Crowd counting is a promising hotspot of computer vision involving crowd intelligence analysis,achieving tremendous success recently with the development of deep learning.However,there have been stillmany challenges i...Crowd counting is a promising hotspot of computer vision involving crowd intelligence analysis,achieving tremendous success recently with the development of deep learning.However,there have been stillmany challenges including crowd multi-scale variations and high network complexity,etc.To tackle these issues,a lightweight Resconnection multi-branch network(LRMBNet)for highly accurate crowd counting and localization is proposed.Specifically,using improved ShuffleNet V2 as the backbone,a lightweight shallow extractor has been designed by employing the channel compression mechanism to reduce enormously the number of network parameters.A light multi-branch structure with different expansion rate convolutions is demonstrated to extract multi-scale features and enlarged receptive fields,where the information transmission and fusion of diverse scale features is enhanced via residual concatenation.In addition,a compound loss function is introduced for training themethod to improve global context information correlation.The proposed method is evaluated on the SHHA,SHHB,UCF-QNRF and UCF_CC_50 public datasets.The accuracy is better than those of many advanced approaches,while the number of parameters is smaller.The experimental results show that the proposed method achieves a good tradeoff between the complexity and accuracy of crowd counting,indicating a lightweight and high-precision method for crowd counting.展开更多
When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ...When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.展开更多
Imaging plates are widely used to detect alpha particles to track information,and the number of alpha particle tracks is affected by the overlapping and fading effects of the track information.In this study,an experim...Imaging plates are widely used to detect alpha particles to track information,and the number of alpha particle tracks is affected by the overlapping and fading effects of the track information.In this study,an experiment and a simulation were used to calibrate the efficiency parameter of an imaging plate,which was used to calculate the grayscale.Images were created by using grayscale,which trained the convolutional neural network to count the alpha tracks.The results demonstrated that the trained convolutional neural network can evaluate the alpha track counts based on the source and background images with a wider linear range,which was unaffected by the overlapping effect.The alpha track counts were unaffected by the fading effect within 60 min,where the calibrated formula for the fading effect was analyzed for 132.7 min.The detection efficiency of the trained convolutional neural network for inhomogeneous ^(241)Am sources(2π emission)was 0.6050±0.0399,whereas the efficiency curve of the photo-stimulated luminescence method was lower than that of the trained convolutional neural network.展开更多
Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and...Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and efficient rice production. In this study, we mainly focus on the precise counting of rice plants in paddy field and design a novel deep learning network, RPNet, consisting of four modules: feature encoder, attention block, initial density map generator, and attention map generator. Additionally, we propose a novel loss function called RPloss. This loss function considers the magnitude relationship between different sub-loss functions and ensures the validity of the designed network. To verify the proposed method, we conducted experiments on our recently presented URC dataset, which is an unmanned aerial vehicle dataset that is quite challenged at counting rice plants. For experimental comparison, we chose some popular or recently proposed counting methods, namely MCNN, CSRNet, SANet, TasselNetV2, and FIDTM. In the experiment, the mean absolute error(MAE), root mean squared error(RMSE), relative MAE(rMAE) and relative RMSE(rRMSE) of the proposed RPNet were 8.3, 11.2, 1.2% and 1.6%, respectively,for the URC dataset. RPNet surpasses state-of-the-art methods in plant counting. To verify the universality of the proposed method, we conducted experiments on the well-know MTC and WED datasets. The final results on these datasets showed that our network achieved the best results compared with excellent previous approaches. The experiments showed that the proposed RPNet can be utilized to count rice plants in paddy fields and replace traditional methods.展开更多
