Search

To improve the lengthy computation time of conventional variable structure interacting multiple model (VSIMM) algorithm and increase the precision of target prediction and extrapolation, the target state and flight intent information captured by the Automatic Dependent Surveillance-Broadcast (ADS-B) are used as the model's prior information; combining this information with VSIMM theoretical framework, we purpose an intent variable structure interacting multiple model (INT-VSIMM) algorithm. Firstly, the motion pattern of the target in the flight phase of the flight path is decomposed, and complete sets of motion models are established. Secondly, according to the principle of directed graph switching, a model set switching method is designed, which is mainly based on "hard" switching and supplemented by "soft" switching. Finally, the INT-VSIMM algorithm is used to track the trajectory of the target aircraft, and short-term trajectory extrapolation is performed based on the target state estimation. The simulation results show that the target tracking performance computational time based on the INT-VSIMM algorithm is superior to the comparative existing methods, and the extrapolated trajectory has less error in the short term, which can satisfy the needs of conflict detection. [ABSTRACT FROM AUTHOR]

The design of new efficient maximum power point tracking (MPPT) techniques has become extremely important due to the rapid expansion of photovoltaic (PV) systems. Because under shading conditions the characteristics of PV devices become multimodal having several power peaks, traditional MPPT techniques provide crappy performance. In turn, metaheuristic algorithms have become massively employed as a typical substitute in maximum power point tracking. In this work, a new optimizer, which was named the hyperbolic slime mould algorithm (HSMA), is designed to be employed as an efficient MPPT algorithm. The hyperbolic tangent function is incorporated into the optimizer framework equations to scale down large perturbations in the tracking stage and boost its convergence trend. Moreover, to provide a strong exploration capability, a new mechanism has been developed in such a way the search process is carried out inside the best two power peak regions along the initial iterations. This region inspection mechanism is the prime hallmark of the designed optimizer in avoiding local power peaks and excessive global search operations. The developed algorithm was examined through diverse complicated partial shading conditions to challenge its global and local search abilities. A comparative analysis was carried out against the well-regarded PSO, GWO, and the standard slime mould algorithm. In overall, the designed optimizer defeated its contenders in all aspects offering higher efficiency, superior robustness, faster convergence, and fewer fluctuations to the operating point. An experimental setup that consists of the DSpace microcontroller and a PV emulator was employed to validate the algorithm overall performance. The recorded outcomes outline that the developed optimizer can achieve a tracking time of 0.6 seconds and 0.86 seconds on average, with 99.85% average efficiency under complex partial shading conditions. [ABSTRACT FROM AUTHOR]

This research work emphasizes proposing a hybrid social grouping algorithm (SGA) and perturb and observe (P&O) scheme for tracking the global power peak in a partially shaded photovoltaic (PV) array. PV panels getting shaded, even partially, exhibits multiple power peaks, and hence conventional maximum power point tracking (MPPT) algorithms fail in tracking the maximum power peak as it gets deceived by local maxima. Most of the prevailing global search algorithms suffer in performance due to the stochastic search which consumes time even after nearing the global power peak. Therefore, a hybridization of the global search algorithm and the conventional algorithm will be a prudent solution. SGA, a global search algorithm based on individual and group cognizant behaviour, has been hybridized with a well-entrenched P&O algorithm that complements each other in achieving the global power peak swiftly. The hybridized algorithm achieves the global power peak in 0.4 seconds faster than the stand-alone SGA algorithm during complex shading conditions. The proposed scheme has been implemented for an 800 W PV array in a MATLAB simulation and validated experimentally in a hardware setup using a SAS1000L solar array simulator-programmable source, a DC-DC converter, and a dSPACE 1104 controller. The simulation and experimental results reveal that the proposed search scheme is very competent in converging towards the global maximum through SGA first and achieving the peak point through P&O. The proposed scheme has also been tested for a dynamic shading pattern, and it is evident that the proposed scheme outperforms its counterparts in terms of convergence time. [ABSTRACT FROM AUTHOR]

The design of finite impulse response (FIR) filters involves the estimation of effective filter coefficients, making the designed filter exhibit infinite stopband attenuation and have a flat-shaped passband. The few conventional filter design methods such as impulse response truncation (IRT) and windowing technique exhibit undesirable characteristics owing to the Gibbs phenomenon, thus making them unsuitable for various practical complexities. This research work employs the fuzzy logic-based diversity-controlled self-adaptive differential evolution algorithm (FLDCSaDE) for the design of FIR band stop (BS) and high pass (HP) filters. In order to validate the results of the proposed technique, various population-based evolutionary computing techniques such as the covariance matrix adaptation evolution strategy (CMAES), differential evolution (DE), self-adaptive differential evolution (SaDE), and Jaya algorithm have also been applied for determining the effective filter coefficients. The performance of the various algorithms has been analysed and compared based on the parameters such as stopband attenuation, passband attenuation, and ripples. The simulation results show that the FLDCSaDE algorithm outperforms other evolutionary algorithms having 4% and 1.5% lower ripples than the SaDE algorithm for high pass and band stop filters, respectively. Experimental results depict that the performance of the fuzzy approach causes positioning and tracking accuracy obtained to be improved by 27% and the corresponding false positive rate (FPR) is substantially reduced to 0.11 from the mean amplitude value obtained from the fuzzy approach in the frequency response. The frequency response obtained from the FLDCSaDE algorithm is close to the ideal response of the BS and HP FIR filters. [ABSTRACT FROM AUTHOR]

In actual traffic scenarios, the environment is complex and constantly changing, with many vehicles that have substantial similarities, posing significant challenges to vehicle tracking research based on deep learning. To address these challenges, this article investigates the application of the DeepSORT (simple online and realtime tracking with a deep association metric) multitarget tracking algorithm in vehicle tracking. Due to the strong dependence of the DeepSORT algorithm on target detection, a YOLOv5s_DSC vehicle detection algorithm based on the YOLOv5s algorithm is proposed, which provides accurate and fast vehicle detection data to the DeepSORT algorithm. Compared to YOLOv5s, YOLOv5s_DSC has no more than a 1% difference in optimal mAP0.5 (mean average precision), precision rate, and recall rate, while reducing the number of parameters by 23.5%, the amount of computation by 32.3%, the size of the weight file by 20%, and increasing the average processing speed of each image by 18.8%. After integrating the DeepSORT algorithm, the processing speed of YOLOv5s_DSC + DeepSORT reaches up to 25 FPS, and the system exhibits better robustness to occlusion. [ABSTRACT FROM AUTHOR]

