Motion In Region Research Articles

Fault diagnosis and failure analysis of motor controller by the approach of Bayesian inference

The paper consists of two parts. First an outline is given of the functions of a tyre as a vehicle component with a discussion of the development of mathematical models describing steady–state cornering behaviour. Also, the concept of effective tyre characteristics are discussed, which represent the combined effects of tyre and elastic suspension and steering properties. The second part considers the motion of the vehicle over a horizontal flat surface with the longitudinal speed constant. After a discussion of steady–state cornering behaviour and the introduction of a handling diagram showing regions of under–steer and over–steer, and regions of stable and unstable motion, the dynamic solution of the plane motion has been studied. In the phase plane, domains of attraction can be indicated beyond which the motion becomes difficult or impossible to control.

Плотность энергетического спектра электрона в поле изображения и запирающем электрическом поле

In the semiclassical approximation, the density of the electron energy spectrum near the metal surface is described, when electron is bound by the image field and the blocking electrostatic field. In the system under consideration, the confinement mechanism is realized, and the energy spectrum for the motion of an electron in the direction perpendicular to the metal surface is completely discrete. The density of states of the energy spectrum is expressed in terms of elliptic integrals, the argument of which is a sigmoidal function. When the field is turned off, it becomes the Heaviside step function. A dimensionless energy parameter is introduced, which determines the intervals with qualitatively different changes in the width of the classically accessible region of motion. For large positive values of the energy parameter, the spectrum density asymptotically tends to the density in the triangular potential with the addition of the Coulomb logarithmic correction, and for negative values of the energy parameter, the spectrum density tends to dependence for a one-dimensional Coulomb potential. Approximate expressions are obtained for the spectrum density in terms of elementary functions in a wide range of electron energies and electric field strength.

Human Activity Recognition Based on Transfer Learning with Spatio-Temporal Representations

A Gait History Image (GHI) is a spatial template that accumulates regions of motion into a single image in which moving pixels are brighter than others. A new descriptor named Time-Sliced Averaged Gradient Boundary Magnitude (TAGBM) is also designed to show the time variations of motion. The spatial and temporal information of each video can be condensed using these templates. Based on this opinion, a new method is proposed in this paper. Each video is split into N and M groups of consecutive frames, and the GHI and TAGBM are computed for each group, resulting spatial and temporal templates. Transfer learning with the fine-tuning technique has been used for classifying these templates. This proposed method achieves the recognition accuracies of 96.50%, 92.30% and 97.12% for KTH, UCF Sport and UCF-11 action datasets, respectively. Also it is compared with state-of-the-art approaches and the results show that the proposed method has the best performance.

Application of human motion recognition technology in extreme learning machine

Human motion recognition is a branch of computer vision research and is widely used in fields like interactive entertainment. Most research work focuses on human motion recognition methods based on traditional video streams. Traditional RGB video contains rich colors, edges, and other information, but due to complex background, variable illumination, occlusion, viewing angle changes, and other factors, the accuracy of motion recognition algorithms is not high. For the problems, this article puts forward human motion recognition based on extreme learning machine (ELM). ELM uses the randomly calculated implicit network layer parameters for network training, which greatly reduces the time spent on network training and reduces computational complexity. In this article, the interframe difference method is used to detect the motion region, and then, the HOG3D feature descriptor is used for feature extraction. Finally, ELM is used for classification and recognition. The results imply that the method proposed here has achieved good results in human motion recognition.

Investigation of infrared dim and small target detection algorithm based on the visual saliency feature

Infrared dim and small target detection has an important role in the infrared thermal imaging seeker, infrared search and tracking system, space-based infrared system and other applications. Inspired by human visual system (HVS), based on the fusion of significant features of targets, the present study proposes an infrared dim and small target detection algorithm for complex backgrounds. Firstly, in order to calculate the target saliency map, the proposed algorithm initially uses the difference of Gaussian (DoG) and the contourlet filters for the preprocessing and fusion, respectively. Then the multi-scale improved local contrast measure (ILCM) method is applied to obtain the interested target area, effectively suppress the background clutter and improve the target signal-to-clutter ratio. Secondly, the optical flow method is used to estimate motion regions in the saliency map, which matches with the interested target region to achieve the initial target screening. Finally, in order to reduce the false alarm rate, forward pipeline filtering and optical flow estimation information are applied to achieve the multi-frame target recognition and achieve continuous detection of dim and small targets in image sequences. Experimental results show that compared with the conventional Tophat (TOP-HAT) and ILCM algorithms, the proposed algorithm can achieve stable, continuous and adaptive target detection for multiple backgrounds. The area under curve (AUC) and the harmonic average measure F1 are used to measure the overall performance and optimal performance of the target detection effect. For sky, sea and ground backgrounds, the test results of proposed algorithm for most sequences are 1. It is concluded that the proposed algorithm significantly improves the detection effect.

Solid‐State Molecular Motions in Organic THz Generators

AbstractOrganic nonlinear optical salt crystals are widely used as efficient broadband THz generators. Although solid state molecular motions of organic crystals can greatly influence THz generation characteristics, their origin and effects on THz photonics are not clearly identified. In this work, the origin of solid‐state molecular motions of the state‐of‐the‐art nonlinear optical organic salt crystals and their effects on THz generation characteristics are theoretically investigated. A model crystal, HMQ‐TMS (2‐(4‐hydroxy‐3‐methoxystyryl)‐1‐methylquinolinium 2,4,6‐trimethylbenzenesulfonate) with large macroscopic optical nonlinearity, which is very attractive for intense broadband and narrowband THz wave generation, is chosen. The solid‐state molecular vibrations of HMQ‐TMS crystals can be classified in three frequency regions: phonon mode region, intramolecular motion region, and their mixing region. For the first time for ionic organic crystalline THz generators, the contributions of cationic chromophores and anionic matchmakers on each of vibrational modes are quantitatively separated. In addition, the influence of solid‐state molecular vibrations of HMQ‐TMS crystals on the generated THz spectra is investigated. These results provide an essential information for design of new organic nonlinear optical salt crystals for THz generators as well as detectors and for optimization of THz generation performance.