In the process of aquaculture,monitoring the number of fish bait particles is of great significance to improve the growth and welfare of fish.Although the counting method based on onvolutional neural network(CNN)achie...In the process of aquaculture,monitoring the number of fish bait particles is of great significance to improve the growth and welfare of fish.Although the counting method based on onvolutional neural network(CNN)achieve good accuracy and applicability,it has a high amount of parameters and computation,which limit the deployment on resource-constrained hardware devices.In order to solve the above problems,this paper proposes a lightweight bait particle counting method based on shift quantization and model pruning strategies.Firstly,we take corresponding lightweight strategies for different layers to flexibly balance the counting accuracy and performance of the model.In order to deeply lighten the counting model,the redundant and less informative weights of the model are removed through the combination of model quantization and pruning.The experimental results show that the compression rate is nearly 9 times.Finally,the quantization candidate value is refined by introducing a power-of-two addition term,which improves the matches of the weight distribution.By analyzing the experimental results,the counting loss at 3 bit is reduced by 35.31%.In summary,the lightweight bait particle counting model proposed in this paper achieves lossless counting accuracy and reduces the storage and computational overhead required for running convolutional neural networks.展开更多
AIM:To assess the performance of a bespoke software for automated counting of intraocular lens(IOL)glistenings in slit-lamp images.METHODS:IOL glistenings from slit-lamp-derived digital images were counted manually an...AIM:To assess the performance of a bespoke software for automated counting of intraocular lens(IOL)glistenings in slit-lamp images.METHODS:IOL glistenings from slit-lamp-derived digital images were counted manually and automatically by the bespoke software.The images of one randomly selected eye from each of 34 participants were used as a training set to determine the threshold setting that gave the best agreement between manual and automatic grading.A second set of 63 images,selected using randomised stratified sampling from 290 images,were used for software validation.The images were obtained using a previously described protocol.Software-derived automated glistenings counts were compared to manual counts produced by three ophthalmologists.RESULTS:A threshold value of 140 was determined that minimised the total deviation in the number of glistenings for the 34 images in the training set.Using this threshold value,only slight agreement was found between automated software counts and manual expert counts for the validating set of 63 images(κ=0.104,95%CI,0.040-0.168).Ten images(15.9%)had glistenings counts that agreed between the software and manual counting.There were 49 images(77.8%)where the software overestimated the number of glistenings.CONCLUSION:The low levels of agreement show between an initial release of software used to automatically count glistenings in in vivo slit-lamp images and manual counting indicates that this is a non-trivial application.Iterative improvement involving a dialogue between software developers and experienced ophthalmologists is required to optimise agreement.The results suggest that validation of software is necessary for studies involving semi-automatic evaluation of glistenings.展开更多
In this paper, a deep learning-based method is proposed for crowdcountingproblems. Specifically, by utilizing the convolution kernel densitymap, the ground truth is generated dynamically to enhance the featureextracti...In this paper, a deep learning-based method is proposed for crowdcountingproblems. Specifically, by utilizing the convolution kernel densitymap, the ground truth is generated dynamically to enhance the featureextractingability of the generator model. Meanwhile, the “cross stage partial”module is integrated into congested scene recognition network (CSRNet) toobtain a lightweight network model. In addition, to compensate for the accuracydrop owing to the lightweight model, we take advantage of “structuredknowledge transfer” to train the model in an end-to-end manner. It aimsto accelerate the fitting speed and enhance the learning ability of the studentmodel. The crowd-counting system solution for edge computing is alsoproposed and implemented on an embedded device equipped with a neuralprocessing unit. Simulations demonstrate the performance improvement ofthe proposed solution in terms of model size, processing speed and accuracy.The performance on the Venice dataset shows that the mean absolute error(MAE) and the root mean squared error (RMSE) of our model drop by32.63% and 39.18% compared with CSRNet. Meanwhile, the performance onthe ShanghaiTech PartB dataset reveals that the MAE and the RMSE of ourmodel are close to those of CSRNet. Therefore, we provide a novel embeddedplatform system scheme for public safety pre-warning applications.展开更多
