In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and ta...In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and targeted marketing.However,existing computer vision solutions often rely on facial recognition to gather such insights,raising significant privacy and ethical concerns.To address these issues,this paper presents a privacypreserving customer analytics system through two key strategies.First,we deploy a deep learning framework using YOLOv9s,trained on the RCA-TVGender dataset.Cameras are positioned perpendicular to observation areas to reduce facial visibility while maintaining accurate gender classification.Second,we apply AES-128 encryption to customer position data,ensuring secure access and regulatory compliance.Our system achieved overall performance,with 81.5%mAP@50,77.7%precision,and 75.7%recall.Moreover,a 90-min observational study confirmed the system’s ability to generate privacy-protected heatmaps revealing distinct behavioral patterns between male and female customers.For instance,women spent more time in certain areas and showed interest in different products.These results confirm the system’s effectiveness in enabling personalized layout and marketing strategies without compromising privacy.展开更多
To overcome the limitations of low efficiency and reliance on manual processes in the measurement of geometric parameters for bridge prefabricated components,a method based on deep learning and computer vision is deve...To overcome the limitations of low efficiency and reliance on manual processes in the measurement of geometric parameters for bridge prefabricated components,a method based on deep learning and computer vision is developed to identify the geometric parameters.The study utilizes a common precast element for highway bridges as the research subject.First,edge feature points of the bridge component section are extracted from images of the precast component cross-sections by combining the Canny operator with mathematical morphology.Subsequently,a deep learning model is developed to identify the geometric parameters of the precast components using the extracted edge coordinates from the images as input and the predefined control parameters of the bridge section as output.A dataset is generated by varying the control parameters and noise levels for model training.Finally,field measurements are conducted to validate the accuracy of the developed method.The results indicate that the developed method effectively identifies the geometric parameters of bridge precast components,with an error rate maintained within 5%.展开更多
Recent years have witnessed the ever-increasing performance of Deep Neural Networks(DNNs)in computer vision tasks.However,researchers have identified a potential vulnerability:carefully crafted adversarial examples ca...Recent years have witnessed the ever-increasing performance of Deep Neural Networks(DNNs)in computer vision tasks.However,researchers have identified a potential vulnerability:carefully crafted adversarial examples can easily mislead DNNs into incorrect behavior via the injection of imperceptible modification to the input data.In this survey,we focus on(1)adversarial attack algorithms to generate adversarial examples,(2)adversarial defense techniques to secure DNNs against adversarial examples,and(3)important problems in the realm of adversarial examples beyond attack and defense,including the theoretical explanations,trade-off issues and benign attacks in adversarial examples.Additionally,we draw a brief comparison between recently published surveys on adversarial examples,and identify the future directions for the research of adversarial examples,such as the generalization of methods and the understanding of transferability,that might be solutions to the open problems in this field.展开更多
Accurate estimation on the state of health(SOH)is essential for ensuring the safe and reliable operation of batteries.Traditional assessment methods primarily focus on electrical attributes for capacity decay,often ov...Accurate estimation on the state of health(SOH)is essential for ensuring the safe and reliable operation of batteries.Traditional assessment methods primarily focus on electrical attributes for capacity decay,often overlooking the impact of thermal distribution on battery aging.However,thermal effect is a critical factor for degradation process and associated risks throughout their service life.In this paper,we introduce a novel deep learning framework specially designed to estimate the capacity and thermal risks of lithium-ion batteries(LIBs).This model consists of two main components that leverage computer vision technology.One predicts battery capacity by integrating the advantages of thermal and electrical features using a temporal pattern attention(TPA)mechanism,while the other assesses thermal risk by incorporating temperature variation to provide early warnings of potential hazards.An infrared camera is deployed to record temperature evolution of LIBs during the electrochemical process.The thermal heterogeneities are recorded by infrared camera,and the corresponding temperature evolutions are extracted as representative features for analysis.The proposed model demonstrates high accuracy and stability,with an average root mean square error(RMSE)of 0.67% for capacity estimation and accuracy exceeding 93.9% for risk prediction,underscoring the importance of integrating spatial temperature distribution into battery health assessments.This work offers valuable insights for the development of intelligent and robust battery management systems.展开更多
Convolutional neural networks have been widely used for analyzing image data in industry,especially in the oil and gas area.Brazil has an extensive hydrocarbon reserve on its coast and has also benefited from these ne...Convolutional neural networks have been widely used for analyzing image data in industry,especially in the oil and gas area.Brazil has an extensive hydrocarbon reserve on its coast and has also benefited from these neural network models.Image data from petrographic thin section can be essential to provide information about reservoir quality,highlighting important features such as carbonate lithology.However,the automatic identification of lithology in reservoir rocks is still a significant challenge,mainly due to the heterogeneity that is part of the lithologies of the Brazilian pre-salt.Within this context,this work presents an approach using one-class or specialist models to identify four classes of lithology present in reservoir rocks in the Brazilian pre-salt.The proposed methodology had the challenge of dealing with a small number of images for training the neural networks,in addition to the complexity involved in the analyzed data.An auto-machine learning tool called AutoKeras was used to define the hyperparameters of the implemented models.The results found were satisfactory and presented an accuracy greater than 70%for image samples belonging to other wells not seen during the model building,which increases the applicability of the implemented model.Finally,a comparison was made between the proposed methodology and multiple-class models,demonstrating the superiority of one-class models.展开更多