In actual traffic scenarios, the environment is complex and constantly changing, with many vehicles that have substantial similarities, posing significant challenges to vehicle tracking research based on deep learning. To address these challenges, this article investigates the application of the DeepSORT (simple online and realtime tracking with a deep association metric) multitarget tracking algorithm in vehicle tracking. Due to the strong dependence of the DeepSORT algorithm on target detection, a YOLOv5s_DSC vehicle detection algorithm based on the YOLOv5s algorithm is proposed, which provides accurate and fast vehicle detection data to the DeepSORT algorithm. Compared to YOLOv5s, YOLOv5s_DSC has no more than a 1% difference in optimal mAP0.5 (mean average precision), precision rate, and recall rate, while reducing the number of parameters by 23.5%, the amount of computation by 32.3%, the size of the weight file by 20%, and increasing the average processing speed of each image by 18.8%. After integrating the DeepSORT algorithm, the processing speed of YOLOv5s_DSC + DeepSORT reaches up to 25 FPS, and the system exhibits better robustness to occlusion. [ABSTRACT FROM AUTHOR]

The transmitting signal of wireless communication system is impaired by the nonlinearity of RF power amplifier (PA) which leads to signal distortion and spectrum spillover, by which the signal transmission quality is affected. Digital predistortion (DPD) is an efficient and economical way to correct the nonlinear effects of power amplifiers. The recursive least square (RLS) recognition algorithm is commonly used to extract the correction coefficients of the DPD model, and the accuracy of the extraction directly affects the system performance. In this paper, a new variable forgetting factor identification algorithm (new variable forgetting factor recursive least square, NVFFRLS) is proposed for recursive least square (RLS) identification algorithm. The 64-QAM signal is combined with a memory polynomial (MP) predistortion model for predistortion system simulation. The experimental results show that, compared with the RLS identification algorithm and two kinds of variable forgetting factor RLS identification algorithms, the algorithm has smaller estimation error, faster convergence, and better tracking capability, stability, and adaptability; the predistortion system based on NVFFRLS identification algorithm can compensate the nonlinear memory effects of power amplifier more effectively. [ABSTRACT FROM AUTHOR]

Photovoltaic (PV) research is rapidly growing, and the need for controlled environments to validate new MPPT controllers is becoming increasingly important. Currently, researchers face several challenges in testing MPPT algorithms due to the unpredictable nature of solar PV power generation. In this paper, we propose a new photovoltaic emulator (PVE) that could replace solar panels and ensure a highly controllable environment suitable for testing photovoltaic (PV) systems. In this PVE, the complex nonlinear equations of the PV cell/module are fast computed and resolved by a new linearization technique which involves the systematic breakdown of the current-voltage (I - V) curve of the PV into twelve linear segments. Based on input environmental conditions, an artificial neural network (ANN) was constructed to assist the linearization process by predicting the current-voltage boundary coordinates of these segments. Using simple linear equations, with the segment boundary coordinates, a reference voltage was generated for the PVE. A nonlinear backstepping controller was designed to exploit the reference voltage and stabilize the power conversion stage (PCS). The PVE was optimized using particle swarm optimization (PSO). Several tests have shown that the proposed nonlinear controller provides better dynamic and robust performance than the PI controller, the most reputable and recurrent control method in the area of PVE. The PVE was coupled with a recently proposed integral backstepping MPPT controller and analyzed under several dynamic conditions, including the MPPT test specified by EN 50530. It was found that the accuracy of the proposed PVE measured by its relative error is less than 0.5%, with an MPPT efficiency of greater than 99.5%. The attractive results achieved by this PVE make it especially suitable for simulating and validating MPPT controllers. [ABSTRACT FROM AUTHOR]

Bridge deformation response data are the basis for calculating the dynamic parameters of the bridge, and it is of great significance to accurately measure the deformation response of the bridge during the load test and service conditions. A bridge deformation measurement method using an unmanned aerial system (UAS) with dual cameras and a deep learning-based object tracking method is proposed to measure the bridge deformation. The contributions are as follows: (1) To address the problem that the movement of the UAS brings error to the deformation measurement results, dual cameras with telephoto and wide-angle lenses are used to simultaneously capture the deformed points and stable points on the bridge, so as to simultaneously measure the deformation of the bridge and the displacement of the UAS, and then the displacement of UAS is eliminated by using the homography relationship between the two cameras. (2) To solve the problem that the traditional digital image correlation-based displacement measurement method is easily disturbed by factors such as light changes and occlusion, a displacement calculation method based on object detection network and target tracking algorithm is proposed to achieve the stable target displacement measurement. Finally, the proposed method was verified in a laboratory test and applied to the deformation measurement of an in-service bridge to verify the practicability of the proposed method. [ABSTRACT FROM AUTHOR]

In this paper, a data-driven differential dynamic programming (DDP) algorithm is presented for the optimal tracking problems of nonlinear affine systems with unknown drift dynamics. Optimal tracking dynamics are established between the system states and expected trajectory. By using the DDP method and test data, a second-order data-driven framework of the Hamilton–Jacobi–Bellman (HJB) equation is constructed, in which system approximation and value function approximation are used. By using this framework, a data-driven iteration algorithm is proposed to achieve the optimal tracking controller. A simulation example is provided to verify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

Elderly individuals with similar abilities are likely to have similar care needs. Abilities are the basis for analysing the need patterns of elderly individuals. Abilities of elderly individuals are both numerical and categorical; therefore, an improved K-prototypes cluster algorithm for mixed attributes was proposed to group elderly individuals based on abilities. In this algorithm, the dissimilarity measure of categorical attributes is designed to consider not only the difference between the object to be allocated and the prototype of the cluster but also the differ6ence between the object to be allocated and other objects in the cluster and can measure the difference in sequential values of ordinal categorical attributes. Experimental results show that the improved K-prototypes algorithm performs well for clustering datasets containing mixed attributes. Taking the CHARLS dataset as an example, distinct groups of elderly individuals based on the improved K-prototypes algorithm showed significant ability differences. [ABSTRACT FROM AUTHOR]

This paper proposes a mobile sun-tracking (MST) system to track the sun on the moving vehicle. We have developed a novel MST algorithm using general sun-tracking formulas associated with simple-moving average linear regression (SMALR) to smoothen sun-tracking activity. Furthermore, two different timing control schemes to activate sun tracking are investigated: time lapse (TL) mode and azimuth actuation (AA) mode. For experimental validation, a prototype of MST has been constructed on a small truck moving at constant speed of 30 km/h for field measurements. For the result, AA mode has average pointing error of 110 mrad for the open-loop tracking design (13% better than that of TL mode), which is still far below the half acceptance angle of compound parabolic concentrator at 659 mrad. Since there is no feedback sensor to be implemented in this prototype, optical encoders and CCD camera can be employed in the future work to further reduce the pointing error of MST system. [ABSTRACT FROM AUTHOR]