Inventory counting is crucial to manufacturing industries in terms of inventory management,production,and procurement planning.Many companies currently require workers to manually count and track the status of materia...Inventory counting is crucial to manufacturing industries in terms of inventory management,production,and procurement planning.Many companies currently require workers to manually count and track the status of materials,which are repetitive and non-value-added activities but incur significant costs to the companies as well as mental fatigue to the employees.This research aims to develop a computer vision system that can automate the material counting activity without applying any marker on the material.The type of material of interest is metal sheet,whose shape is simple,a large rectangular shape,yet difficult to detect.The use of computer vision technology can reduce the costs incurred fromthe loss of high-value materials,eliminate repetitive work requirements for skilled labor,and reduce human error.A computer vision system is proposed and tested on a metal sheet picking process formultiple metal sheet stacks in the storage area by using one video camera.Our results show that the proposed computer vision system can count the metal sheet picks under a real situation with a precision of 97.83%and a recall of 100%.展开更多
The analysis of overcrowded areas is essential for flow monitoring,assembly control,and security.Crowd counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of con...The analysis of overcrowded areas is essential for flow monitoring,assembly control,and security.Crowd counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary actions.The crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test data.In this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd scene.The proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training samples.The decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive field.Five benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.展开更多
By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting ...By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting sort while maintaining the original stability. Compared with the original counting sort, it has a wider scope of application and better time and space efficiency. In addition, the accuracy of the above conclusions can be proved by a large amount of experimental data.展开更多
The fatigue of concrete structures will gradually appear after being subjected to alternating loads for a long time,and the accidents caused by fatigue failure of bridge structures also appear from time to time.Aiming...The fatigue of concrete structures will gradually appear after being subjected to alternating loads for a long time,and the accidents caused by fatigue failure of bridge structures also appear from time to time.Aiming at the problem of degradation of long-span continuous rigid frame bridges due to fatigue and environmental effects,this paper suggests a method to analyze the fatigue degradation mechanism of this type of bridge,which combines long-term in-site monitoring data collected by the health monitoring system(HMS)and fatigue theory.In the paper,the authors mainly carry out the research work in the following aspects:First of all,a long-span continuous rigid frame bridge installed with HMS is used as an example,and a large amount of health monitoring data have been acquired,which can provide efficient information for fatigue in terms of equivalent stress range and cumulative number of stress cycles;next,for calculating the cumulative fatigue damage of the bridge structure,fatigue stress spectrum got by rain flow counting method,S-N curves and damage criteria are used for fatigue damage analysis.Moreover,it was considered a linear accumulation damage through the Palmgren-Miner rule for the counting of stress cycles.The health monitoring data are adopted to obtain fatigue stress data and the rain flow counting method is used to count the amplitude varying fatigue stress.The proposed fatigue reliability approach in the paper can estimate the fatigue damage degree and its evolution law of bridge structures well,and also can help bridge engineers do the assessment of future service duration.展开更多
4H-SiC single photon counting avalanche photodiodes(SPADs)are prior devices for weak ultraviolet(UV)signal detection with the advantages of small size,low leakage current,high avalanche multiplication gain,and high qu...4H-SiC single photon counting avalanche photodiodes(SPADs)are prior devices for weak ultraviolet(UV)signal detection with the advantages of small size,low leakage current,high avalanche multiplication gain,and high quantum efficiency,which benefit from the large bandgap energy,high carrier drift velocity and excellent physical stability of 4 H-SiC semiconductor material.UV detectors are widely used in many key applications,such as missile plume detection,corona discharge,UV astronomy,and biological and chemical agent detection.In this paper,we will describe basic concepts and review recent results on device design,process development,and basic characterizations of 4 H-SiC avalanche photodiodes.Several promising device structures and uniformity of avalanche multiplication are discussed,which are important for achieving high performance of 4 HSiC UV SPADs.展开更多