The classification of seedlings is important to ensure the viability of seedlings after transplantation and is acknowledged as a key factor in forestation and environmental improvement. Based on numerous papers on aut...The classification of seedlings is important to ensure the viability of seedlings after transplantation and is acknowledged as a key factor in forestation and environmental improvement. Based on numerous papers on automatic seedling classification (ASC), the seedling grading theory, traditional grading methods, the background and the proceeding of ASC techniques are described. The automation of the measurement of seedling morphological characteristics by photoelectric meters and computer vision is studied, and the automatic methods of the current grading systems are described respectively. And the further researches on ASC by computer vision are proposed.展开更多
Variety identification is important for maize breeding, processing and trade. The computer vision technique has been widely applied to maize variety identification. In this paper, computer vision technique has been su...Variety identification is important for maize breeding, processing and trade. The computer vision technique has been widely applied to maize variety identification. In this paper, computer vision technique has been summarized from the following technical aspects including image acquisition, image processing, characteristic parameter extraction, pattern recognition and programming softwares. In addition, the existing problems during the application of this technique to maize variety identification have also been analyzed and its development tendency is forecasted.展开更多
With the development of image processing technology and computer, computer vision technology has been widely used in the production of agriculture,and has made many important achievements. This paper reviews its-resea...With the development of image processing technology and computer, computer vision technology has been widely used in the production of agriculture,and has made many important achievements. This paper reviews its-research progress on diagnosis of agricultural products, water diagnosis, weed identification,product quality testing and grading, agricultural picking and sorting and other as- pects, and finally put forward its existing problems and prospects for the future.展开更多
Damage detection is a key procedure in maintenance throughout structures′life cycles and post-disaster loss assessment.Due to the complex types of structural damages and the low efficiency and safety of manual detect...Damage detection is a key procedure in maintenance throughout structures′life cycles and post-disaster loss assessment.Due to the complex types of structural damages and the low efficiency and safety of manual detection,detecting damages with high efficiency and accuracy is the most popular research direction in civil engineering.Computer vision(CV)technology and deep learning(DL)algorithms are considered as promising tools to address the aforementioned challenges.The paper aims to systematically summarized the research and applications of DL-based CV technology in the field of damage detection in recent years.The basic concepts of DL-based CV technology are introduced first.The implementation steps of creating a damage detection dataset and some typical datasets are reviewed.CV-based structural damage detection algorithms are divided into three categories,namely,image classification-based(IC-based)algorithms,object detection-based(OD-based)algorithms,and semantic segmentation-based(SS-based)algorithms.Finally,the problems to be solved and future research directions are discussed.The foundation for promoting the deep integration of DL-based CV technology in structural damage detection and structural seismic damage identification has been laid.展开更多
The behavioral responses of a tilapia (Oreochromis niloticus) school to low (0.13 mg/L), moderate (0.79 mg/L) and high (2.65 mg/L) levels of unionized ammonia (UIA) concentration were monitored using a computer vision...The behavioral responses of a tilapia (Oreochromis niloticus) school to low (0.13 mg/L), moderate (0.79 mg/L) and high (2.65 mg/L) levels of unionized ammonia (UIA) concentration were monitored using a computer vision system. The swimming activity and geometrical parameters such as location of the gravity center and distribution of the fish school were calculated continuously. These behavioral parameters of tilapia school responded sensitively to moderate and high UIA concen-tration. Under high UIA concentration the fish activity showed a significant increase (P<0.05), exhibiting an avoidance reaction to high ammonia condition, and then decreased gradually. Under moderate and high UIA concentration the school’s vertical location had significantly large fluctuation (P<0.05) with the school moving up to the water surface then down to the bottom of the aquarium alternately and tending to crowd together. After several hours’ exposure to high UIA level, the school finally stayed at the aquarium bottom. These observations indicate that alterations in fish behavior under acute stress can provide important in-formation useful in predicting the stress.展开更多
The structure, function and working principle of JLUIV-3, which is a new typeof auto-mated guided vehicle (AGV) with computer vision, is described. The white stripe line withcertain width is used as inductive mark for...The structure, function and working principle of JLUIV-3, which is a new typeof auto-mated guided vehicle (AGV) with computer vision, is described. The white stripe line withcertain width is used as inductive mark for JLUIV-3 automated navigation. JULIV-3 can automaticallyrecognize the Arabic numeral codes which mark the multi-branch paths and multi-operation buffers,and autonomously select the correct path for destination. Compared with the traditional AGV, it hasmuch more navigation flexibility and less cost, and provides higher-level intelligence. Theidentification method of navigation path by using neural network and the optimal control method ofthe AGV are introduced in detail.展开更多