A novel composite terminal guidance law with impact angle constraints is proposed for supercavitating torpedoes to intercept maneuvering warships. Based on an adaptive super-twisting algorithm and nonsingular terminal sliding mode (NTSM), the proposed guidance law can guarantee the finite-time convergence of line-of-sight (LOS) angle error and the LOS angular rate error. The new guidance law is a combination of finite-time stability theory, sliding mode control (SMC), tracking differentiator (TD), disturbance observer (DO), and dynamic surface control. A high-order sliding mode TD is used for denoising, tracking, and differentiating the measured target heading angle. A novel DO, with its finite-time stability proved, is designed to estimate the target lateral acceleration for feedforward compensation to attenuate chattering in control input. In the case of a first-order-lag autopilot, a new kind of tracking differentiator is adopted to compute the first-order time derivative of the virtual control command, which can improve the accuracy of dynamic surface control and avoid the "explosion of items" problem encountered with the backstepping control. Finally, numerical simulation results are presented to validate the effectiveness and superiority of the proposed TD, DO, and the composite guidance law. [ABSTRACT FROM AUTHOR]

Understanding trajectory tracking control concerns is crucial for industrial-grade manipulators to provide precise and risk-free operations for the safe environment. Consequently, the robot arms need precise aim for tracking a given target trajectory by the trajectory control input driving torque which can use smart AI-based techniques for precision. Similarly, a decision tree is a soft computing-based method of feature space partitioning which can certainly allow the movement of robots in an accurate manner. The control of robot arms is an important aspect for automating the process of sustainable development. Aiming at the problem of poor tracking accuracy of traditional Multi-Degree-of-Freedom Manipulator Joint Trajectory Monitoring (Multi-DoF MJTM) and long monitoring delay, this article proposes a Multi-DOF manipulator joint trajectory tracking method based on decision tree. The Multi-DoF manipulator is developed for the adaptive control object of the working machine, and it is combined with the output response feature to construct the kinematics model of the Multi-DoF manipulator mechanism of the walking machine. The joint trajectory reconstruction of the running trajectory is used to obtain the joint trajectory deviation of the Multi-DoF manipulator's running trajectory through the multi-measurement system. Based on this, the Multi-DoF manipulator's running trajectory joint trajectory tracking control equation is obtained to realize the joint trajectory tracking and monitoring of the manipulator. The features for a safe environment are also integrated. The experimental results show that the proposed method has high accuracy in tracking the trajectory of Multi-DoF manipulator joints, and the time delay for tracking and monitoring the trajectory of manipulator's joints is also optimized. [ABSTRACT FROM AUTHOR]

In this paper, the initial parameters of C-V level set image recognition are optimized by using the global optimization characteristics of cultural algorithm, and a cultural algorithm C-V level set image recognition model is proposed, which is abbreviated as the CC-V model. The initial population space of the cultural algorithm is used to set the initial recognition parameters in a large range, and the population evolution is continuously optimized and guided by the situation knowledge and normative knowledge of the reliability space, so as to realize the global optimization of the recognition parameters and to timely terminate by judging the change of the image entropy fitness value. Through the analysis and comparison of the experimental results, the CC-V model has a better recognition effect than the C–V model. The partial differential equation image recognition model is applied to the video image sequence for moving target recognition. The background model is constructed by the block statistical histogram. The background difference method is used to locate the video moving target, and the minimum circumscribed rectangle of the multitarget positioning is used as the initial outline of the model recognition. The research results show that the nonintellectual factors of each group of ethnic traditional sports have an obvious effect on the application value of people, and the application effect of nonintellectual factors produced by different groups will also vary. All ethnic traditional sports groups show higher application value to nonintellectual character factors. The comprehensive application value of nonintelligence factors of the combat confrontation item group, accuracy item group, and endurance item group is relatively higher than the comprehensive application value of nonintelligence factors of other item groups. [ABSTRACT FROM AUTHOR]

An online social network is a platform where people can communicate with friends, share information, speed up business development, and improve teamwork. A large amount of user privacy information existing in real social networks is leaked from person to person, and this issue has hardly been studied. With the rapid expansion of the network, the issue of privacy protection has received increasing attention. So far, many privacy protection methods including differential protection algorithms, encryption algorithms, access control strategies, and anonymization have been researched and applied. Information leakage means that the information shared by the user is disseminated or downloaded by his friends without the user's consent, and the transmission of private information will not be recorded. In order to track and find out the ways and methods of information leakage, this article adopts an unusual method, namely, the probability judgment based on trust. By screening the similarities between users, past information exchanges, and the topology of social networks, a trust model is established to evaluate and estimate the degree of trust between users. According to the rating information privacy of friends' trust, an information dissemination system is established, which can be applied to online social networking platforms to reduce the risk of information leakage, thereby ensuring the security of users' private information. At the same time, this paper expands the transmission system model without user authorization and proposes a fingerprint-based deterministic leak tracking algorithm. [ABSTRACT FROM AUTHOR]

Pedestrian detection and tracking based on computer vision has gradually become an international pattern recognition, which is one of the most active research topics in the field of computer vision and artificial intelligence. Using the theoretical results in the field of pattern recognition and computer vision technology, we are committed to detect and track pedestrians from video sequences. In addition to computer vision-based passer-by detection and tracking technology as the key, in the advanced computer vision action and analysis, it has a direct impact on the accuracy and robustness of its understanding. We analyzed various targets, such as subsequent recognition motion and pedestrian motion, and described them as high-level application processing, such as action understanding. In addition, because of the unique texture of human clothes compared with the surrounding natural landscape, they are highly "prominent" from the perspective of human visual system, and they are particularly prominent in the peripheral part of human contact with the background. In this paper, a binary function based on importance is proposed. As the space representation of image itself is not sensitive to noise and local signal, space representation is used. In addition, as an observation model, it can reduce the adverse effects of background noise and local noise on the tracking algorithm. Through the function block tracking, the pedestrian's body can be tracked in detail. At the same time, the color band learning method is used to update the target template online to deal with the changes of target appearance caused by sunshine, pedestrian posture, and other factors. According to the experimental results, even if the appearance and posture of pedestrians change greatly, it has a stable tracking effect. [ABSTRACT FROM AUTHOR]