鉴于失败的DNS查询(failed DNS query)能提供恶意网络活动的证据,以DNS查询失败的数据为切入口,提出一种轻量级的基于Counting Bloom Filter的DNS异常检测方法。该方法使用带语义特征的可逆哈希函数对被查询的域名及发起查询的IP进行快...鉴于失败的DNS查询(failed DNS query)能提供恶意网络活动的证据,以DNS查询失败的数据为切入口,提出一种轻量级的基于Counting Bloom Filter的DNS异常检测方法。该方法使用带语义特征的可逆哈希函数对被查询的域名及发起查询的IP进行快速的聚类和还原。实验结果证明该方法能以较少的空间占用和较快的计算速度有效识别出DNS流量中的异常,适用于僵尸网络、分布式拒绝服务(DDoS)攻击等异常检测的前期筛选和后期验证。展开更多
We demonstrate a photon-counting chirped amplitude modulation(CAM) light detection and ranging(lidar) system incorporating a superconducting nanowire single-photon detector(SNSPD) and operated at a wavelength of 1550 ...We demonstrate a photon-counting chirped amplitude modulation(CAM) light detection and ranging(lidar) system incorporating a superconducting nanowire single-photon detector(SNSPD) and operated at a wavelength of 1550 nm.The distance accuracy of the lidar system was determined by the CAM bandwidth and signal-to-noise ratio(SNR) of an intermediate frequency(IF) signal. Owing to a short dead time(10 ns) and negligible dark count rate(70 Hz) of the SNSPD, the obtained IF signal attained an SNR of 42 d B and the direct distance accuracy was improved to 3 mm when the modulation bandwidth of the CAM signal was 240 MHz and the modulation period was 1 ms.展开更多
A signal chain model of single-bit and multi-bit quanta image sensors(QISs)is established.Based on the proposed model,the photoresponse characteristics and signal error rates of QISs are investigated,and the effects o...A signal chain model of single-bit and multi-bit quanta image sensors(QISs)is established.Based on the proposed model,the photoresponse characteristics and signal error rates of QISs are investigated,and the effects of bit depth,quantum efficiency,dark current,and read noise on them are analyzed.When the signal error rates towards photons and photoelectrons counting are lower than 0.01,the high accuracy photon and photoelectron counting exposure ranges are determined.Furthermore,an optimization method of integration time to ensure that the QIS works in these high accuracy exposure ranges is presented.The trade-offs between pixel area,the mean value of incident photons,and integration time under different illuminance level are analyzed.For the 3-bit QIS with 0.16 e-/s dark current and 0.21 e-r.m.s.read noise,when the illuminance level and pixel area are 1 lux and 1.21μm^(2),or 10000 lux and 0.21μm^(2),the recommended integration time is 8.8 to 30 ms,or 10 to21.3μs,respectively.The proposed method can guide the design and operation of single-bit and multi-bit QISs.展开更多
This study presents an estimation approach to non-life insurance claim counts relating to a specified time. The objective of this study is to estimate the parameters in non-life insurance claim counting process, inclu...This study presents an estimation approach to non-life insurance claim counts relating to a specified time. The objective of this study is to estimate the parameters in non-life insurance claim counting process, including the homogeneous Poisson process (HPP) and the non-homogeneous Poisson process (NHPP) with a bell-shaped intensity. We use the estimating function, the zero mean martingale (ZMM) as a procedure of parameter estimation in the insurance claim counting process. Then, Λ(t) , the compensator of is proposed for the number of claims in the time interval . We present situations through a simulation study of both processes on the time interval . Some examples of the situations in the simulation study are depicted by a sample path relating to its compensator Λ(t). In addition, an example of the claim counting process illustrates the result of the compensator estimate misspecification.展开更多
基金Double First-Class Innovation Research Project for People’s Public Security University of China(2023SYL08).
文摘Crowd counting is a promising hotspot of computer vision involving crowd intelligence analysis,achieving tremendous success recently with the development of deep learning.However,there have been stillmany challenges including crowd multi-scale variations and high network complexity,etc.To tackle these issues,a lightweight Resconnection multi-branch network(LRMBNet)for highly accurate crowd counting and localization is proposed.Specifically,using improved ShuffleNet V2 as the backbone,a lightweight shallow extractor has been designed by employing the channel compression mechanism to reduce enormously the number of network parameters.A light multi-branch structure with different expansion rate convolutions is demonstrated to extract multi-scale features and enlarged receptive fields,where the information transmission and fusion of diverse scale features is enhanced via residual concatenation.In addition,a compound loss function is introduced for training themethod to improve global context information correlation.The proposed method is evaluated on the SHHA,SHHB,UCF-QNRF and UCF_CC_50 public datasets.The accuracy is better than those of many advanced approaches,while the number of parameters is smaller.The experimental results show that the proposed method achieves a good tradeoff between the complexity and accuracy of crowd counting,indicating a lightweight and high-precision method for crowd counting.