In recent years, aquaculture industry in China is developing rapidly, and especially, China has the largest aquaculture area and the most output in the world. In the past, traditional aquaculture mainly depended on ma...In recent years, aquaculture industry in China is developing rapidly, and especially, China has the largest aquaculture area and the most output in the world. In the past, traditional aquaculture mainly depended on manual labour to breed and gain aquatic organisms. However, with the increasing scale of production and the continuous improvement of science and technology, the traditional aquaculture approach has become more and more unsuitable for the development of the times. With the rapid development of computer technology, computer vision technology infiltrates through the traditional aquaculture industry quickly and improves the aquaculture production efficiency .This paper mainly introduces the basic situation of computer vision technology and summarizes the application of computer vision technology in aquaculture industry at home and abroad. The paper concludes with the expectation of application of computer vision in the aquaculture.展开更多
Age-related Macular Degeneration(AMD)and Diabetic Macular Edema(DME)are two com-mon retinal diseases for elder people that may ultimately cause irreversible blindness.Timely and accurate diagnosis is essential for the...Age-related Macular Degeneration(AMD)and Diabetic Macular Edema(DME)are two com-mon retinal diseases for elder people that may ultimately cause irreversible blindness.Timely and accurate diagnosis is essential for the treatment of these diseases.In recent years,computer-aided diagnosis(CAD)has been deeply investigated and effectively used for rapid and early diagnosis.In this paper,we proposed a method of CAD using vision transformer to analyze optical co-herence tomography(OCT)images and to automatically discriminate AMD,DME,and normal eyes.A classification accuracy of 99.69%was achieved.After the model pruning,the recognition time reached 0.010 s and the classification accuracy did not drop.Compared with the Con-volutional Neural Network(CNN)image classification models(VGG16,Resnet50,Densenet121,and EfficientNet),vision transformer after pruning exhibited better recognition ability.Results show that vision transformer is an improved alternative to diagnose retinal diseases more accurately.展开更多
Spodoptera frugiperda(Lepidoptera:Noctuidae)is an important migratory agricultural pest worldwide,which has invaded many countries in the Old World since 2016 and now poses a serious threat to world food security.The ...Spodoptera frugiperda(Lepidoptera:Noctuidae)is an important migratory agricultural pest worldwide,which has invaded many countries in the Old World since 2016 and now poses a serious threat to world food security.The present monitoring and early warning strategies for the fall army worm(FAW)mainly focus on adult population density,but lack an information technology platform for precisely forecasting the reproductive dynamics of the adults.In this study,to identify the developmental status of the adults,we first utilized female ovarian images to extract and screen five features combined with the support vector machine(SVM)classifier and employed male testes images to obtain the testis circular features.Then,we established models for the relationship between oviposition dynamics and the developmental time of adult reproductive organs using laboratory tests.The results show that the accuracy of female ovary development stage determination reached 91%.The mean standard error(MSE)between the actual and predicted values of the ovarian developmental time was 0.2431,and the mean error rate between the actual and predicted values of the daily oviposition quantity was 12.38%.The error rate for the recognition of testis diameter was 3.25%,and the predicted and actual values of the testis developmental time in males had an MSE of 0.7734.A WeChat applet for identifying the reproductive developmental state and predicting reproduction of S.frugiperda was developed by integrating the above research results,and it is now available for use by anyone involved in plant protection.This study developed an automated method for accurately forecasting the reproductive dynamics of S.frugiperda populations,which can be helpful for the construction of a population monitoring and early warning system for use by both professional experts and local people at the county level.展开更多
In textile inspection field,the fabric defect refers to the destruction of the texture structure on the fabric surface.The technology of computer vision makes it possible to detect defects automatically.Firstly,the ov...In textile inspection field,the fabric defect refers to the destruction of the texture structure on the fabric surface.The technology of computer vision makes it possible to detect defects automatically.Firstly,the overall structure of the fabric defect detection system is introduced and some mature detection systems are studied.Then the fabric detection methods are summarized,including structural methods,statistical methods,frequency domain methods,model methods and deep learning methods.In addition,the evaluation criteria of automatic detection algorithms are discussed and the characteristics of various algorithms are analyzed.Finally,the research status of this field is discussed,and the future development trend is predicted.展开更多
Recent advances in artificial intelligence(AI)have sparked a surge in the application of computer vision(CV)in surgical video analysis.Laparoscopic surgery produces a large number of surgical videos,which provides a n...Recent advances in artificial intelligence(AI)have sparked a surge in the application of computer vision(CV)in surgical video analysis.Laparoscopic surgery produces a large number of surgical videos,which provides a new opportunity for improving of CV technology in laparoscopic surgery.AI-based CV techniques may leverage these surgical video data to develop real-time automated decision support tools and surgeon training systems,which shows a new direction in dealing with the shortcomings of laparoscopic surgery.The effectiveness of CV applications in surgical procedures is still under early evaluation,so it is necessary to discuss challenges and obstacles.The review introduced the commonly used deep learning algorithms in CV and described their usage in detail in four application scenes,including phase recognition,anatomy detection,instrument detection and action recognition in laparoscopic surgery.The currently described applications of CV in laparoscopic surgery are limited.Most of the current research focuses on the identification of workflow and anatomical structure,while the identification of instruments and surgical actions is still awaiting further breakthroughs.Future research on the use of CV in laparoscopic surgery should focus on applications in more scenarios,such as surgeon skill assessment and the development of more efficient models.展开更多