As an indispensable part in the field of computer vision, target tracking has been widely used in intelligent transportation, missile guidance, unmanned aerial vehicle (UAV) tracking, and many other fields. It has become one of the hot directions in computer vision in recent years, while occlusion problem has always been a great difficulty and challenge in the process of target tracking. In this article, the problem of occlusion interference in target tracking is described, and the solution of occlusion problem is proposed based on different occlusion conditions. Due to the disadvantages of feature point center weighting, multiparticle template matching, and Kalman filter trajectory prediction algorithms in different cases, some algorithms with higher robustness and stability are developed to solve the occlusion problem. In the analysis of the anti-occlusion model, it is found that some tracking errors caused by occlusion can be solved by improving the quality of negative training samples and enriching the diversity of positive sample sets. According to the different training characteristics of online and offline tracking algorithms, the anti-occlusion model suitable for an active learning algorithm under different tracking conditions is found, and the tracking algorithm and characteristics of the active learning algorithm are listed, which is helpful to select the suitable tracking model in different scenarios. Finally, the future development of occlusion problem in target tracking is prospected. [ABSTRACT FROM AUTHOR]

In order to solve the problem of distrust of a large number of nodes under the overly centralized and centralized information transfer mode, a research method of real-time tracking algorithm of e-commerce logistics information based on blockchain technology is proposed. The application background of blockchain technology in real-time tracking algorithm of e-commerce logistics information is firstly described. Also, the blockchain technology, logistics information real-time tracking algorithm, cryptography technology, blockchain consensus algorithm, blockchain application scenarios, and other related technologies are analyzed in detail. Then, the blockchain model of real-time tracking of e-commerce logistics information is established, and it is found that data will be stored on the chain only when more than 51% of the nodes in the distributed system confirm that the data are valid. Otherwise, the data on the chain cannot be affected. Finally, the model description and hypothesis of real-time tracking of e-commerce logistics information based on blockchain technology are verified to provide guarantee for improving real-time tracking of e-commerce logistics information. [ABSTRACT FROM AUTHOR]

In order to overcome the problems of high error rate and poor tracking effect of traditional tracking algorithms, a multitarget pedestrian tracking algorithm based on a contour template is designed in this paper. The pedestrian template is divided into several contour regions by template voting strategy and pedestrian features are classified by regional feature similarity classification. Then, the score function is selected to realize the multiobjective pedestrian feature division, and the multicontour template matching is realized according to the similarity of deformation diversity. According to the matching results, the detection and tracking of multitarget objects are realized. The experimental results show that the feature recognition accuracy of the algorithm is between 93% and 98%, the tracking error of pedestrian gravity center position is always below 5%, and the tracking time is always below 5 S in different video frame scales, which fully proves the effectiveness of the algorithm. [ABSTRACT FROM AUTHOR]

Feature pyramid network is widely used in advanced object detection. By simply changing the network connection, the performance of small object detection can be greatly improved without increasing the amount of calculation of the original model. However, the algorithm still has some shortcomings. Therefore, a new attention feature pyramid network (attention PFN) is proposed. Firstly, an improved receptive field module is added, which can make full use of global and local context information. Secondly, the connection mode of the pyramid is further optimized. Deconvolution is used to replace the nearest neighbor interpolation in top-down up-sampling and a channel attention module is added to the horizontal connection to highlight important context information. Finally, adaptive fusion and spatial feature balance are used for each feature pyramid, so that the network can learn the weights of different feature layers. Each pyramid layer contains more discrimination information. Attention PFN is tested on Pascal VOC and MS COCO datasets, respectively. The experiment results revealed that the proposed method has better performance than the original algorithm. Therefore, the attention PFN is an effective algorithm. [ABSTRACT FROM AUTHOR]

The application of information technology has realized the transformation of people's production and lifestyle and also promoted the development of the sports industry. At present, the application of informatization in the field of sports is becoming more and more powerful. By using the advanced methods and technologies of its information display, this paper aimed to realize the research on the tracking of tennis sports video objects in the mobile network environment. It is helpful to analyze and solve the objectivity problems such as most of the loopholes in the single research and traditional methods of tennis video target tracking research. By drawing on the principles and rules of machine learning algorithms, the tennis video target tracking research is carried out, and the informatization and dataization of tennis are realized. In the experiment of the target tracking algorithm, 12 tracking videos have higher tracking accuracy than other parameters. The overall tracking accuracy of the video sequence under grayscale feature was 0.694; the tracking accuracy was the highest, but the tracking speed was the lowest compared to other parameters in the experiment. Therefore, it is very important to study the target tracking of tennis sports in the tennis field. [ABSTRACT FROM AUTHOR]

In order to solve the problems of inaccurate information collection, incomplete information collection, and inconsistency of collected images in traditional sports injury collection methods, an application method of moving target information perception technology in intelligent supervision system is proposed. By judging and analyzing the potential motion damage posture of the motion posture intelligent tracking images, the collected motion intelligence tracking images are judged. The intelligent tracking image matrix can make up for the shortcomings of traditional images that are not connected, complete the identification, detect potential damage in time, and take targeted preventive measures and means. Finally, according to the target detection algorithm and target tracking algorithm, combined with OpenCV computer vision library and QT image library, an intelligent video surveillance target tracking simulation system is developed. The algorithm studied in this paper is to realize the target tracking function of the intelligent video surveillance system. Through the comparison of experimental results, the design method can accurately collect damage attitude information, without calculating continuous values, and the use of three-dimensional images in the positioning process can analyze the damage attitude from multiple angles. [ABSTRACT FROM AUTHOR]

In track construction, it is an important and necessary guarantee for production safety to check the number of workers and tools before and after the track maintenance. In view of time-consuming, laborious, and low detection efficiency of traditional manual inspection way, we propose an improved YOLOv5 multiscale object detection algorithm for track construction safety in this paper. We improve, from Generalized Intersection over Union (GIoU) to Distance Intersection over Union (DIoU), the loss function for Bounding Box (BBox) regression to speed up the convergence of the model. And we also improve, from the Non-Maximum Suppression (NMS) to DIoU-NMS, the post-processing method to enhance the model's detection ability for occluded objects and small objects. The experiment results on the Track Maintenance dataset (our self-prepared dataset) and MS COCO dataset show that the mAP value of our improved YOLOv5 algorithm is 94.8% and 38.7%, respectively. Compared with the original YOLOv5 algorithm, the mAP values on above datasets are increased by 5.1% and 5.4%, respectively. The validation experimental results on MS COCO dataset and Track Maintenance dataset indicate that the detection ability of our improved YOLOv5 algorithm for occluded objects and small objects is enhanced. The proposed algorithm can provide technical support for the real-time accurate detection of track construction workers and tools. [ABSTRACT FROM AUTHOR]