文摘When employing penetration ammunition to strike multi-story buildings,the detection methods using acceleration sensors suffer from signal aliasing,while magnetic detection methods are susceptible to interference from ferromagnetic materials,thereby posing challenges in accurately determining the number of layers.To address this issue,this research proposes a layer counting method for penetration fuze that incorporates multi-source information fusion,utilizing both the temporal convolutional network(TCN)and the long short-term memory(LSTM)recurrent network.By leveraging the strengths of these two network structures,the method extracts temporal and high-dimensional features from the multi-source physical field during the penetration process,establishing a relationship between the multi-source physical field and the distance between the fuze and the target plate.A simulation model is developed to simulate the overload and magnetic field of a projectile penetrating multiple layers of target plates,capturing the multi-source physical field signals and their patterns during the penetration process.The analysis reveals that the proposed multi-source fusion layer counting method reduces errors by 60% and 50% compared to single overload layer counting and single magnetic anomaly signal layer counting,respectively.The model's predictive performance is evaluated under various operating conditions,including different ratios of added noise to random sample positions,penetration speeds,and spacing between target plates.The maximum errors in fuze penetration time predicted by the three modes are 0.08 ms,0.12 ms,and 0.16 ms,respectively,confirming the robustness of the proposed model.Moreover,the model's predictions indicate that the fitting degree for large interlayer spacings is superior to that for small interlayer spacings due to the influence of stress waves.
基金supported by the Hunan Provincial Innovation Foundation for Postgraduates (No.QL20210228)the National Natural Science Foundation of China (No.12075112)the National Natural Science Foundation of China (No.12175102).
文摘Imaging plates are widely used to detect alpha particles to track information,and the number of alpha particle tracks is affected by the overlapping and fading effects of the track information.In this study,an experiment and a simulation were used to calibrate the efficiency parameter of an imaging plate,which was used to calculate the grayscale.Images were created by using grayscale,which trained the convolutional neural network to count the alpha tracks.The results demonstrated that the trained convolutional neural network can evaluate the alpha track counts based on the source and background images with a wider linear range,which was unaffected by the overlapping effect.The alpha track counts were unaffected by the fading effect within 60 min,where the calibrated formula for the fading effect was analyzed for 132.7 min.The detection efficiency of the trained convolutional neural network for inhomogeneous ^(241)Am sources(2π emission)was 0.6050±0.0399,whereas the efficiency curve of the photo-stimulated luminescence method was lower than that of the trained convolutional neural network.
基金supported by the National Natural Science Foundation of China (61701260 and 62271266)the Postgraduate Research&Practice Innovation Program of Jiangsu Province (SJCX21_0255)the Postdoctoral Research Program of Jiangsu Province(2019K287)。
文摘Rice is a major food crop and is planted worldwide. Climatic deterioration, population growth, farmland shrinkage, and other factors have necessitated the application of cutting-edge technology to achieve accurate and efficient rice production. In this study, we mainly focus on the precise counting of rice plants in paddy field and design a novel deep learning network, RPNet, consisting of four modules: feature encoder, attention block, initial density map generator, and attention map generator. Additionally, we propose a novel loss function called RPloss. This loss function considers the magnitude relationship between different sub-loss functions and ensures the validity of the designed network. To verify the proposed method, we conducted experiments on our recently presented URC dataset, which is an unmanned aerial vehicle dataset that is quite challenged at counting rice plants. For experimental comparison, we chose some popular or recently proposed counting methods, namely MCNN, CSRNet, SANet, TasselNetV2, and FIDTM. In the experiment, the mean absolute error(MAE), root mean squared error(RMSE), relative MAE(rMAE) and relative RMSE(rRMSE) of the proposed RPNet were 8.3, 11.2, 1.2% and 1.6%, respectively,for the URC dataset. RPNet surpasses state-of-the-art methods in plant counting. To verify the universality of the proposed method, we conducted experiments on the well-know MTC and WED datasets. The final results on these datasets showed that our network achieved the best results compared with excellent previous approaches. The experiments showed that the proposed RPNet can be utilized to count rice plants in paddy fields and replace traditional methods.