The purpose of this study is to develop a standard methodology for measuring the surface free energy (SFE),and its component parts of bamboo fiber materials.The current methods was reviewed to determine the surface te...The purpose of this study is to develop a standard methodology for measuring the surface free energy (SFE),and its component parts of bamboo fiber materials.The current methods was reviewed to determine the surface tension of natural fibers and the disadvantages of techniques used were discussed.Although numerous techniques have been employed to characterize surface tension of natural fibers,it seems that the credibility of results obtained may often be dubious.In this paper,critical surface tension estimates were obtained from computer aided machine vision based measurement.Data were then analyzed by the least squares method to estimate the components of SFE.SFE was estimated by least squares analysis and also by Schultz' method.By using the Fowkes method the polar and disperse fractions of the surface free energy of bamboo fiber materials can be obtained.Strictly speaking,this method is based on a combination of the knowledge of Fowkes theory. SFE is desirable when adhesion is required,and it avoids some of the limitations of existing studies which has been proposed.The calculation steps described in this research are only intended to explain the methods.The results show that the method that only determines SFE as a single parameter may be unable to differentiate adequately between bamboo fiber materials,but it is feasible and very efficient.In order to obtain the maximum performance from the computer aided machine vision based measurement instruments,this measurement should be recommended and kept available for reference.展开更多
Computer vision(CV)is widely expected to be the next big thing in emerging applications.So many heterogeneous architectures for computer vision emerge.However,plenty of data need to be transferred between different st...Computer vision(CV)is widely expected to be the next big thing in emerging applications.So many heterogeneous architectures for computer vision emerge.However,plenty of data need to be transferred between different structures for heterogeneous architecture.The long data transfer delay becomes the mainly problem to limit the processing speed for computer vision applications.For reducing data transfer delay and fasting computer vision applications,a clustered data-driven array processor is proposed.A three-level pipelining processing element is designed which supports two-buffer data flow interface and 8 bits,16 bits,32 bits subtext parallel computation.At the same time,for accelerating transcendental function computation,a four-way shared pipelining transcendental function accelerator is designed,which is based on Y-intercept adjusted piecewise linear segment algorithm.A distributed shared memory structure based on unified addressing is also employed.To verify efficiency of architecture,some image processing algorithms are implemented on proposed architecture.Simultaneously the proposed architecture has been implemented on Xilinx ZC 706 development board.The same circuitry has been synthesized using SMIC 130 nm CMOS technology.The circuitry is able to run at 100 MHz.Area is 26.58 mm2.展开更多
Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable...Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable in weight measurement due to variation in the quantity of water in the respiratory tree and intestinal content of this species.Recently,video survey method has been applied widely in biometric detection on underwater benthos.However,because of the high flexibility of A.japonicus body,video survey method of monitoring is less used in sea cucumber.In this study,we designed a model to evaluate the wet weight of A.japonicus,using machine vision technology combined with a support vector machine(SVM) that can be used infield surveys on the A.japonicus population.Continuous dorsal images of free-moving A.japonicus individuals in seawater were captured,which also allows for the development of images of the core body edge as well as thorn segmentation.Parameters that include body length,body breadth,perimeter and area,were extracted from the core body edge images and used in SVM regression,to predict the weight of A.japonicus and for comparison with a power model.Results indicate that the use of SVM for predicting the weight of 33 A.japonicus individuals is accurate(R^2=0.99) and compatible with the power model(R^2=0.96).The image-based analysis and size-weight regression models in this study may be useful in body weight evaluation of A.japonicus in lab and field study.展开更多
This paper summarized the previous researches about resin emciency of particleboard in the world, and introduced the computer vision (CV) technique on resin effciency. which has the properties of high measuring speed,...This paper summarized the previous researches about resin emciency of particleboard in the world, and introduced the computer vision (CV) technique on resin effciency. which has the properties of high measuring speed, automatic pattern recognition and low environmental requirement. etc. The theory of the CV technique used for resin effciency in particleboard was studied,along with the handling of resined-particle images and the gathering of relative gray image features. Some quantitative parameters describing the resin efficiency of particleboard were established, and the results indicated that the computer vision method on the resin effciency was much better than others and can control the producing of pafticleboard more effect.展开更多
文摘In the competitive retail industry of the digital era,data-driven insights into gender-specific customer behavior are essential.They support the optimization of store performance,layout design,product placement,and targeted marketing.However,existing computer vision solutions often rely on facial recognition to gather such insights,raising significant privacy and ethical concerns.To address these issues,this paper presents a privacypreserving customer analytics system through two key strategies.First,we deploy a deep learning framework using YOLOv9s,trained on the RCA-TVGender dataset.Cameras are positioned perpendicular to observation areas to reduce facial visibility while maintaining accurate gender classification.Second,we apply AES-128 encryption to customer position data,ensuring secure access and regulatory compliance.Our system achieved overall performance,with 81.5%mAP@50,77.7%precision,and 75.7%recall.Moreover,a 90-min observational study confirmed the system’s ability to generate privacy-protected heatmaps revealing distinct behavioral patterns between male and female customers.For instance,women spent more time in certain areas and showed interest in different products.These results confirm the system’s effectiveness in enabling personalized layout and marketing strategies without compromising privacy.