The traditional A ∗ algorithm, applied to the motion planning of autonomous vehicles, easily causes high computational costs and excessive turning points generated in the planning path. In addition, the vehicle cannot track the path due to the unsmooth inflection point. To overcome these potential limitations, an improved A ∗ algorithm-based motion planning algorithm and a tracking control strategy based on model predictive control theory were proposed in this work. The method of expanding the search neighborhood is adopted to improve the planning efficiency of A ∗ algorithm. The artificial potential field method is also incorporated into the proposed A ∗ algorithm. The resultant force generated by each potential field is further introduced into the evaluation function of A ∗ algorithm to plan the driving path, which could be suitable for autonomous vehicles. The sharp nodes in the path are smoothed by cubic quasi-uniform B-spline curve. The tracking control strategy is designed based on model predictive control theory to realize the accurate tracking of the planned path. Typical obstacle avoidance conditions were selected for co-simulation test verification. The experimental results show that the proposed motion planning algorithm and tracking control strategy can effectively plan the obstacle avoidance path and accurately track the path in different environments. [ABSTRACT FROM AUTHOR]

Maximum Power Point Tracking (MPPT) for photovoltaic systems has widely been studied. However, studying the impact of partial shading (due to buildings, trees, clouds, adjacent arrays, and so on) on the MPPT and achieving the global maximum is still a challenging topic. This is because not only there is a global maximum power point (GMPP) but also there are several local maximums due to the non-linear nature of the power-voltage curve after partial shading. Therefore, the conventional MPPT methods fail to track the GMPP and are commonly trapped at one of the local maximum power points. This study utilizes the Hyper-Spherical Search (HSS) algorithm in MATLAB to achieve the GMPP while improving the efficiency, convergence speed, dynamic response, and reducing the losses. To track the GMPP using the HSS algorithm, the output power for the array (PPV) is defined as the objective function, and the duty cycle of the DC-DC converter is selected as the particles' position (control variable). The performance of the proposed algorithm has been studied in three different partial shading patterns, and the simulation results confirm the capability of the algorithm in the rapid tracking of GMPP points. In addition, if the GMPP position changes over time, it will track the new GMPP with minimal oscillations. The proposed method along with PSO, P&O, ABC, and Dragon algorithms has been applied for various scenarios, and the obtained results using HSS have been compared with the four mentioned algorithms, which confirmed the effectiveness of the proposed method. Briefly, the advantages of the HSS algorithm in finding GMPP can be stated as simple implementation with few parameters, strong exploration, and exploitation during the tracking process, fast-tracking and low fluctuations during tracking, low oscillation at steady-state, high dynamic efficiency, and non-convergence to LMPP points. [ABSTRACT FROM AUTHOR]

Martial arts education has a relatively comprehensive educational function. Compared with other educational methods, it has some unique features. When martial arts education carries out moral education, it not only attaches importance to the teaching of moral norms but also requires martial arts practitioners to practice moral norms, so martial arts education is more practical in improving moral literacy. In fact, the role of martial arts education is far from just playing its role in strengthening the body. This kind of prejudice of mindset conceals the diversity characteristics of martial arts education. This paper proposes to apply artificial intelligence technology in martial arts education governance, which uses the target tracking algorithm based on deep learning to track and analyze the movement of martial arts practitioners. At the same time, this paper uses the pose estimation algorithm of coordinate regression to predict the key points of the human body from the global perspective of the human body and then locates the key points of the human body from the features. It greatly simplifies the prediction of key points and solves the problem of nonstandard movements of students in martial arts education. The experimental analysis part includes the results and analysis of the impact of AI-based flipped classroom teaching on students' martial arts learning and the comparison and analysis of students' martial arts learning in the two classes after the experiment. The analysis results show that the P values of the four aspects of learning interest, active participation attitude, independent exploration ability, and analysis and problem-solving ability of the two classes are all less than 0.01, indicating that there is a significant difference. [ABSTRACT FROM AUTHOR]

The traditional project management in the construction industry has the uniqueness of exclusive customization, the irreversibility of the project, the immobility of the project address, the long-term nature of the project, and the dynamic nature of the project. Based on these characteristics, the complexity and difficulty of project management in the construction industry are determined. Modern engineering is no longer satisfied with the traditional basic needs, but develops in a green, environmental friendly and efficient way. On the one hand, the project is required to meet good use requirements and meet the most basic functional requirements. On the other hand, the project construction process is required to meet the requirements of green environmental protection and ecological harmony. Therefore, the maintenance cost and operation cost corresponding to modern projects have become the key to the sustainable and healthy development of the engineering construction industry. Based on this, this paper will take the construction industry as an example to fully analyze the current situation and existing problems faced by the current project cost management. Through the research on the full life-cycle project cost management mode of the construction industry, the random matrix weight algorithm is creatively introduced, and the adaptive full life-cycle project cost management extended target tracking algorithm is proposed, which cuts the corresponding full life-cycle project cost management model into multiple submodels, and the corresponding management subobjectives are constructed from the submodel, and the expansion status of the corresponding subobjectives is described and analyzed in detail using the inverse distribution description, so as to accurately estimate the effect and target weight coefficient required by the management subobjectives, and finally realize the efficient, reasonable and scientific operation of the construction industry's whole life-cycle project cost management, so as to maximize economic benefits. An experimental verification is carried out for a specific construction company. The verification results show that the full life-cycle project cost management scheme based on random matrix weight algorithm proposed in this paper has obvious advantages in management efficiency, cost control, process control, and other aspects compared with the traditional management scheme. [ABSTRACT FROM AUTHOR]

The purpose of this study was to investigate the state estimation problem for the multisensor descriptor fractional systems. Firstly, the descriptor fractional order system was transformed into two nondescriptor fractional order subsystem based on the singular value decomposition method; then, the descriptor fractional Kalman filters for the subsystems were proposed based on projection theory, which effectively solved the state estimation problem of the descriptor fractional order system with singular matrix; on this basis, the track fusion fractional Kalman filter of the multisensor descriptor fractional system is proposed by using the track fusion algorithm. The state estimation accuracy of multisensor descriptor fractional order systems is greatly improved. Simulation results show the effectiveness of the proposed algorithm. [ABSTRACT FROM AUTHOR]

Machine learning methods use computers to imitate human learning activities to discover new knowledge and enhance learning effects through continuous improvement. The main process is to further classify or predict unknown data by learning from existing experience and creating a learning machine. In order to improve the real-time performance and accuracy of the distributed EM algorithm for machine online learning, a clustering analysis algorithm based on distance measurement is proposed in combination with related theories. Among them, the greedy EM algorithm is a practical and important algorithm. However, the existing methods cannot simultaneously load a large amount of social information into the memory at a time. Therefore, we created a Hadoop cluster to cluster the Gaussian mixture model and check the accuracy of the algorithm, then compare the running time of the distributed EM algorithm and the greedy algorithm to verify the efficiency of the algorithm, and finally check the scalability of the algorithm by increasing the number of nodes. Based on this fact, this article has conducted research and discussion on the visualization of sports movements, and the teaching of visualization of sports movements can stimulate students' interest in physical education. The traditional physical education curriculum is completely based on the teacher's oral explanation and personal demonstration, and the emergence of visualized teaching of motor movements broke the teacher-centered teaching model and made teaching methods more interesting. This stimulated students' interest in sports and improved classroom efficiency. [ABSTRACT FROM AUTHOR]

