Search

Image enhancement and reconstruction are the basic processing steps of many real vision systems. Their purpose is to improve the visual quality of images and provide reliable information for subsequent visual decision-making. In this paper, convolution neural network, residual neural network, and generative countermeasure network are studied. A rain fog image enhancement generative countermeasure network model structure including a scalable auxiliary generation network is proposed. The objective loss function is defined, and the periodic consistency loss and periodic perceptual consistency loss analysis are introduced. The core problem of image layering is discussed, and a layering solution framework with a deep expansion structure is proposed. This method realizes multitasking through adaptive feature learning, which has a good theoretical guarantee. This paper can not only bring a pleasant visual experience to viewers but also help to improve the performance of computer vision applications. Through image enhancement technology, the quality of low illumination image can be effectively improved, so that the image has better definition, richer texture details, and lower image noise. [ABSTRACT FROM AUTHOR]

This paper introduces the development status of machine vision nondestructive testing technology and industrial IoT supervision mechanism. The study designs and implements a machine vision nondestructive testing system from two aspects: construction of industrial IoT supervision and detection model, and optimization of machine vision nondestructive testing algorithm. In this paper, the random deployment of dynamic and static nodes is adopted. The coverage rate after random deployment and the moving distance of dynamic nodes are two necessary research parameters. To improve the initial coverage and optimize the mobile path of dynamic nodes, this paper proposes a mobile deployment optimization scheme based on the supervisory mechanism model of industrial IoT, which improves the traversal of the quantum genetic algorithm by improving the genetic variation rules, thus improving the initial deployment of the network. The optimized machine vision nondestructive detection algorithm is used for mobile path optimization from dynamic nodes to target locations. Simulation results show that a random deployment of 100 static nodes and 20 dynamic nodes in a 400 m × 400 m factory area works best with a coverage rate of 6.719% and an average movement distance of 23.47 m, and the movement path avoids the obstacle area. The average accuracy of the modified machine vision nondestructive testing system is 1.59% higher than that before the modification, and the average detection accuracy of the final experiment reaches 95.46%. Not only is the coverage rate better than that of the cellular structure-based dynamic node optimization scheme, but also the monitoring range of the plant tends to be more comprehensive in the actual deployment environment. Through the analysis of test results, the system achieves the monitoring and display of data on the one hand and provides a natural information access and interaction experience for IoT managers on the other hand, which meets the requirements of real time, accuracy, and stability of industrial IoT information data to a certain extent. [ABSTRACT FROM AUTHOR]

With the rapid development of high-speed rail in China, addressing the issue of safety assurance during the operation of the train is very important. A very important part of a train's power supply system is the pantograph and catenary system, which consists of a pantograph and a catenary. Failure of the pantograph-catenary system can cause significant damage to the normal operation of the train. The dynamic performance of the pantograph-catheter system must be detected in real time during the operation of the train. This paper is based on the study and analysis of pantograph-catheter dynamic performance parameters and developed a system for real-time detection of pantograph-catheter dynamic performance parameters based on a car visual system. The results are as follows: based on this detection method, the visual error is low and the accuracy is high. The machine-based directional height detection module developed in this paper has a good detection effect and high test accuracy; the arcing detection module designed in this paper can effectively detect the arcing and store the arcing pictures and can display the duration of single arcing and the arcing rate of the section in real-time. The practical application effect is good. The results show that the focal length of the camera lens is 16 mm, and the error of the machine vision system is low. The system designed in this paper may make a great contribution to the operation condition monitoring and fault diagnosis of the pantograph-catenary system of a high-speed train in the future. [ABSTRACT FROM AUTHOR]

Water contaminated by microorganisms can lead to the outbreak and prevalence of various diseases, which seriously threaten the health of people. In the monitoring of the water biological environment, the traditional methods have low detection sensitivity and low efficiency, so it is urgent to design a water biological monitoring system with low cost and high monitoring efficiency. Machine vision has the advantages of fast speed, appropriate precision, and strong anti-interference ability, which has been greatly developed in recent years. In this paper, the monitoring and early warning system of the water biological environment is built, in which the SVM algorithm is applied to image processing and feature extraction, and each module of the system is designed. Finally, the computational complexity of the system algorithm and the detection accuracy of the system are tested, and the results show that the system has the advantages of low cost, low computational complexity, and high monitoring efficiency, which can provide a reference for water resources protection. [ABSTRACT FROM AUTHOR]

Human behavior analysis has been a leading technology in computer vision in recent years. The station operation room is responsible for the dispatch of trains when they enter and leave the station. By analyzing the behaviors of the operators in the operation room, we can judge whether the operators have violations. However, there is no scheme to analyze the operator's behavior in the operation room, so we propose an operator behavior analysis system in the station operation room to detect operator's violations. This paper proposes an improved target tracking algorithm based on Deep-sort. The proposed algorithm can improve the target tracking performance through the actual test compared with the traditional Deep-sort algorithm. In addition, we put forward the detection scheme for common violations in the operation room: off-position, sleeping, and playing mobile phone. Finally, we verify that the proposed algorithm can detect the behaviors of operators in the station operation room in real time. [ABSTRACT FROM AUTHOR]

In this paper, we focus on the safety supervision of inland vessels. This paper especially aims at studying the vessel target detection and dynamic tracking algorithm based on computer vision and the target fusion algorithm based on multisensor. For the vessel video target detection and tracking, this paper analyzes the current widely used methods and theories. Additionally, facing the application scenarios and characteristics of inland vessels, a comprehensive vessel video target detection algorithm is proposed in this paper. It is combined with a three-frame difference method based on Canny edge detection and a background subtraction method based on mixed Gaussian background modeling. Besides, for the multisensor target fusion, the processing method of laser point cloud data and automatic identification system (AIS) data is analyzed in this paper. Based on the idea of fuzzy mathematics, this paper proposes a method for calculating the fuzzy correlation matrix with normal membership function, which realizes the fusion of vessel track features of laser point cloud data and AIS data under dynamic video correction. Finally, through this method, a set of vessel situation active intelligent perception systems based on multisensor fusion was developed. Experiments show that this method has better environmental applicability and detection accuracy than traditional manual detection and any single monitoring method. [ABSTRACT FROM AUTHOR]