基金The National Natural Science Foundation of China(No.52338011,52378291)Young Elite Scientists Sponsorship Program by CAST(No.2022-2024QNRC0101).
文摘To overcome the limitations of low efficiency and reliance on manual processes in the measurement of geometric parameters for bridge prefabricated components,a method based on deep learning and computer vision is developed to identify the geometric parameters.The study utilizes a common precast element for highway bridges as the research subject.First,edge feature points of the bridge component section are extracted from images of the precast component cross-sections by combining the Canny operator with mathematical morphology.Subsequently,a deep learning model is developed to identify the geometric parameters of the precast components using the extracted edge coordinates from the images as input and the predefined control parameters of the bridge section as output.A dataset is generated by varying the control parameters and noise levels for model training.Finally,field measurements are conducted to validate the accuracy of the developed method.The results indicate that the developed method effectively identifies the geometric parameters of bridge precast components,with an error rate maintained within 5%.
基金Supported by the National Natural Science Foundation of China(U1903214,62372339,62371350,61876135)the Ministry of Education Industry University Cooperative Education Project(202102246004,220800006041043,202002142012)the Fundamental Research Funds for the Central Universities(2042023kf1033)。
文摘Recent years have witnessed the ever-increasing performance of Deep Neural Networks(DNNs)in computer vision tasks.However,researchers have identified a potential vulnerability:carefully crafted adversarial examples can easily mislead DNNs into incorrect behavior via the injection of imperceptible modification to the input data.In this survey,we focus on(1)adversarial attack algorithms to generate adversarial examples,(2)adversarial defense techniques to secure DNNs against adversarial examples,and(3)important problems in the realm of adversarial examples beyond attack and defense,including the theoretical explanations,trade-off issues and benign attacks in adversarial examples.Additionally,we draw a brief comparison between recently published surveys on adversarial examples,and identify the future directions for the research of adversarial examples,such as the generalization of methods and the understanding of transferability,that might be solutions to the open problems in this field.
基金financial support of the Fundamental Research Funds for the Central Universities(SCU2023HGXY)Special Research Funds for Intelligent Battery Cell Multidimensional Signal Sensing Technology Project from Huawei Technologies Co.Ltd.(24H1117)。
文摘Accurate estimation on the state of health(SOH)is essential for ensuring the safe and reliable operation of batteries.Traditional assessment methods primarily focus on electrical attributes for capacity decay,often overlooking the impact of thermal distribution on battery aging.However,thermal effect is a critical factor for degradation process and associated risks throughout their service life.In this paper,we introduce a novel deep learning framework specially designed to estimate the capacity and thermal risks of lithium-ion batteries(LIBs).This model consists of two main components that leverage computer vision technology.One predicts battery capacity by integrating the advantages of thermal and electrical features using a temporal pattern attention(TPA)mechanism,while the other assesses thermal risk by incorporating temperature variation to provide early warnings of potential hazards.An infrared camera is deployed to record temperature evolution of LIBs during the electrochemical process.The thermal heterogeneities are recorded by infrared camera,and the corresponding temperature evolutions are extracted as representative features for analysis.The proposed model demonstrates high accuracy and stability,with an average root mean square error(RMSE)of 0.67% for capacity estimation and accuracy exceeding 93.9% for risk prediction,underscoring the importance of integrating spatial temperature distribution into battery health assessments.This work offers valuable insights for the development of intelligent and robust battery management systems.
基金supported by the R&D cooperation agreement be-tween Petrobras and CBPF(Contract No.0050.0121790.22.9)Brazilian Research Council(CNPq)for the scholarships for students.
文摘Convolutional neural networks have been widely used for analyzing image data in industry,especially in the oil and gas area.Brazil has an extensive hydrocarbon reserve on its coast and has also benefited from these neural network models.Image data from petrographic thin section can be essential to provide information about reservoir quality,highlighting important features such as carbonate lithology.However,the automatic identification of lithology in reservoir rocks is still a significant challenge,mainly due to the heterogeneity that is part of the lithologies of the Brazilian pre-salt.Within this context,this work presents an approach using one-class or specialist models to identify four classes of lithology present in reservoir rocks in the Brazilian pre-salt.The proposed methodology had the challenge of dealing with a small number of images for training the neural networks,in addition to the complexity involved in the analyzed data.An auto-machine learning tool called AutoKeras was used to define the hyperparameters of the implemented models.The results found were satisfactory and presented an accuracy greater than 70%for image samples belonging to other wells not seen during the model building,which increases the applicability of the implemented model.Finally,a comparison was made between the proposed methodology and multiple-class models,demonstrating the superiority of one-class models.