Freestyle skiing U-shaped field is a snow sport that uses double boards to perform a series of action skills in a U-shaped pool, which requires very high skills for athletes. In this era of deep learning, in order to develop a more scientific training method, this paper combines multitarget tracking algorithm and deep learning to conduct research in freestyle skiing U-shaped venue skills motion capture. Therefore, this paper combines the convolutional neural network and multitarget tracking algorithm in deep learning to study the human action recognition technology, and then uses the LSTM module to study the freestyle skiing U-shaped venue skills. Finally, this paper designs the training method of the action recognition algorithm of the freestyle U-shaped skiing skills multitarget tracking algorithm based on deep learning. This paper also designs multitarget tracking dataset experiments and model updating experiments. Based on the data of experimental analysis, the training method designed in this paper is optimized, and finally compared with the traditional training method. Compared with the traditional freestyle U-shaped skiing skills training method, the experimental results show that the training method of the freestyle U-shaped skiing skills multitarget tracking algorithm action recognition algorithm is based on deep learning designed in this paper and this improves the skill score by 14.48%. Most professional students are very satisfied with the training method designed in this paper. [ABSTRACT FROM AUTHOR]

To simultaneously achieve space formation flight and target tracking of multiple unmanned aerial vehicles (UAVs) and solve the rotation buffeting problem of the UAV, a robust formation control and target tracking algorithm is proposed. The artificial potential function consisting of formation control term and target tracking term is established, and its convergence is proved. The sliding mode control method with the saturation function is established, and a sufficient condition for sliding mode to occur is analysed. Finally, the numerical simulation is conducted for the proposed algorithm, and the simulation result is analysed. The results show that the proposed algorithm can quickly achieve the formation flight and target tracking of multi-UAVs and improve the tracking performance; meanwhile, it can effectively weaken the rotation buffeting and improve the robustness. [ABSTRACT FROM AUTHOR]

The vast majority of currently available kernelized correlation filter (KCF)-based trackers simply make use of a single object feature to define the object of interest. It is impossible to avoid tracking instability while working with a wide variety of complex videos. In this piece of research, an ensemble learning-based multi-cues fusion object tracking method is offered as a potential solution to the issue at hand. Using ensemble learning to train multiple kernelized correlation filters with different features in order to obtain the optimal tracking parameters is the primary concept behind the improved KCF-based tracking algorithm. After that, the peak side lobe ratio and the response consistency of two adjacent frames are used to obtain the fusion weight. In addition, an adaptive weighted fusion technique is applied in order to combine the response findings in order to finish the location estimation; finally, the tracking confidence is applied in order to update the tracking model in order to prevent model deterioration. In order to increase the adaptability of the revised algorithm to size-change, a Bayesian estimate model based on scale pyramid has been presented. This model is able to determine the optimal scale of the object, which is the goal of this endeavor. The tracking results of a number of different benchmark movies demonstrate that the algorithm that we have suggested is able to effectively eliminate the effects of interference elements, and that its overall performance is superior to that of the comparison algorithms. [ABSTRACT FROM AUTHOR]

Machine learning only uses single-channel grayscale features to model the target, and the filter solution process is relatively simple. When the target has a large change relative to the initial frame, the tracking effect is poor. When there is the same kind of target interference in the target search area, the tracking results will be poor. The tracking algorithm based on the fully convolutional Siamese network can solve these problems. By learning the similarity measurement function, the similarity between the template and the target search area is evaluated, and the target area is found according to the similarity. It adopts offline pre-training and does not update online for tracking, which has a faster tracking speed. According to this study, (1) considering the accuracy and speed, the target tracking algorithm based on correlation filtering performs well. A sample adaptive update model is introduced to eliminate unreliable samples, which effectively enhances the reliability of training samples. With simultaneous changes in illumination and scale, fast motion and in-plane rotation IPR can still be maintained. (2) Determined by calculating the Hessian matrix, in the Struck function, Bike3 parameter adjustment can achieve fast tracking, and Boat5 ensures that the system stability is maintained in the presence of interference factors. The position of the highest scoring point in the fine similarity score map of the same size as the search image is obtained by bicubic interpolation as the target position. (3) The parallax discontinuity caused by the object boundary cannot be directly processed as a smooth continuous parallax. The MeanShift vector obtained by calculating the target template feature and the feature to be searched can increase the accuracy by 53.1%, reduce the robustness by 31.8%, and reduce the error by 28.6% in the SiamVGG algorithm. [ABSTRACT FROM AUTHOR]

Because the scene of football video is fixed and simple, the events in football video, such as shooting and offside , also have clear semantics. At the same time, they have sufficient domain knowledge and have broad application prospects. The research framework of sports video intelligence analysis is usually regarded as a three-level framework, namely, the low-level feature layer, the middle-level key primitive generation layer, and the high-level event analysis layer. A MF_O2T (Moving Feature Online Target Tracking) algorithm is proposed. First, based on the marked first frame image, this algorithm extracts a set of standardized local images from the target areas of visible and infrared images as target convolution filters, removes the main color of the stadium by using HSV color space nonuniform quantization algorithm, and extracts the histogram of the main color of players in upper and lower blocks. Experimental results show that the algorithm designed in this paper has strong robustness, can better adapt to player tracking in different scenes of football video, and meets the real-time requirements of football training. [ABSTRACT FROM AUTHOR]

Track failure at a railway station is a common disruption in the station area caused by abnormal weather or frequent use. This paper focuses on the real-time track reallocation problem to recover the affected track utilization plan and minimize the total train delays and passenger inconveniences. Train platforming operations in busy complex passenger stations are generally conducted according to fixed track utilization rules. In this paper, we presented a mixed-integer linear programming model for train platforming problems with constraints relevant to fixed track utilization rule and objectives of balanced usage of tracks. Furthermore, we proposed an improved genetic simulated annealing algorithm based on improved crossover and selection methods without breaking the fixed track utilization rule constraint. An experiment of Guanzhou East Station with fixed track utilization rules shows the effectiveness of the proposed model and algorithm. The model and algorithm provide efficient approaches for track reallocation problems based on fixed track utilization rules in busy complex passenger stations. [ABSTRACT FROM AUTHOR]