China is gradually transitioning from the "tunnel construction era" to the "tunnel maintenance era," and more and more operating tunnels need to be inspected for diseases. With the continuous development of computer vision, the automatic identification of tunnel lining cracks with computers has gradually been applied in engineering. On the basis of summarizing the weaknesses and strengths of previous studies, this paper first uses the improved multiscale Retinex algorithm to filter the collected tunnel crack images and introduces the eight-direction Sobel edge detection operator to extract the edges of the cracks. Perform mathematical morphological operations on the image after edge extraction, and use the principle of the smallest enclosing rectangle to remove the isolated points of the image. Finally, the performance of the algorithm is judged by the objective evaluation index of the image, the accuracy of crack recognition, and the running time of the algorithm. The image filtering algorithm proposed in this paper can better preserve the edges of the image while enhancing the image. The objective evaluation indexes of the image have been improved significantly, and the main body of the crack can be accurately identified. The overall crack recognition accuracy rate can reach 97.5%, which is higher than the existing tunnel lining crack recognition algorithm, and the average calculation time for each image is shorter. This algorithm has high research significance and engineering application value. [ABSTRACT FROM AUTHOR]

This paper represents the recognition of group activity in public areas, considering personal actions and interactions between people from the field of computer vision. Modeling the interaction relationships between multiple people is essential for recognizing group activity in the video scene. In artificial intelligence applications, identifying group activities based on human interaction is often a challenging task. This paper proposed a model that formulates a group action context (GAC) descriptor. The descriptor was developed by integrating the focal person action descriptor and interaction joint context descriptor of nearby people in the video frame. The model used an efficient optimization principle based on machine learning to learn the discriminative interaction context relations between multiple persons. The proposed novel group action context descriptor is classified by support vector machine (SVM) to recognize group activity. The proposed technique effectiveness is evaluated for group activity recognition by performing experiments on a publicly available collective activity dataset. The proposed approach infers a group action class when multiple persons are together in the video sequence, especially when the interaction between people is confusing. The overall group action recognition model is interrelated with a baseline model to estimate the performance of interaction context information. The experimental result of the proposed group activity recognition model is comparable and outperforms the previous methods. [ABSTRACT FROM AUTHOR]

With the exploding development of edge intelligence and smart industry, deep learning-based intelligent industrial solutions are promptly applied in the manufacturing process. Many intelligent industrial solutions such as automatic manufacturing inspection are computer vision based and require fast and efficient video encoding techniques so that video streams can be processed as quickly as possible either at the edge cluster or over the cloud. As one of the most popular video coding standards, the high efficiency video coding (HEVC) standard has been applied to various industrial scenes. However, HEVC brings not only a higher compression rate but also a significant increase in encoding complexity, which hinders its practical application in industrial scenarios. Fortunately, a large amount of video coding data makes it possible to accelerate the encoding process in the industry. To speed up the video coding process in some industrial scenes, this paper proposes a data-driven fast approach for coding tree unit (CTU) partitioning in HEVC intracoding. First, we propose a method to represent the partition result of a CTU as a column vector of length 21. Then, we employ lots of encoding data produced in normal industry scenes to train transformer models used to predict the partitioning vector of the CTU. Finally, the final partitioning structure of the CTU is generated from the partitioning vector after a postprocessing operation and used by an industrial encoder. Compared with the original HEVC encoder used by some industrial applications, experiment results show that our approach achieves 58.77% encoding time reduction with 3.9% bit rate loss, which indicates that our data-driven approach for video coding has great capacity working in industrial applications. [ABSTRACT FROM AUTHOR]

In order to solve the problems of low brightness contrast of a color image, hiding a large amount of detail information, and deviation of color information in the process of image acquisition, an optimization method of plane image color enhancement processing based on computer vision virtual reality is proposed. In this method, the input RGB image is converted into the image represented by the HSI color model, and its adaptive brightness is adjusted to improve the overall brightness of the image. For the local detail enhancement of the color image, the three-dimensional Gaussian model perceived by retinal neurons is introduced into the illuminance image estimation of the MSR algorithm to enhance the image color. The results are as follows: from the perspective of objective parameter evaluation, the mean, standard deviation, information entropy, and average gradient of example images 1 and 2 are improved by about 70%; this algorithm not only enhances the brightness and contrast of the image but also maintains the detailed edge information of the image and the color characteristics of the object itself. The average enhancement rate is the highest among various algorithms, up to 95%. The algorithm proposed in this paper maintains the edge detail information of the image, optimizes the defects of the combination of traditional bilateral filtering and Retinex algorithm, and the color is also well restored, which makes the monitoring image easier to identify, more conducive to criminal investigation and solving cases, and lays a foundation for subsequent image processing. [ABSTRACT FROM AUTHOR]

Today people are witnessing the rapid evolvement in every area. This is because of the emerging trends in communication technology and autonomous unmanned vehicles. These trends have led us towards the high standards of health, energy, transportation, monitoring, and surveillance of huge domestic and industrial projects. Thus, this review paper presents the integration of the latest trend in communication technology, i.e., Internet of things (IoT) with unmanned aerial vehicles (UAVs). This manuscript not only reviews the use of IoT-enabled unmanned aerial vehicles for inspecting the several construction sites but also emphasizes the utilization of such IoT-enabled autonomous aerial vehicles for ensuring the health and safety measures at the site. It discusses the major limitations and shortcomings of state-of-the-art techniques for the same purpose, i.e., optimization issues in path planning, lightweight artificial intelligence (AI) and computer vision algorithms, coordination in communication using IoT, and scalability of IoT network. Thus, this paper shall help the reader to explore different open research problems in-depth. [ABSTRACT FROM AUTHOR]