基金This paper was supported by National Natural Science Foundation of China (Grant No. 39670607).
文摘The classification of seedlings is important to ensure the viability of seedlings after transplantation and is acknowledged as a key factor in forestation and environmental improvement. Based on numerous papers on automatic seedling classification (ASC), the seedling grading theory, traditional grading methods, the background and the proceeding of ASC techniques are described. The automation of the measurement of seedling morphological characteristics by photoelectric meters and computer vision is studied, and the automatic methods of the current grading systems are described respectively. And the further researches on ASC by computer vision are proposed.
基金Special Fund for Science & Technology Research of Education Commission,Chongqing(KJ101302)~~
文摘Variety identification is important for maize breeding, processing and trade. The computer vision technique has been widely applied to maize variety identification. In this paper, computer vision technique has been summarized from the following technical aspects including image acquisition, image processing, characteristic parameter extraction, pattern recognition and programming softwares. In addition, the existing problems during the application of this technique to maize variety identification have also been analyzed and its development tendency is forecasted.
文摘With the development of image processing technology and computer, computer vision technology has been widely used in the production of agriculture,and has made many important achievements. This paper reviews its-research progress on diagnosis of agricultural products, water diagnosis, weed identification,product quality testing and grading, agricultural picking and sorting and other as- pects, and finally put forward its existing problems and prospects for the future.
基金National Key R&D Program of China under Grant No.2017YFC1500606,National Natural Science Foundation of China under Grant No.52020105002Heilongjiang Touyan Innovation Team Program。
文摘Damage detection is a key procedure in maintenance throughout structures′life cycles and post-disaster loss assessment.Due to the complex types of structural damages and the low efficiency and safety of manual detection,detecting damages with high efficiency and accuracy is the most popular research direction in civil engineering.Computer vision(CV)technology and deep learning(DL)algorithms are considered as promising tools to address the aforementioned challenges.The paper aims to systematically summarized the research and applications of DL-based CV technology in the field of damage detection in recent years.The basic concepts of DL-based CV technology are introduced first.The implementation steps of creating a damage detection dataset and some typical datasets are reviewed.CV-based structural damage detection algorithms are divided into three categories,namely,image classification-based(IC-based)algorithms,object detection-based(OD-based)algorithms,and semantic segmentation-based(SS-based)algorithms.Finally,the problems to be solved and future research directions are discussed.The foundation for promoting the deep integration of DL-based CV technology in structural damage detection and structural seismic damage identification has been laid.
基金Project (Nos. 2001AA620104 and 2003AA603140) supported by theHi-Tech Research and Development Program (863) of China
文摘The behavioral responses of a tilapia (Oreochromis niloticus) school to low (0.13 mg/L), moderate (0.79 mg/L) and high (2.65 mg/L) levels of unionized ammonia (UIA) concentration were monitored using a computer vision system. The swimming activity and geometrical parameters such as location of the gravity center and distribution of the fish school were calculated continuously. These behavioral parameters of tilapia school responded sensitively to moderate and high UIA concen-tration. Under high UIA concentration the fish activity showed a significant increase (P<0.05), exhibiting an avoidance reaction to high ammonia condition, and then decreased gradually. Under moderate and high UIA concentration the school’s vertical location had significantly large fluctuation (P<0.05) with the school moving up to the water surface then down to the bottom of the aquarium alternately and tending to crowd together. After several hours’ exposure to high UIA level, the school finally stayed at the aquarium bottom. These observations indicate that alterations in fish behavior under acute stress can provide important in-formation useful in predicting the stress.
基金This project is supported by National Natural Science Foundation of China(No.50175046) Technology Foundation of Education Ministry of China(No.00037).
文摘The structure, function and working principle of JLUIV-3, which is a new typeof auto-mated guided vehicle (AGV) with computer vision, is described. The white stripe line withcertain width is used as inductive mark for JLUIV-3 automated navigation. JULIV-3 can automaticallyrecognize the Arabic numeral codes which mark the multi-branch paths and multi-operation buffers,and autonomously select the correct path for destination. Compared with the traditional AGV, it hasmuch more navigation flexibility and less cost, and provides higher-level intelligence. Theidentification method of navigation path by using neural network and the optimal control method ofthe AGV are introduced in detail.
文摘In recent years, aquaculture industry in China is developing rapidly, and especially, China has the largest aquaculture area and the most output in the world. In the past, traditional aquaculture mainly depended on manual labour to breed and gain aquatic organisms. However, with the increasing scale of production and the continuous improvement of science and technology, the traditional aquaculture approach has become more and more unsuitable for the development of the times. With the rapid development of computer technology, computer vision technology infiltrates through the traditional aquaculture industry quickly and improves the aquaculture production efficiency .This paper mainly introduces the basic situation of computer vision technology and summarizes the application of computer vision technology in aquaculture industry at home and abroad. The paper concludes with the expectation of application of computer vision in the aquaculture.