In order to improve the effectiveness of tennis teaching and enhance students' understanding and mastery of tennis standard movements, based on the three-dimensional (3D) convolutional neural network architecture, the problem of action recognition is deeply studied. Firstly, through OpenPose, the recognition process of human poses in tennis sports videos is discussed. Athlete tracking algorithms are designed to target players. According to the target tracking data, combined with the movement characteristics of tennis, real-time semantic analysis is used to discriminate the movement types of human key point displacement in tennis. Secondly, through 2D pose estimation of tennis players, the analysis of tennis movement types is achieved. Finally, in the tennis player action recognition, a lightweight multiscale convolutional model is proposed for tennis player action recognition. Meanwhile, a key frame segment network (KFSN) for local information fusion based on keyframes is proposed. The network improves the efficiency of the whole action video learning. Through simulation experiments on the public dataset UCF101, the proposed 3DCNN-based KFSN achieves a recognition rate of 94.8%. The average time per iteration is only 1/3 of the C3D network, and the convergence speed of the model is significantly faster. The 3DCNN-based recognition method of information fusion action discussed can effectively improve the recognition effect of tennis actions and improve students' learning and understanding of actions in the teaching process. [ABSTRACT FROM AUTHOR]

Computer vision is an interesting branch of artificial intelligence which is dedicated to how electronic devices can achieve the level of capabilities to perceive things just like ordinary human beings do. In order to solve the poor effect of video for the detection of target in football matches and the low accuracy of target tracking, this paper aims to make a deep exploration of the methods of video for the detection of target and tracking in football matches. The video moving for the detection of target method based on background model is used to extract the image in the background of the matching video which improves the light flow field. Secondly, the video differential image is acquired according to the difference of colors, the ghost target of the image in the video background model is scientifically determined, the ghost degree of the pixel points of the image is scientifically determined, and the flicker matrix of the target image is constructed. The number of pixels of the moving target is derived. A meanshift-based video target tracking algorithm is used in conjunction for the detection of target result to determine whether to track the target image until the overall video target tracking task is completed, move the central position of the target frame and background frame to the target position, select the best one to adapt to the target change, and determine whether to track the target image until the overall video target tracking task is completed. The simulation results suggest that the approach described in this study is capable of detecting and tracking moving objects, as well as improving target recognition and tracking accuracy. [ABSTRACT FROM AUTHOR]

In order to solve the difficult problem of deep learning-based robot vision tracking algorithm research and implementation, a deep learning-based target tracking algorithm and a classical tracking algorithm were proposed. It mainly uses the combination of traditional TLD algorithm and GOTURN algorithm to benefit from a large number of offline training data and updates the learner online, so that the whole system has better performance in real-time and accuracy. The results show that the performance of the TLD algorithm is poor regardless of the accuracy curve or the accuracy curve, and the performance of GOTURN-LD is significantly improved when the illumination changes. In the face of occlusion problem, the TLD algorithm shows strong robustness. Although GOTURN-LD is not very stable, its performance is better than GOTURN on the whole. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, the application of intelligent algorithms to low-power embedded chips has become a new research topic today. Based on this, this study optimizes the YOLOv2 algorithm by tailoring and successfully deploys it on the K210 chip to train the face object detection algorithm model separately. The intelligent fan with YOLOv2 model deployed in K210 chip can detect the target of the character and obtain the position and size of the character in the machine coordinates. Based on the obtained information of character coordinate position and size, the fan's turning Angle and the size of air supply are intelligently perceived. The experimental results show that the intelligent fan design method proposed here is a new embedded chip intelligent method of cutting and improving the YOLOv2 algorithm. It innovatively designed solo tracking, crowd tracking, and intelligent ranging algorithms, which perform well in human perception of solo tracking and crowd tracking and automatic air volume adjustment, improve the accuracy of air delivery and user comfort, and also provide good theoretical and practical support for the combination of AI and embedded in other fields. [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]

With the development of computer hardware technology, the real-time problem of visual target tracking algorithm increasingly depends on hardware solutions. The core problem of visual target tracking is how to enhance the robustness of tracking algorithm to various complex background environments and various interference factors. Aiming at overcoming the defect that the traditional SLAM (simultaneous localization and map building) algorithm based on EKF (extended Kalman filter) has a slow repair speed for environmental interference, a Monocular SLAM_WOCPF (Monocular vision SLAM based on weight optimization combined particle filter) algorithm is proposed. The weights of all particles are reoptimized in the particle set and they are combined with the tendency of particles to degenerate and deplete. In this way, the chance of self replication of low weight particles is increased, thus increasing the diversity of the whole sample. Furthermore, the improved PF (particle filter) algorithm is applied to solve the problem of road sign observation of mobile robots, so as to expand its application scope. The results show that the mean road sign errors of the Monocular SLAM_WOCPF algorithm in two noise environments are 0.332/m and 0.441/m. The conclusion shows that the Monocular SLAM_WOCPF road sign observation method proposed in this paper can effectively improve the matching success rate of visual road signs and improve the observation quality. [ABSTRACT FROM AUTHOR]

In order to improve the effect of e-sports training, this paper combines the intelligent gesture recognition technology to construct an e-sports training system and judges the training effect of players through the recognition of players' gestures. Moreover, this paper studies the commonly used feature extraction algorithms and proposes an improved SLC-Harris feature extraction algorithm, and the feasibility of this algorithm is verified by the experimental results on the EUROC data set. In addition, this paper uses the KLT optical flow algorithm to track the extracted feature points and calculates the pure visual pose through epipolar geometry, triangulation, and PnP algorithms. The experimental research results show that the electronic economic training system based on intelligent gesture recognition proposed in this paper has certain effects. [ABSTRACT FROM AUTHOR]

Aiming at the problem that the probability transition matrix is set by prior information and the filtering parameters are fixed in the traditional interactive multimodel (IMM) algorithm, which leads to the model probability lag in the switching process and the low filtering and tracking accuracy, an interactive multimodel filter tracking (IABBSCA-IMM) algorithm with improved parameter adaptive and bare bone sine cosine optimization is proposed. First, the Markov probability transition matrix is dynamically adjusted and limited conditions are added through the parameter adaptation method; then, the filtering parameters Q and R are optimized by the bare bones sine cosine algorithm (BBSCA); finally, three motion models of CV (uniform velocity motion), CA (uniform acceleration motion), and CT (uniform velocity turning motion) are used to conduct filtering and tracking experiments on the target. The simulation results show that, compared with the IMM algorithm, the AMP-IMM algorithm, the IASCA-IMM algorithm, and the IABBSCA-IMM algorithm proposed in this study have the smallest position and velocity root mean square error (RMSE) in the X and Y directions, and the accuracy is better. [ABSTRACT FROM AUTHOR]