Convolutional neural network (CNN) algorithm is a very important branch of deep learning research, which has been widely applied in many fields and achieved excellent results, especially in computer vision, where convolutional neural network has made breakthroughs in image classification and object detection. Convolutional neural network architecture can realize more efficient network training through the final combination of different modules, and the convolutional neural network training does not need to actively extract image features and can directly carry out end-to-end training and prediction. At first, this paper analyzed some problems of the current image recognition and expounds the progress of convolution neural network in image recognition and then studied the traditional algorithm of target recognition, including traditional recognition algorithm framework of target, the target orientation, feature extraction, classifier classification, etc., and the traditional target recognition algorithm is compared with those of the target recognition algorithm of deep learning. On the basis of the above research, an improved model of CNN is proposed, which focuses on the structural design and network optimization of convolutional neural network and designs a more efficient convolutional neural network. Test experiments verify the effectiveness of the proposed model, which not only achieves lower error rate, but also greatly reduces the number of network parameters and has stronger learning ability. [ABSTRACT FROM AUTHOR]

Real-time load detection method for belt conveyors based on computer vision is the research topic of this paper. A belt conveyor system equipped with cameras and a laser generator is used as the test apparatus. As the basis for conveyor intelligent speed regulation, two methods from different angles to perceive the load of conveyor belt were proposed, applied, and compared in this paper. Method 1 is based on the area proportion and method 2 is the detection based on laser-based computer vision technology. Laboratory experiments show that both methods can well detect the load on the conveyor belt. Method 2 is more economical and practical under the background of existing technology, also compared to the method 1, which provides a new idea and theoretical basis for the energy-saving control and intelligent development of the conveyor. [ABSTRACT FROM AUTHOR]

Target detection and segmentation algorithms have long been one of the main research directions in the field of computer vision, especially in the study of sea surface image understanding, these two tasks often need to consider the collaborative work at the same time, which is very high for the computing processor performance requirements. This article aims to study the deep learning sea target detection and segmentation algorithm. This paper uses wavelet transform-based filtering method for speckle noise suppression, deep learning-based method for land masking, and the target detection part uses an improved CFAR cascade algorithm. Finally, the best separable features are selected to eliminate false alarms. In order to further illustrate the feasibility of the scheme, this paper uses measured data and simulation data to verify the scheme and discusses the effect of different signal-to-noise ratio, sea target type, and attitude on the algorithm performance. The research data show that the deep learning sea target detection and segmentation algorithm has good detection performance and is generally applicable to ship target detection of different types and different attitudes. The results show that the deep learning sea target detection and segmentation algorithm fully takes into account the irregular shape and texture of the interfering target detected in the optical remote sensing image so that the accuracy rate is 32.7% higher and the efficiency is increased by about 1.3 times. The deep learning sea target detection is compared with segmentation algorithm, and it has strong target characterization ability and can be applied to ship targets of different scales. [ABSTRACT FROM AUTHOR]

Object detection in public spaces on urban streets has always been an important research topic in the field of computer vision networks. Due to the complex and changeable scene in the prediction of public space art design indicators, there are still problems in the research of target detection algorithms in practical applications. Based on the DCNN, this paper studies the accurate detection algorithm and implementation of urban streets in complex scenes. This paper uses the characteristics of DCNN coding to collect and compress data at the same time, studies the prediction module of urban street saliency detection algorithm, and combines saliency map to determine the saliency of urban street art design indicators in the measurement domain. The experimental method can greatly shorten the index prediction scan time and solve the problems of high window calibration redundancy and long positioning time in index prediction. The experimental results show that the proposed method combining urban street mask and public space feature information can reduce other interference information, the average accuracy of target detection is increased by 0.398, and the error is reduced to 3.12%, which significantly promotes urban streets and improves recognition accuracy. [ABSTRACT FROM AUTHOR]

In the field of computer vision, image saliency target detection can not only improve the accuracy of image detection but also accelerate the speed of image detection. In order to solve the existing problems of the saliency target detection algorithms at present, such as inconspicuous texture details and incomplete edge contour display, this paper proposes a saliency target detection algorithm integrating multiple information. The algorithm consists of three processes: preprocessing process, multi-information extraction process, and fusion optimization process. The frequency domain features of the image are calculated, the algorithm calculates the frequency domain features of the image, introduces power law transform and feature normalization, improves the frequency domain features of the image, saves the information of the target region, and inhibits the information of the background region. On three public MSRA, SED2, and ECSSD image datasets, the proposed algorithm is compared with other classical algorithms in subjective and objective comparison experiments. Experimental results show that the proposed algorithm can not only accurately and comprehensively extract significant target regions but also retain more texture information and complete edge information while satisfying the human visual experience. All evaluation indexes are significantly better than the comparison algorithm, showing good reliability and adaptability. [ABSTRACT FROM AUTHOR]

This paper is dedicated to machine learning, the branches of machine learning, which include the methods for solving this issue, and the practical implementation of the solution to the automatic image description generation. Automatic image caption generation is one of the frequent goals of computer vision. Image description generation models must solve a larger number of complex problems to have this task successfully solved. The objects in the image must be detected and recognized, after which a logical and syntactically correct textual description is generated. For that reason, description generation is a complex problem. It is an extremely important challenge for machine learning algorithms because it represents an impersonation of a complicated human ability to encapsulate huge amounts of highlighted visual pieces of information in descriptive language. The results of the generated descriptions are compared depending on the used pretrained convolutional networks. The BLEU metrics are used to calculate the quality of the image description. Although the solution to the problem of image description automatic generation does provide us with good results, there is yet room for improvement since there are images that are not adequately described. [ABSTRACT FROM AUTHOR]

With the development of computational simulation technology, the need for stable and immersive display effects of space scene animation in the field of life experience and visual art has gradually increased. In this case, the requirements for immersive characteristics of space scene animation have also been strengthened. The existing 3D space scene animation has a limited degree of stereoscopic display model and data visualization. However, the current space scene interactive animation adopts a plane layout as a whole, and the size of the view interface is generally fixed, including the size of virtual elements. However, the immersion in this paper interactive animation of spatial scene can effectively solve the problems of incomplete display of 3D effects and unstable view simulation in 3D effects. This paper takes immersive space scene animation as the research object and studies the 3D and characteristics of space scene animation based on computer parallel computing in different immersive space scenes and different virtual space technologies, as well as the animation effects of different scene transformations and art forms. The result of research shows that, with the continuous increase of the degree of virtuality within a certain range, the immersive effect of spatial scene interactive animation gradually becomes better. When the color of the space scene animation is below 15, the virtual immersive effect changes less. When the space scene is in the range of 15–20, the space scene will make people feel the atmosphere of a beautiful and mysterious illusion. [ABSTRACT FROM AUTHOR]