基金supported by the National Key Research and Development Program of China(No.2019YFD0901000)。
文摘In the process of aquaculture,monitoring the number of fish bait particles is of great significance to improve the growth and welfare of fish.Although the counting method based on onvolutional neural network(CNN)achieve good accuracy and applicability,it has a high amount of parameters and computation,which limit the deployment on resource-constrained hardware devices.In order to solve the above problems,this paper proposes a lightweight bait particle counting method based on shift quantization and model pruning strategies.Firstly,we take corresponding lightweight strategies for different layers to flexibly balance the counting accuracy and performance of the model.In order to deeply lighten the counting model,the redundant and less informative weights of the model are removed through the combination of model quantization and pruning.The experimental results show that the compression rate is nearly 9 times.Finally,the quantization candidate value is refined by introducing a power-of-two addition term,which improves the matches of the weight distribution.By analyzing the experimental results,the counting loss at 3 bit is reduced by 35.31%.In summary,the lightweight bait particle counting model proposed in this paper achieves lossless counting accuracy and reduces the storage and computational overhead required for running convolutional neural networks.
文摘AIM:To assess the performance of a bespoke software for automated counting of intraocular lens(IOL)glistenings in slit-lamp images.METHODS:IOL glistenings from slit-lamp-derived digital images were counted manually and automatically by the bespoke software.The images of one randomly selected eye from each of 34 participants were used as a training set to determine the threshold setting that gave the best agreement between manual and automatic grading.A second set of 63 images,selected using randomised stratified sampling from 290 images,were used for software validation.The images were obtained using a previously described protocol.Software-derived automated glistenings counts were compared to manual counts produced by three ophthalmologists.RESULTS:A threshold value of 140 was determined that minimised the total deviation in the number of glistenings for the 34 images in the training set.Using this threshold value,only slight agreement was found between automated software counts and manual expert counts for the validating set of 63 images(κ=0.104,95%CI,0.040-0.168).Ten images(15.9%)had glistenings counts that agreed between the software and manual counting.There were 49 images(77.8%)where the software overestimated the number of glistenings.CONCLUSION:The low levels of agreement show between an initial release of software used to automatically count glistenings in in vivo slit-lamp images and manual counting indicates that this is a non-trivial application.Iterative improvement involving a dialogue between software developers and experienced ophthalmologists is required to optimise agreement.The results suggest that validation of software is necessary for studies involving semi-automatic evaluation of glistenings.
文摘In this paper, a deep learning-based method is proposed for crowdcountingproblems. Specifically, by utilizing the convolution kernel densitymap, the ground truth is generated dynamically to enhance the featureextractingability of the generator model. Meanwhile, the “cross stage partial”module is integrated into congested scene recognition network (CSRNet) toobtain a lightweight network model. In addition, to compensate for the accuracydrop owing to the lightweight model, we take advantage of “structuredknowledge transfer” to train the model in an end-to-end manner. It aimsto accelerate the fitting speed and enhance the learning ability of the studentmodel. The crowd-counting system solution for edge computing is alsoproposed and implemented on an embedded device equipped with a neuralprocessing unit. Simulations demonstrate the performance improvement ofthe proposed solution in terms of model size, processing speed and accuracy.The performance on the Venice dataset shows that the mean absolute error(MAE) and the root mean squared error (RMSE) of our model drop by32.63% and 39.18% compared with CSRNet. Meanwhile, the performance onthe ShanghaiTech PartB dataset reveals that the MAE and the RMSE of ourmodel are close to those of CSRNet. Therefore, we provide a novel embeddedplatform system scheme for public safety pre-warning applications.