Based on the importance of climate change in the environmental and economic fields, this study analyzes the impact of climate change on the economy based on the current situation, including the impact on sensitive industries and the impact on each district, in order to study the impact of abnormal atmospheric anticyclones on the economy. Furthermore, this study enhances the image-tracking algorithm, fuses the registered radar picture using the wavelet multiresolution analysis approach, and decomposes the registered radar image using the Mallat algorithm to retrieve the low- and high-frequency components of the image. Because the information included in the frequency components after wavelet decomposition differs, this study uses appropriate fusion algorithms for the decomposed low-frequency and high-frequency components, respectively, to produce panoramic photographs with acceptable visual effects. Through experimental research, it can be seen that the statistical analysis model of anomalous anticyclone in ocean atmosphere and economy based on the target tracking algorithm proposed in this study has a good simulation operation effect, and it also verifies that there is a certain correlation between the atmospheric anomalous anticyclone and the economy. [ABSTRACT FROM AUTHOR]

With the development of computer hardware technology, the real-time problem of visual target tracking algorithm increasingly depends on hardware solutions. The core problem of visual target tracking is how to enhance the robustness of tracking algorithm to various complex background environments and various interference factors. Aiming at overcoming the defect that the traditional SLAM (simultaneous localization and map building) algorithm based on EKF (extended Kalman filter) has a slow repair speed for environmental interference, a Monocular SLAM_WOCPF (Monocular vision SLAM based on weight optimization combined particle filter) algorithm is proposed. The weights of all particles are reoptimized in the particle set and they are combined with the tendency of particles to degenerate and deplete. In this way, the chance of self replication of low weight particles is increased, thus increasing the diversity of the whole sample. Furthermore, the improved PF (particle filter) algorithm is applied to solve the problem of road sign observation of mobile robots, so as to expand its application scope. The results show that the mean road sign errors of the Monocular SLAM_WOCPF algorithm in two noise environments are 0.332/m and 0.441/m. The conclusion shows that the Monocular SLAM_WOCPF road sign observation method proposed in this paper can effectively improve the matching success rate of visual road signs and improve the observation quality. [ABSTRACT FROM AUTHOR]

Because of the overwhelming characteristics of computer vision technology, the trend of intelligent upgrading in sports industry is obvious. Video technical and tactical data extraction, big data analysis, and match assistance systems have caused profound changes to all aspects of the sports industry. One of the important applications is the playback and analysis of sports videos. People can observe the videos and summarize the experience of sports matches, and in this process, people prefer the computers to also interpret and analyze sports matches, which can not only help coaches in postmatch analysis but also design robots to assist in teaching and training. In this paper, we have examined and designed an automatic detection system for ping pong balls, in which the motion trajectory and rotation information of ping pong balls are mainly detected. To achieve this goal, the detection and tracking algorithm of ping pong balls based on deep neural network is used, and better results are achieved on the data set established by ourselves and the actual system test. After obtaining the position of the ping pong ball in the image, the rotation direction and speed of the ping pong ball are calculated next, and the Fourier transform-based speed measurement method and the CNN-based rotation direction detection method are implemented, which achieve better results in the testing of lower speed datasets. Finally, this paper proposes an LSTM-based trajectory prediction algorithm to lay the foundation for the design of table tennis robot by predicting the trajectory of table tennis. Experimental tests show that the proposed system can better handle the ping pong ball tracking and rotation measurement problems. [ABSTRACT FROM AUTHOR]

A multitarget real-time tracking system for panoramic video with multisensor information fusion dual neural networks is studied and implemented by combining dual neural networks, fused geometric features, and deep learning-based target real-time tracking algorithms. The motion model of multisensor information fusion is analyzed, the dual neural network perturbation model is introduced, and the state variables of the system are determined. Combined with the data structure model of multisensor information fusion, a least-squares-based optimization function is constructed. In this optimization function, the image sensor is constructed as an observationally constrained residual term based on the pixel plane, the inertial measurement unit is constructed as an observationally constrained residual term based on the motion model, and the motion relationship between sensors is constructed as a motion-constrained residual term to derive a mathematical model for real-time multitarget tracking of panoramic video. The simulation experimental results show that the integrated position estimation accuracy of the multisensor information fusion dual neural network-based panoramic video multitarget real-time tracking fusion algorithm is 10.5% higher than that of the optimal distributed panoramic video multitarget fusion algorithm without feedback. The results of the simulation experiments show that the integrated position estimation accuracy of the multitarget real-time tracking fusion algorithm for panoramic video improves by 10.96%, and the integrated speed estimation accuracy improves by 6.32% compared with the optimal distributed multitarget fusion algorithm without feedback. The proposed panoramic video multitarget real-time tracking algorithm based on the dual neural network can effectively improve the target tracking accuracy of the model on degraded frames (motion blur, target occlusion, out-of-focus, etc.), and the stability of the algorithm for target location and category detection is effectively improved by multiframe feature fusion. The research in this paper provides better technical support and research theory for panoramic video multitarget real-time tracking. [ABSTRACT FROM AUTHOR]

After the introduction of online learning mechanism, the traditional target tracking algorithm in football game video based on TLD has good tracking ability, but it will lose the target when the target is seriously obscured. Therefore, a soccer game video target tracking algorithm based on deep learning is proposed. The target detection algorithm of GoogLeNet-LSTM is used for faltung to obtain the feature mapping array. After processing, a high reliability candidate box for training and matching is obtained, and the feature maps of the detection results are collected to obtain the depth features required for tracking. Scale space discriminant tracking algorithm and Markov Monte Carlo algorithm are used to track single target or multi-target, respectively. Experimental results show that the average frame rate of the algorithm is maintained above 35 Hz, and the tracking time is about 12.5 s. The average center position deviation index is 39, the average coverage index is 40, and the resource utilization is low. The algorithm can track the target in the football game video well. [ABSTRACT FROM AUTHOR]

A distributed double-layered dynamic matrix control is proposed for large-scale systems. In the scheme, a large-scale system is first decomposed into several low-dimensional subsystems, and then a double-layered dynamic matrix control algorithm with distributed structure is developed for these subsystems. The distributed open-loop prediction equation of each subsystem is formed based on the predicted output of each local subsystem and effects of its interconnecting neighbor subsystems. Due to simultaneous optimization, at each prediction, the coupling effects of neighbor subsystems are not available in time. Thus, the assumed value is utilized instead. In the economic optimization stage, conflicts may occur among different economic optimization goals. Utopia-tracking strategy is introduced to optimize multiple steady-state targets. Then, the obtained steady-state target values are taken as reference values and tracked in subsequent dynamic control. The actual control move for each subsystem is finally calculated. The proposed algorithm is tested on Shell heavy oil fractionator benchmark, and the effectiveness is demonstrated by comparing with the typical double-layered dynamic matrix control algorithm. [ABSTRACT FROM AUTHOR]