Image contrast enhancement is one of the most important tasks in the field of image digital processing. With the help of computers and programming languages, many mathematical methods have been implemented to improve the visual quality of an image. However, the majority of these methods have a major drawback: they tend to make the image look blocked. This effect is visually unpleasant and is likely to cause a computer vision system to falsely recognize as edges the boundaries of different blocks that belong to the same smooth area in the original image. To avoid the block effect while enhancing the quality of dark images, we propose a new fractional differential mask based on the Asumu fractional derivative. Experiments with dark natural images show that, even though our method does not have a better performance in statistical quality, it achieves a solution to the problem that was the motivation to write this paper, suppressing efficiently the block effect while improving the visual qualities of dark images. [ABSTRACT FROM AUTHOR]

Deep learning is a computer-based modeling approach, which is made up of many processing layers that are used to understand the representation of data with several levels of abstraction. This review paper presents the state of the art in deep learning to highlight the major challenges and contributions in computer vision. This work mainly gives an overview of the current understanding of deep learning and their approaches in solving traditional artificial intelligence problems. These computational models enhanced its application in object detection, visual object recognition, speech recognition, face recognition, vision for driverless cars, virtual assistants, and many other fields such as genomics and drug discovery. Finally, this paper also showcases the current developments and challenges in training deep neural network. [ABSTRACT FROM AUTHOR]

Object tracking has been one of the most active research directions in the field of computer vision. In this paper, an effective single-object tracking algorithm based on two-step spatiotemporal feature fusion is proposed, which combines deep learning detection with the kernelized correlation filtering (KCF) tracking algorithm. Deep learning detection is adopted to obtain more accurate spatial position and scale information and reduce the cumulative error. In addition, the improved KCF algorithm is adopted to track and calculate the temporal information correlation of gradient features between video frames, so as to reduce the probability of missing detection and ensure the running speed. In the process of tracking, the spatiotemporal information is fused through feature analysis. A large number of experiment results show that our proposed algorithm has more tracking performance than the traditional KCF algorithm and can efficiently continuously detect and track objects in different complex scenes, which is suitable for engineering application. [ABSTRACT FROM AUTHOR]

With the development of 5G wireless communications and the arrival of Industry 4.0, computer vision has further penetrated the manufacturing sector. This paper makes a comprehensive study on the field of intelligent manufacturing. By constructing a model analysis method, the current situation of computer vision intelligent manufacturing under the background of 5G wireless communication and industry 4.0 is comprehensively analyzed. It is found that today 's computer vision technology is developing rapidly, while the Industry 4.0 stage and 5G communication technology have helped the field of intelligent manufacturing. At the same time, the author deeply analyzes the characteristics of intelligent manufacturing enterprises supported by computer vision and finds that it has the problem of unbalanced distribution of enterprises. After that, the author demonstrates the application of computer vision re-intelligent manufacturing from multiple dimensions. The application of computational optimization methods provides more diverse and comprehensive algorithms for labor saving and resource utilization improvement. Computer vision technology drives and promotes the development of intelligent applications and promotes a more comprehensive development of intelligent manufacturing. [ABSTRACT FROM AUTHOR]

Many technical improvements have recently been made in the field of road safety, as accidents have been increasing at an alarming rate, and one of the major causes of such accidents is a driver's lack of attention. To lower the incidence of accidents and keep safe, technological innovations should be made. One way to accomplish this is with IoT-based lane detection systems, which function by recognizing the lane borders on the road and then prompting the turning of the road. Because of the various road conditions that one can encounter when driving, lane detection is a difficult problem. An image processing-based method for lane detection has been proposed in this paper. In this regard, each frame from the video is extracted and image processing techniques are applied for the detection of lanes. The frame which is extracted from the video is then subjected to a Gaussian filter for the removal of noise. Subsequently, color masking has been used to process the frame to detect only the road lanes, whose edges are obtained by applying the canny edge detection algorithm. Afterward, the Hough transform has been applied to the region of interest to extrapolate the lines. Finally, the path is plotted along the lines, and turns are predicted by using the concept of vanishing points. [ABSTRACT FROM AUTHOR]

In the cold season, wine aids in maintaining body temperature and is advised for military officers. This paper proposes a study on the multimotor drive control method of the upper-retort-robot based on machine vision for wine brewing automation to meet the demand of military areas located in cold regions, as wine is recommended to keep soldiers' body temperatures normal in China's extremely cold regions. Based on machine vision, the target is converted into an image signal by an image pickup device and is sent to the image processing system. Pixel distribution, brightness, color, and other data are transformed to digital signals, and target attributes are retrieved to control the field equipment's operations. The Monte-Carlo approach is used to generate joint variables at random within each joint's fluctuation range. The positive aspects of kinematics model are utilized and the working space of the upper-retort-robot is calculated using multimotor drive control method. The multimotor drive compensates the harmonic ripple torque and establishes the fault-tolerant automatic control of the system to maintain quality of the liquor. The results of the experiments reveal that the robot arm can reach any place within the barrel's set range. To control the quality of the liquor, the robot will function in an automatic manner. The robot's transmission performance is capable of meeting the requirements for automated liquor quality control during the production of wine from grapes. The results show that the suggested multimotor drive control (MMDCM) approach is robust and viable in terms of robot transmission performance and dexterity. [ABSTRACT FROM AUTHOR]

In recent years, modeling methods based on Deep Learning and Recurrent Neural Network (RNN) have achieved rapid development in various tasks in the field of computer vision, and video generation technology has also achieved remarkable results on this basis, with boosting effect. This paper analyzes the requirements and system design of the dance generation system based on cyclic neural network and clearly puts forward the specific functional requirements and nonfunctional requirements. Design, test each function of the system, and show the graphs generated by our application during training and testing, and visualize the specific value of the loss function during training. Combining the latest image generation technology and the most effective open source gesture detection project, a dance generation algorithm is completed, which can generate a video of the target person completing the specified dance action. [ABSTRACT FROM AUTHOR]