基金This work was supported by the Science and Technology innovation project of Shanghai Science and Technology Commission(19441905800)the Natural National Science Foundation of China(62175156,81827807,8210041176,82101177,61675134)+1 种基金the Project of State Key Laboratory of Ophthalmology,Optometry and Visual Science,Wenzhou Medical University(K181002)the Key R&D Program Projects in Zhejiang Province(2019C03045).
文摘Age-related Macular Degeneration(AMD)and Diabetic Macular Edema(DME)are two com-mon retinal diseases for elder people that may ultimately cause irreversible blindness.Timely and accurate diagnosis is essential for the treatment of these diseases.In recent years,computer-aided diagnosis(CAD)has been deeply investigated and effectively used for rapid and early diagnosis.In this paper,we proposed a method of CAD using vision transformer to analyze optical co-herence tomography(OCT)images and to automatically discriminate AMD,DME,and normal eyes.A classification accuracy of 99.69%was achieved.After the model pruning,the recognition time reached 0.010 s and the classification accuracy did not drop.Compared with the Con-volutional Neural Network(CNN)image classification models(VGG16,Resnet50,Densenet121,and EfficientNet),vision transformer after pruning exhibited better recognition ability.Results show that vision transformer is an improved alternative to diagnose retinal diseases more accurately.
基金supported by the National Natural Science Foundation of China(31727901)the National Key R&D Program of China(2021YFD1400702)the Science and Technology Innovation Program of the Chinese Academy of Agricultural Sciences.
文摘Spodoptera frugiperda(Lepidoptera:Noctuidae)is an important migratory agricultural pest worldwide,which has invaded many countries in the Old World since 2016 and now poses a serious threat to world food security.The present monitoring and early warning strategies for the fall army worm(FAW)mainly focus on adult population density,but lack an information technology platform for precisely forecasting the reproductive dynamics of the adults.In this study,to identify the developmental status of the adults,we first utilized female ovarian images to extract and screen five features combined with the support vector machine(SVM)classifier and employed male testes images to obtain the testis circular features.Then,we established models for the relationship between oviposition dynamics and the developmental time of adult reproductive organs using laboratory tests.The results show that the accuracy of female ovary development stage determination reached 91%.The mean standard error(MSE)between the actual and predicted values of the ovarian developmental time was 0.2431,and the mean error rate between the actual and predicted values of the daily oviposition quantity was 12.38%.The error rate for the recognition of testis diameter was 3.25%,and the predicted and actual values of the testis developmental time in males had an MSE of 0.7734.A WeChat applet for identifying the reproductive developmental state and predicting reproduction of S.frugiperda was developed by integrating the above research results,and it is now available for use by anyone involved in plant protection.This study developed an automated method for accurately forecasting the reproductive dynamics of S.frugiperda populations,which can be helpful for the construction of a population monitoring and early warning system for use by both professional experts and local people at the county level.
文摘In textile inspection field,the fabric defect refers to the destruction of the texture structure on the fabric surface.The technology of computer vision makes it possible to detect defects automatically.Firstly,the overall structure of the fabric defect detection system is introduced and some mature detection systems are studied.Then the fabric detection methods are summarized,including structural methods,statistical methods,frequency domain methods,model methods and deep learning methods.In addition,the evaluation criteria of automatic detection algorithms are discussed and the characteristics of various algorithms are analyzed.Finally,the research status of this field is discussed,and the future development trend is predicted.
基金supported by the China Postdoctoral Science Foundation(2022M721514)the National Natural Science Foundation of China(82272132)+2 种基金the Guangdong Basic and Applied Basic Research Foundation(2021A1515011869)the Regional Joint Fund of Guangdong(Guangdong-Hong Kong-Macao Research Team Project,2021B1515130003)the Science and Technology Plan Project of Guangdong Province(2021A1414020003).
文摘Recent advances in artificial intelligence(AI)have sparked a surge in the application of computer vision(CV)in surgical video analysis.Laparoscopic surgery produces a large number of surgical videos,which provides a new opportunity for improving of CV technology in laparoscopic surgery.AI-based CV techniques may leverage these surgical video data to develop real-time automated decision support tools and surgeon training systems,which shows a new direction in dealing with the shortcomings of laparoscopic surgery.The effectiveness of CV applications in surgical procedures is still under early evaluation,so it is necessary to discuss challenges and obstacles.The review introduced the commonly used deep learning algorithms in CV and described their usage in detail in four application scenes,including phase recognition,anatomy detection,instrument detection and action recognition in laparoscopic surgery.The currently described applications of CV in laparoscopic surgery are limited.Most of the current research focuses on the identification of workflow and anatomical structure,while the identification of instruments and surgical actions is still awaiting further breakthroughs.Future research on the use of CV in laparoscopic surgery should focus on applications in more scenarios,such as surgeon skill assessment and the development of more efficient models.
