technique is used to obtain a series of images with increased depth of field and on them a shape reconstruction procedure(structure from motion,SfM)is made.With use of a dense cloud of points,a sequence of parallax-related images suitable for Geola’s digital holographic printing is generated.The holographic printer produces single-parallax holographic(full three-dimensional)images of real or virtual objects.
文摘The evaluation of regional cerebral vascular reserve (rCVR) with single-photon emission computed tomography (SPECT) is useful for predicting cerebral hyperperfusion following carotid artery stenting (CAS) and carotidendarterectomy (CEA).