Computer vision systems cannot function without visual target tracking. Intelligent video monitoring, medical treatment, human-computer interaction, and traffic management all stand to benefit greatly from this technology. Although many new algorithms and methods emerge every year, the reality is complex. Targets are often disturbed by factors such as occlusion, illumination changes, deformation, and rapid motion. Solving these problems has also become the main task of visual target tracking researchers. As with the development for deep neural networks and attention mechanisms, object-tracking methods with deep learning show great research potential. This paper analyzes the abovementioned difficult factors, uses the tracking framework based on deep learning, and combines the attention mechanism model to accurately model the target, aiming to improve tracking algorithm. In this work, twin network tracking strategy with dual self-attention is designed. A dual self-attention mechanism is used to enhance feature representation of the target from the standpoint of space and channel, with the goal of addressing target deformation and other problems. In addition, adaptive weights and residual connections are used to enable adaptive attention feature selection. A Siamese tracking network is used in conjunction with the proposed dual self-attention technique. Massive experimental results show our proposed method improves tracking performance, and tracking strategy achieves an excellent tracking effect. [ABSTRACT FROM AUTHOR]

Plant diseases pose a major challenge in the agricultural sector, which affects plant development and crop productivity. Sugarcane farming is a highly organized part of farming. Owing to the desirable condition for sugarcane cultivation, India stands among the second largest producers of sugarcane over the globe. At the same time, sugarcane gets easily affected by multifarious diseases which significantly influence crop productivity. The recently developed computer vision (CV) and deep learning (DL) models with an effective design can be employed for the detection and classification of diseases in sugarcane plant. The disease detection in sugarcane plant is not accurate in the existing techniques. This paper presents a quantum behaved particle swarm optimization based deep transfer learning (QBPSO-DTL) model for sugarcane leaf disease detection and classification which produces high accuracy. The proposed QBPSO-DTL method is designed and trained for the prediction of diseased leaf images. The proposed QBPSO-DTL technique encompasses the design of optimal region growing segmentation to determine the affected regions in the leaf image. In addition, the SqueezeNet model is employed as a feature extractor and the deep stacked autoencoder (DSAE) model is applied as a classification model. Finally, the hyperparameter tuning of the DSAE model is carried out by using the QBPSO algorithm. For demonstrating the enhanced outcomes of the QBPSO-DTL approach, a wide range of experiments were implemented and the results ensured the improvements of the QBPSO-DTL model. [ABSTRACT FROM AUTHOR]

Embedded machine vision algorithm development platform is of great significance. Based on the elaboration of visual communication design, this paper further details the design of fractal visual art graphics based on computer-aided algorithms to design edge detection schemes, where edges represent sudden changes in the signal and are able to characterize the rich information of an image. In response to the problems of poor robustness and difficult parameter selection of the currently widely used edge detection algorithms, the platform encapsulates joint edge detection graphic components in a higher-order processing library to achieve the requirements of high-precision detection and to realise enhanced edge detection effects. Finally, the experimental analysis shows that the proposed algorithm has a more accurate detection effect and can meet the user's high-precision detection requirements. [ABSTRACT FROM AUTHOR]

Image text description is a multimodal data processing problem in the computer field, which involves the research tasks of computer vision and natural language processing. At present, the research focus of image text description task is mainly on the method based on deep learning. The work of this paper is mainly focused on the imprecise description of visual words and nonvisual words in the description of image description tasks in the image text description. An adaptive attention double-layer LSTM (long short-term memory) model based on coding-decoding is proposed. Compared with the algorithm based on the adaptive attention mechanism based on the coding-decoding framework, the evaluation index BLEU-1 is improved by 1.21%. The METEOR was 0.75% higher and CIDEr was 0.55%, while the indexes of BLEU-4 and ROUGE-L were not as good as those of the original model, but the index was not different. Although it cannot surpass all the performance indicators of the original model, the description of visual words and nonvisual words is more accurate in the actual image text description. [ABSTRACT FROM AUTHOR]

With the rapid development of computer vision, it has been widely used in football. Aiming at the problems of incomplete collection of information, poor operability of system, and bad practical application in the field of football match, an analysis system of football tactics is designed in this paper. Combining the requirements of functions and performance, the analysis system is divided into management of basic information, collection of tactical information, detection of passing pattern, inquiry of tactical information, and visual display, which puts forward the method of the detection of passing pattern based on model. Through the intelligent design, the visual display of the information of athlete, team, competition, tactics, and passing pattern is realized under computational intelligence, which has certain practical value in application. [ABSTRACT FROM AUTHOR]

In recent years, driven by the high-speed computing performance of computers and massive data on the Internet, deep nervine networks with highly abstract feature extraction and classification capabilities have been widely used in 3D art design and other fields, and a large number of breakthrough results have emerged. 3D art design is a research hotspot in the field of computer vision, which has broad application prospects and practical application value. Aiming at the problems of slow convergence and long training time of traditional deep belief network in the process of data feature expression, this paper proposes an unsupervised learning algorithm, namely adaptive deep belief network, and applies it to 3D art design. Its linear correction unit has good sparsity, which can improve the network performance well. The deep belief network DBN is formed by stacking the restricted Boltzmann machine RBM. The recognition research of 3D art design by optimizing the wavelet deep belief network can effectively improve the recognition rate and recognition speed of handwritten character recognition and achieve good results. [ABSTRACT FROM AUTHOR]

The collaborative filtering (CF) approach is one of the most successful personalized recommendation methods so far, which is employed by the majority of personalized recommender systems to predict users’ preferences or interests. The basic idea of CF is that if users had the same interests in the past they will also have similar tastes in the future. In general, the traditional CF may suffer the following problems: (1) The recommendation quality of CF based system is greatly affected by the sparsity of data. (2) The traditional CF is relatively difficult to adapt the situation that users’ preferences always change over time. (3) CF based approaches are used to recommend similar items to a user ignoring the user’s demand for variety. In this paper, to solve the above problems we build a new user-user covariance matrix to replace the traditional CF’s user-user similarity matrix. Compared with the user-user similarity matrix, the user-user covariance matrix introduces the user-user covariance to finely describe the changing trends of users’ interests. Furthermore, we propose an enhancing collaborative filtering method based on the user-user covariance matrix. The experimental results show that the proposed method can significantly improve the diversity of recommendation results and ensure the good recommendation precision. [ABSTRACT FROM AUTHOR]