基金This work was jointly supported by the Excellent Research Graduate Scholarship-EreG Scholarship Program Under the Memorandum of Understanding between Thammasat University and National Science and Technology Development Agency(NSTDA),Thailand[No.MOU-CO-2562-8675]the Center of Excellence in Logistics and Supply Chain System Engineering and Technology(COE LogEn)+1 种基金Sirindhorn International Institute of Technology(SIIT)Thammasat University,Thailand.
文摘Inventory counting is crucial to manufacturing industries in terms of inventory management,production,and procurement planning.Many companies currently require workers to manually count and track the status of materials,which are repetitive and non-value-added activities but incur significant costs to the companies as well as mental fatigue to the employees.This research aims to develop a computer vision system that can automate the material counting activity without applying any marker on the material.The type of material of interest is metal sheet,whose shape is simple,a large rectangular shape,yet difficult to detect.The use of computer vision technology can reduce the costs incurred fromthe loss of high-value materials,eliminate repetitive work requirements for skilled labor,and reduce human error.A computer vision system is proposed and tested on a metal sheet picking process formultiple metal sheet stacks in the storage area by using one video camera.Our results show that the proposed computer vision system can count the metal sheet picks under a real situation with a precision of 97.83%and a recall of 100%.
基金This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(No.2021R1I1A1A01055652).
文摘The analysis of overcrowded areas is essential for flow monitoring,assembly control,and security.Crowd counting’s primary goal is to calculate the population in a given region,which requires real-time analysis of congested scenes for prompt reactionary actions.The crowd is always unexpected,and the benchmarked available datasets have a lot of variation,which limits the trained models’performance on unseen test data.In this paper,we proposed an end-to-end deep neural network that takes an input image and generates a density map of a crowd scene.The proposed model consists of encoder and decoder networks comprising batch-free normalization layers known as evolving normalization(EvoNorm).This allows our network to be generalized for unseen data because EvoNorm is not using statistics from the training samples.The decoder network uses dilated 2D convolutional layers to provide large receptive fields and fewer parameters,which enables real-time processing and solves the density drift problem due to its large receptive field.Five benchmark datasets are used in this study to assess the proposed model,resulting in the conclusion that it outperforms conventional models.
文摘By analyzing the internal features of counting sorting algorithm. Two improvements of counting sorting algorithms are proposed, which have a wide range of applications and better efficiency than the original counting sort while maintaining the original stability. Compared with the original counting sort, it has a wider scope of application and better time and space efficiency. In addition, the accuracy of the above conclusions can be proved by a large amount of experimental data.
文摘The fatigue of concrete structures will gradually appear after being subjected to alternating loads for a long time,and the accidents caused by fatigue failure of bridge structures also appear from time to time.Aiming at the problem of degradation of long-span continuous rigid frame bridges due to fatigue and environmental effects,this paper suggests a method to analyze the fatigue degradation mechanism of this type of bridge,which combines long-term in-site monitoring data collected by the health monitoring system(HMS)and fatigue theory.In the paper,the authors mainly carry out the research work in the following aspects:First of all,a long-span continuous rigid frame bridge installed with HMS is used as an example,and a large amount of health monitoring data have been acquired,which can provide efficient information for fatigue in terms of equivalent stress range and cumulative number of stress cycles;next,for calculating the cumulative fatigue damage of the bridge structure,fatigue stress spectrum got by rain flow counting method,S-N curves and damage criteria are used for fatigue damage analysis.Moreover,it was considered a linear accumulation damage through the Palmgren-Miner rule for the counting of stress cycles.The health monitoring data are adopted to obtain fatigue stress data and the rain flow counting method is used to count the amplitude varying fatigue stress.The proposed fatigue reliability approach in the paper can estimate the fatigue damage degree and its evolution law of bridge structures well,and also can help bridge engineers do the assessment of future service duration.