基金the National Natural Science Foundation of China(No.31101085)the Scientific Research and Development Foundation for Start-up Projects of Zhejiang Agriculture and Forestry University (No.2034020044)
文摘The purpose of this study is to develop a standard methodology for measuring the surface free energy (SFE),and its component parts of bamboo fiber materials.The current methods was reviewed to determine the surface tension of natural fibers and the disadvantages of techniques used were discussed.Although numerous techniques have been employed to characterize surface tension of natural fibers,it seems that the credibility of results obtained may often be dubious.In this paper,critical surface tension estimates were obtained from computer aided machine vision based measurement.Data were then analyzed by the least squares method to estimate the components of SFE.SFE was estimated by least squares analysis and also by Schultz' method.By using the Fowkes method the polar and disperse fractions of the surface free energy of bamboo fiber materials can be obtained.Strictly speaking,this method is based on a combination of the knowledge of Fowkes theory. SFE is desirable when adhesion is required,and it avoids some of the limitations of existing studies which has been proposed.The calculation steps described in this research are only intended to explain the methods.The results show that the method that only determines SFE as a single parameter may be unable to differentiate adequately between bamboo fiber materials,but it is feasible and very efficient.In order to obtain the maximum performance from the computer aided machine vision based measurement instruments,this measurement should be recommended and kept available for reference.
基金the National Natural Science Foundation of China(No.61802304,61834005,61772417,61634004,61602377)Shaanxi Provincial Co-ordination Innovation Project of Science and Technology(No.2016KTZDGY02-04-02)+1 种基金Shaanxi Provincial Key R&D Plan(No.2017GY-060)Shaanxi International Science and Technology Cooperation Program(No.2018KW-006).
文摘Computer vision(CV)is widely expected to be the next big thing in emerging applications.So many heterogeneous architectures for computer vision emerge.However,plenty of data need to be transferred between different structures for heterogeneous architecture.The long data transfer delay becomes the mainly problem to limit the processing speed for computer vision applications.For reducing data transfer delay and fasting computer vision applications,a clustered data-driven array processor is proposed.A three-level pipelining processing element is designed which supports two-buffer data flow interface and 8 bits,16 bits,32 bits subtext parallel computation.At the same time,for accelerating transcendental function computation,a four-way shared pipelining transcendental function accelerator is designed,which is based on Y-intercept adjusted piecewise linear segment algorithm.A distributed shared memory structure based on unified addressing is also employed.To verify efficiency of architecture,some image processing algorithms are implemented on proposed architecture.Simultaneously the proposed architecture has been implemented on Xilinx ZC 706 development board.The same circuitry has been synthesized using SMIC 130 nm CMOS technology.The circuitry is able to run at 100 MHz.Area is 26.58 mm2.
基金Supported by the National Natural Science Foundation of China(NSFC)-Shandong Joint Fund for Marine Science Research Centers(No.U1406403)the National Key Technology Research and Development Program of China(No.2011BAD13B02)+1 种基金the National Marine Public Welfare Research Project(No.201205023)the Strategic Priority Research Program of Chinese Academy of Sciences(No.XDA11020404)
文摘Apostichopus japonicus(Holothuroidea,Echinodermata) is an ecological and economic species in East Asia.Conventional biometric monitoring method includes diving for samples and weighing above water,with highly variable in weight measurement due to variation in the quantity of water in the respiratory tree and intestinal content of this species.Recently,video survey method has been applied widely in biometric detection on underwater benthos.However,because of the high flexibility of A.japonicus body,video survey method of monitoring is less used in sea cucumber.In this study,we designed a model to evaluate the wet weight of A.japonicus,using machine vision technology combined with a support vector machine(SVM) that can be used infield surveys on the A.japonicus population.Continuous dorsal images of free-moving A.japonicus individuals in seawater were captured,which also allows for the development of images of the core body edge as well as thorn segmentation.Parameters that include body length,body breadth,perimeter and area,were extracted from the core body edge images and used in SVM regression,to predict the weight of A.japonicus and for comparison with a power model.Results indicate that the use of SVM for predicting the weight of 33 A.japonicus individuals is accurate(R^2=0.99) and compatible with the power model(R^2=0.96).The image-based analysis and size-weight regression models in this study may be useful in body weight evaluation of A.japonicus in lab and field study.
文摘This paper summarized the previous researches about resin emciency of particleboard in the world, and introduced the computer vision (CV) technique on resin effciency. which has the properties of high measuring speed, automatic pattern recognition and low environmental requirement. etc. The theory of the CV technique used for resin effciency in particleboard was studied,along with the handling of resined-particle images and the gathering of relative gray image features. Some quantitative parameters describing the resin efficiency of particleboard were established, and the results indicated that the computer vision method on the resin effciency was much better than others and can control the producing of pafticleboard more effect.