Target tracking is currently a hot research topic in machine vision. The traditional target tracking algorithm based on the generative model selects target features manually, which has a simple structure and fast running speed, but it cannot meet the requirements of algorithm accuracy in complex scenes. Compared with traditional algorithms, due to the good performance, the tracking method based on full convolutional network has become one of the important methods of target tracking. However, the RPN-based Siamese network lacks positional reliability when predicting the target area. Aiming at the low tracking accuracy of the RPN-based Siamese network, this paper proposes an improved framework model named IoU-guided SiamRPN (IG-SiamRPN). In the proposed IG-SiamRPN, the IoU-guided branch is first constructed and sample pairs are generated through data augmentation. Then, the Jittered RoI is constructed to train the network to realize the direct prediction of the localization confidence of the candidate area. Subsequently, a target selection method based on predicted IoU scores is proposed, which uses predicted IoU scores instead of classification scores to optimize the target decision strategy of the Siamese network. Finally, an optimization-based fine-tuning method for the Siamese network frame is proposed, which solves the problem of location degradation and improves the performance of the algorithm. Compared with other state-of-the-art target tracking algorithms, experimental results on popular databases demonstrate that the proposed IG-SiamRPN can achieve better performance in both tracking accuracy and robustness. [ABSTRACT FROM AUTHOR]

During the past few decades, face recognition has been an active research area in pattern recognition and computer vision due to its wide range of applications. However, one of the most challenging problems encountered by face recognition is the difficulty of handling large head pose variations. Therefore, the efficient and effective head pose estimation is a critical step of face recognition. In this paper, a novel feature extraction framework, called Directional Correlation Filter Bank (DCFB), is presented for head pose estimation. Specifically, in the proposed framework, the 1-Dimensional Optimal Tradeoff Filters (1D-OTF) corresponding to different head poses are simultaneously and jointly designed in the low-dimensional linear subspace. Different from the traditional methods that heavily rely on the precise localization of the key facial feature points, our proposed framework exploits the frequency domain of the face images, which effectively captures the high-order statistics of faces. As a result, the obtained features are compact and discriminative. Experimental results on public face databases with large head pose variations show the superior performance obtained by the proposed framework on the tasks of both head pose estimation and face recognition. [ABSTRACT FROM AUTHOR]

Convolution neural network has become a hot research topic in the field of computer vision because of its superior performance in image classification. Based on the above background, the purpose of this paper is to analyze sports sequence images based on convolutional neural network. In view of the low detection rate of single-frame and the complexity of multiframe detection algorithms, this paper proposes a new algorithm combining single-frame detection and multiframe detection, so as to improve the detection rate of small targets and reduce the detection time. Based on the traditional residual network, an improved, multiscale, residual network is proposed in this paper. The network structure enables the convolution layer to "observe" data from different scales and obtain more abundant input features. Moreover, the depth of the network is reduced, the gradient vanishing problem is effectively suppressed, and the training difficulty is reduced. Finally, the ensemble learning method of relative majority voting is used to reduce the classification error rate of the network to 3.99% on CIFAR-10, and the error rate is reduced by 3% compared with the original residual neural network. [ABSTRACT FROM AUTHOR]

The singular value thresholding (SVT) algorithm plays an important role in the well-known matrix reconstruction problem, and it has many applications in computer vision and recommendation systems. In this paper, an SVT with diagonal-update (D-SVT) algorithm was put forward, which allows the algorithm to make use of simple arithmetic operation and keep the computational cost of each iteration low. The low-rank matrix would be reconstructed well. The convergence of the new algorithm was discussed in detail. Finally, the numerical experiments show the effectiveness of the new algorithm for low-rank matrix completion. [ABSTRACT FROM AUTHOR]

End-to-end neural machine translation does not require us to have specialized knowledge of investigated language pairs in building an effective system. On the other hand, feature engineering proves to be vital in other artificial intelligence fields, such as speech recognition and computer vision. Inspired by works in those fields, in this paper, we propose a novel feature-based translation model by modifying the state-of-the-art transformer model. Specifically, the encoder of the modified transformer model takes input combinations of linguistic features comprising of lemma, dependency label, part-of-speech tag, and morphological label instead of source words. The experiment results for the Russian-Vietnamese language pair show that the proposed feature-based transformer model improves over the strongest baseline transformer translation model by impressive 4.83 BLEU. In addition, experiment analysis reveals that human judgment on the translation results strongly confirms machine judgment. Our model could be useful in building translation systems translating from a highly inflectional language into a noninflectional language. [ABSTRACT FROM AUTHOR]

Ship detection is one of the most important research contents of ship intelligent navigation and monitoring. As a supplement to classical navigational equipment such as radar and the Automatic Identification System (AIS), target detection based on computer vision and deep learning has become a new important method. A target detector called YOLOv3 has the advantages of detection speed and accuracy and meets the real-time requirements for ship detection. However, YOLOv3 has a large number of backbone network parameters and requires high hardware performance, which is not conducive to the popularization of applications. On the basis of YOLOv3, this paper proposes a lightweight ship detection model (LSDM) in which the backbone network is improved by using dense connection inspired from DenseNet, and the feature pyramid networks are improved by using spatial separation convolution to replace normal convolution. The two improvements reduce parameters and optimize the network structure greatly. The experimental results show that, with only one-third of parameters of YOLOv3, the LSDM has higher accuracy and speed for ship detection. In addition, the LSDM is simplified further by reducing the number of densely connected units to form a model called LSDM-tiny. The experimental results show that, LSDM-tiny has similar detection speed with YOLOv3-tiny, but has a lot higher accuracy. [ABSTRACT FROM AUTHOR]