基金supported in part by National Key R&D Program of China under Grant No. 2016YFB0400902in part by the Priority Academic Program Development of Jiangsu Higher Education Institutions
文摘4H-SiC single photon counting avalanche photodiodes(SPADs)are prior devices for weak ultraviolet(UV)signal detection with the advantages of small size,low leakage current,high avalanche multiplication gain,and high quantum efficiency,which benefit from the large bandgap energy,high carrier drift velocity and excellent physical stability of 4 H-SiC semiconductor material.UV detectors are widely used in many key applications,such as missile plume detection,corona discharge,UV astronomy,and biological and chemical agent detection.In this paper,we will describe basic concepts and review recent results on device design,process development,and basic characterizations of 4 H-SiC avalanche photodiodes.Several promising device structures and uniformity of avalanche multiplication are discussed,which are important for achieving high performance of 4 HSiC UV SPADs.
文摘鉴于失败的DNS查询(failed DNS query)能提供恶意网络活动的证据,以DNS查询失败的数据为切入口,提出一种轻量级的基于Counting Bloom Filter的DNS异常检测方法。该方法使用带语义特征的可逆哈希函数对被查询的域名及发起查询的IP进行快速的聚类和还原。实验结果证明该方法能以较少的空间占用和较快的计算速度有效识别出DNS流量中的异常,适用于僵尸网络、分布式拒绝服务(DDoS)攻击等异常检测的前期筛选和后期验证。
基金Project supported by National Key R&D Program of China(Grant No.2017YFA0304000)the National Natural Science Foundation of China(NSFC)(Grant Nos.61501442 and 61671438)the Joint Research Fund in Astronomy(U1631240)under Cooperative Agreement between the NSFC and Chinese Academy of Sciences(CAS)
文摘We demonstrate a photon-counting chirped amplitude modulation(CAM) light detection and ranging(lidar) system incorporating a superconducting nanowire single-photon detector(SNSPD) and operated at a wavelength of 1550 nm.The distance accuracy of the lidar system was determined by the CAM bandwidth and signal-to-noise ratio(SNR) of an intermediate frequency(IF) signal. Owing to a short dead time(10 ns) and negligible dark count rate(70 Hz) of the SNSPD, the obtained IF signal attained an SNR of 42 d B and the direct distance accuracy was improved to 3 mm when the modulation bandwidth of the CAM signal was 240 MHz and the modulation period was 1 ms.
基金supported by the Tianjin Key Laboratory of Imaging and Sensing Microelectronic Technology。
文摘A signal chain model of single-bit and multi-bit quanta image sensors(QISs)is established.Based on the proposed model,the photoresponse characteristics and signal error rates of QISs are investigated,and the effects of bit depth,quantum efficiency,dark current,and read noise on them are analyzed.When the signal error rates towards photons and photoelectrons counting are lower than 0.01,the high accuracy photon and photoelectron counting exposure ranges are determined.Furthermore,an optimization method of integration time to ensure that the QIS works in these high accuracy exposure ranges is presented.The trade-offs between pixel area,the mean value of incident photons,and integration time under different illuminance level are analyzed.For the 3-bit QIS with 0.16 e-/s dark current and 0.21 e-r.m.s.read noise,when the illuminance level and pixel area are 1 lux and 1.21μm^(2),or 10000 lux and 0.21μm^(2),the recommended integration time is 8.8 to 30 ms,or 10 to21.3μs,respectively.The proposed method can guide the design and operation of single-bit and multi-bit QISs.
文摘This study presents an estimation approach to non-life insurance claim counts relating to a specified time. The objective of this study is to estimate the parameters in non-life insurance claim counting process, including the homogeneous Poisson process (HPP) and the non-homogeneous Poisson process (NHPP) with a bell-shaped intensity. We use the estimating function, the zero mean martingale (ZMM) as a procedure of parameter estimation in the insurance claim counting process. Then, Λ(t) , the compensator of is proposed for the number of claims in the time interval . We present situations through a simulation study of both processes on the time interval . Some examples of the situations in the simulation study are depicted by a sample path relating to its compensator Λ(t). In addition, an example of the claim counting process illustrates the result of the compensator estimate misspecification.