Recent research has shown that, during integrated piercing, the yarn tension can displace the needles from the centers of the holes in the piercing template. To reduce the damage done to the needle tips when the needles and the hole walls collide when the needle displacement is too large, this paper proposes a method for optimizing the needle shape that satisfies the strength constraint while targeting minimum needle displacement. First, the optimal objective function and strength constraint conditions for the tip displacement of the integrated puncture needle are established, which are affected by many factors. Then, the feature selection method of machine learning is used to reduce the dimensionality of the objective function after data reduction, and the feasible region of key features is reduced to avoid falling into the local best point in the optimization iteration. Finally, machine vision is used to measure experimentally the tip displacement of a needle array. The results show that the average tip displacement is reduced by 18.16–31.42% and the collision risk is reduced from 43.14% to 5.54%. It shows that the optimization method of needle shape based on feature selection is effective for reducing needle tip impact damage during integrated piercing. [ABSTRACT FROM AUTHOR]

Object tracking is a critical research in computer vision and has attracted significant attention over the past few years. However, the traditional object tracking algorithms often suffer from the object drifting problem due to various challenging factors in complex environments such as object occlusion and background clutter. This paper proposes a robust and effective object tracking algorithm, called MCM, which combines compressive sensing and online multiple instance learning in a multi-classifier fusion framework. In this framework, we integrate the different discriminative classifiers by learning the varied and compressed feature vectors based on different random projection matrices. And then an improved online multiple instance learning mechanism SMILE is adopted, which introduces the relative similarity to select and weight the instances in the positive bag. The experiments show that the proposed algorithm can improve the performance of object tracking on the challenging video sequences. [ABSTRACT FROM AUTHOR]

Owing to the importance of rod pumping system fault detection using an indicator diagram, indicator diagram identification has been a challenging task in the computer-vision field. The gradual changing fault is a special type of fault because it is not clearly indicated in the indicator diagram at the onset of its occurrence and can only be identified when an irreversible damage in the well has been caused. In this paper, we proposed a new method that combines the convolutional neural network (CNN) and long short-term memory (LSTM) network to perform a gradual changing fault classification. In particular, we employed CNN to extract the indicator diagram multilevel abstraction features based on its hierarchical structure. We considered the change in the time series of indicator diagrams as a sequence and employed LSTM to perform recognition. Compared with traditional mathematical model diagnosis methods, CNN-LSTM overcame the limitations of the traditional mathematical model theoretical analysis such as unclear assumption conditions and improved the diagnosis accuracy. Finally, 1.3 million sets of well production were set as a training dataset and used to evaluate CNN-LSTM. The results demonstrated the effectiveness of utilizing CNN and LSTM to recognize a gradual changing fault using the indicator diagram and characteristic parameters. The accuracy reached 98.4%, and the loss was less than 0.9%. [ABSTRACT FROM AUTHOR]

With the development of computer vision technology, more and more enterprises begin to use computer vision instead of manual inspection for steel surface defect detection. However, classical image processing methods often face great difficulties when dealing with images containing noise and distortions, which leads to low computational efficiency and poor accuracy of detection. In view of the particularity of hot round steel production, a computational intelligence method is proposed in this paper. On the basis of preliminary image preprocessing, we combine the improved PCA with genetic algorithm for feature selection and then use evolutionary computing and CUDA-based parallel computing to screen out the suspected defective image of round steel surface intelligently, quickly, and accurately. This method can provide decision support for subsequent defect analysis and production process improvement. [ABSTRACT FROM AUTHOR]

Multimedia content analysis is applied in different real-world computer vision applications, and digital images constitute a major part of multimedia data. In last few years, the complexity of multimedia contents, especially the images, has grown exponentially, and on daily basis, more than millions of images are uploaded at different archives such as Twitter, Facebook, and Instagram. To search for a relevant image from an archive is a challenging research problem for computer vision research community. Most of the search engines retrieve images on the basis of traditional text-based approaches that rely on captions and metadata. In the last two decades, extensive research is reported for content-based image retrieval (CBIR), image classification, and analysis. In CBIR and image classification-based models, high-level image visuals are represented in the form of feature vectors that consists of numerical values. The research shows that there is a significant gap between image feature representation and human visual understanding. Due to this reason, the research presented in this area is focused to reduce the semantic gap between the image feature representation and human visual understanding. In this paper, we aim to present a comprehensive review of the recent development in the area of CBIR and image representation. We analyzed the main aspects of various image retrieval and image representation models from low-level feature extraction to recent semantic deep-learning approaches. The important concepts and major research studies based on CBIR and image representation are discussed in detail, and future research directions are concluded to inspire further research in this area. [ABSTRACT FROM AUTHOR]

As computer vision develops, pan-tilt platform visual systems are able to track moving target over static camera systems. In this paper, a novel motion-intelligence-based control algorithm for object tracking by controlling pan-tilt platform has been proposed. The algorithm includes the motion control model based on angular speed and the intelligent control algorithm based on reinforcement learning (RL). The motion control model converts deviation between the center point of the tracked target and the center point of the frame to angular speed of pan-tilt platform. It can keep position of the tracked object in the center of the frame automatically. The intelligent control algorithm based on reinforcement learning can reduce the error between the ideal value and the actual value when the pan-tilt platform moves. The two blocks work together to make the pan-tilt platform track a dynamic object more stably and the experiment result shows that both the tracking accuracy and robustness are improved. [ABSTRACT FROM AUTHOR]

Image restoration is a long-standing problem in low-level computer vision. In this paper, we offer a simple but effective estimation paradigm for various image restoration problems. Specifically, we first propose a model-based Gaussian denoising method Adaptive Dual-Domain Filtering (ADDF) by learning the optimal confidence factors which are adjusted adaptively with Gaussian noise standard deviation. In addition, by generalizing this learning approach to Laplace noise, the learning algorithm of the optimum confidence factors in Laplace denoising is presented. Finally, the proposed ADDF is tactfully plugged into the method frameworks of off-the-shelf image deblurring and single image super-resolution (SISR). The approach, coining the name Plug-ADDF, achieves promising performance. Extensive experiments validate that the proposed ADDF for Gaussian and Laplace noise removals indeed results in visual and quantitative improvements over some existing state-of-the-art methods. Moreover, our Plug-ADDF for image deblurring and SISR also demonstrates superior performance objectively and subjectively. [ABSTRACT FROM AUTHOR]

Content-based image retrieval (CBIR) is a mechanism that is used to retrieve similar images from an image collection. In this paper, an effective novel technique is introduced to improve the performance of CBIR on the basis of visual words fusion of scale-invariant feature transform (SIFT) and local intensity order pattern (LIOP) descriptors. SIFT performs better on scale changes and on invariant rotations. However, SIFT does not perform better in the case of low contrast and illumination changes within an image, while LIOP performs better in such circumstances. SIFT performs better even at large rotation and scale changes, while LIOP does not perform well in such circumstances. Moreover, SIFT features are invariant to slight distortion as compared to LIOP. The proposed technique is based on the visual words fusion of SIFT and LIOP descriptors which overcomes the aforementioned issues and significantly improves the performance of CBIR. The experimental results of the proposed technique are compared with another proposed novel features fusion technique based on SIFT-LIOP descriptors as well as with the state-of-the-art CBIR techniques. The qualitative and quantitative analysis carried out on three image collections, namely, Corel-A, Corel-B, and Caltech-256, demonstrate the robustness of the proposed technique based on visual words fusion as compared to features fusion and the state-of-the-art CBIR techniques. [ABSTRACT FROM AUTHOR]

The emergence of machine vision has promoted the automation of defect detection (DD) in the industrial field. Therefore, scholars at home and abroad have carried out a lot of research and exploration on the traditional visual DD method of mechanical design products. At the same time, this method has been widely used in the field of modern manufacturing due to its noncontact and fast detection speed. The traditional visual detection method is to use cameras, computers, and other equipment instead of people to detect the detected objects, although this method improves the production efficiency to a certain extent. However, this detection method is greatly affected by light, has a certain false detection rate, and has poor adaptability. The intelligent detection method based on deep learning developed on the basis of traditional vision is a further optimization of traditional visual detection methods. The rapid development of deep learning makes the advantages of visual DD more obvious. [ABSTRACT FROM AUTHOR]

An automated flower thinning system, when combined with machine vision, has the potential to reduce the labor force, improve efficiency, and lower costs. This combination represents the future of agricultural machinery development. The primary objective of automatic flower thinning is to determine the flowering density of fruit trees under natural light conditions. In this study, we introduce a flower recognition algorithm that uses pixel values as an independent variable to recognize flower categories by constructing a nonlinear regression model. Initially, the RGB pixel values of elements in the training set are extracted. Similar pixel values are clustered together to reduce the amount of computation, and representative elements are selected to construct a nonlinear classification function, known as the regression function. The coefficients in the classifier are determined by transforming the problem into an unconstrained optimization problem using the least square method. The optimal solution is then found as the coefficient value in the classifier. The classification function calculates the function value of the RGB pixel value for each input entity to determine whether it belongs to the flower entity. Finally, the developed algorithm is used to classify the flower graphic elements of the measured pictures, and the efficiency of the algorithm is verified. [ABSTRACT FROM AUTHOR]

Diabetes is a very fast-growing disease in India, with currently more than 72 million patients. Prolonged diabetes (about almost 20 years) can cause serious loss to the tiny blood vessels and neurons in the patient eyes, called diabetic retinopathy (DR). This first causes occlusion and then rapid vision loss. The symptoms of the disease are not very conspicuous in its early stage. The disease is featured by the formation of bloated structures in the retinal area called microaneurysms. Because of negligence, the condition of the eye worsens into the generation of more severe blots and damage to retinal vessels causing complete loss of vision. Early screening and monitoring of DR can reduce the risk of vision loss in patients with high possibilities. But the diabetic retinopathy detection and its classification by a human, is a challenging and error-prone task, because of the complexity of the image captured by color fundus photography. Machine learning algorithms armed with some feature extraction techniques have been employed earlier to detect and classify the levels of DR. However, these techniques provide below-par accuracy. Now, with the advent of deep learning (DL) techniques in computer vision, it has become possible to achieve very high levels of accuracy. DL models are an abstraction of the human brain coupled with the eyes. To create a model from scratch and train it is a cumbersome task requiring a huge amount of images. This deficiency of the DL techniques can be patched up by employing another technique to a task called transfer learning. In this, a DL model is trained on image metadata, and to learn features it used hundreds of classes from the DR fundus images. This enables professionals to create models capable of classifying unseen images into a proper grade or level with acceptable accuracy. This paper proposed a DL model coupled with different classifiers to classify the fundus image into its correct class of severity. We have trained the model on IDRD images and it has proven to show very high accuracy. [ABSTRACT FROM AUTHOR]

Human motion recognition has an important application value in scenarios such as intelligent monitoring and advanced human-computer interaction, and it is an important research direction in the field of computer vision. Traditional human motion recognition algorithms based on two-dimensional cameras are susceptible to changes in light intensity and texture. The advent of depth sensors, especially the Kinect series with good performance and low price released by Microsoft, enables extensive research based on depth information. However, to a large extent, the depth information has not overcome these problems based on two-dimensional images. This article introduces the research background and significance of human motion recognition technology based on depth information, introduces in detail the research methods of human motion recognition algorithms based on depth information at home and abroad, and analyzes their advantages and disadvantages. The public dataset is introduced. Then, based on the depth information, a method of human motion recognition is proposed and optimized. A moving human body image segmentation method based on an improved two-dimensional Otsu method is proposed to solve the problem of inaccurate and slow segmentation of moving human body images using the two-dimensional Otsu method. In the process of constructing the threshold recognition function, this algorithm not only uses the cohesion of the pixels within the class but also considers the maximum variance between the target class and the background class. Then, the quantum particle swarm algorithm is used to find the optimal threshold solution of the threshold recognition function. Finally, the optimal solution is used to achieve accurate and fast image segmentation, which increases the accuracy of human body motion tracking by more than 30%. [ABSTRACT FROM AUTHOR]