Towards accurate HDR imaging with learning generator constraints

High dynamic range (HDR) image generation is a useful technology in various applications. An easy way to obtain an HDR image is the multiple exposures fusion technique which fuses a set of sequential exposures. However it suffers from the ghosting artifacts for scenes with significant motion objects, which is the key challenge in HDR imaging. Detecting and removing ghosting artifacts is a crucial issue for automatically generating HDR images of dynamic scenes. Although previous methods align the low dynamic range (LDR) images or detect motion regions to remove the ghosting artifacts in the final HDR, they still cannot generate a well-pleasing HDR image. In this paper, we propose a novel deep neural network with learning generator constraints called GHDRNet that blends information from all the exposures. Different from previous methods which only use ground truth to learn parameters of the network for HDR image reconstruction, our method is based on a novel successive network which not only estimates HDR results from dynamic scenes but also restores the static LDR images from the estimated HDR image. This special designed network restrains the estimated HDR image by restoring the corresponding LDR images. To capture deep hierarchical features and increase the receptive field for recovering the abundant details, we also propose an enhancement block (EBlock) that is a topology structure to aggregate several scale features. Furthermore, considering the cumbersome networks have a redundant parameter, we introduce a light-weight residual module to EBlock which effectively reduces the network parameters. Extensive evaluations show the advantages of our method over related state-of-the-art methods on three benchmarks.

Moving Object Detection Based on Background Compensation and Deep Learning

Detecting moving objects in a video sequence is an important problem in many vision-based applications. In particular, detecting moving objects when the camera is moving is a difficult problem. In this study, we propose a symmetric method for detecting moving objects in the presence of a dynamic background. First, a background compensation method is used to detect the proposed region of motion. Next, in order to accurately locate the moving objects, we propose a convolutional neural network-based method called YOLOv3-SOD for detecting all objects in the image, which is lightweight and specifically designed for small objects. Finally, the moving objects are determined by fusing the results obtained by motion detection and object detection. Missed detections are recalled according to the temporal and spatial information in adjacent frames. A dataset is not currently available specifically for moving object detection and recognition, and thus, we have released the MDR105 dataset comprising three classes with 105 videos. Our experiments demonstrated that the proposed algorithm can accurately detect moving objects in various scenarios with good overall performance.

RETRACTED: Swimming target detection and tracking technology in video image processing

The new system is presented for target detection swimming, tracking multiple targets in a video sequence. Since the output of the system is based on target motion, to use background subtraction to move the area within each video frame of the first segment foreground and background. A new method proposed for detecting drowning in a person swimming in a data using video footage. The proposed Swimming target detection and tracking technology based on Discrete Cosine Transform Algorithm, Target Detection Algorithm, and Traditional Cam-Shift Algorithm. For background extraction and updating, use the frame-by-frame differential Discrete Cosine Transform Algorithm used to the exact motion region of the entire video section in image processing technology based analysis. Static and dynamic feature detection identification normal swimmers and drowning swimmers. Swimming-based data are collected in real time using a camera on the surface of the water, including a video image sequence with the main observation swimming and behavior analysis based system immersion and three steps to detect swimming. By combining frame subtraction and background subtraction, the advanced moving Target Detection Algorithm can detect the full area of interest. Then, with average particle filtering, analysis of Traditional Cam Shift Algorithm, it can automatically select the target for the resulting detection results and introduce a new person tracking method. Swim target detection and track results to analyze motion parameter estimation algorithms. Finally, the purpose of the set of human diagnostics and follow-up tests is to test algorithmic efficiency.

Impact of radiation pressure and circumstellar dust on motion of a test particle in Manev’s field

In this paper, we present a study on the impact of radiation pressure and circumstellar dust on the motion of a test particle in the framework of the restricted four-body problem under the Manev’s field. We show that the distribution of equilibrium points on the plane of motion is slightly different from that of the classical Newtonian problem. With the aid of the Lyapunov characteristic exponents, we show that the system is sensitive to changes in initial conditions; hence, the orbit of the system is found to be chaotic in the phase space for the given initial conditions. Furthermore, a numerical application of this model to a stellar system (Gliese 667C) is considered, which validates the dependence of the equilibrium points on the mass parameter. We show that the non-collinear equilibrium points of this stellar system are distributed symmetrically about the x-axis, and five of them are linearly stable. The basins of attraction of the system show that the equilibrium points have irregular boundaries, and we use the energy integral and the Manev parameter to illustrate the zero-velocity curves showing the permissible region of motion of the test particle with respect to the Jacobi constant.

An Intelligent Augmented Reality Training Framework for Neonatal Endotracheal Intubation.

Neonatal Endotracheal Intubation (ETI) is a critical resuscitation skill that requires tremendous practice of trainees before clinical exposure. However, current manikin-based training regimen is ineffective in providing satisfactory real-time procedural guidance for accurate assessment due to the lack of see-through visualization within the manikin. The training efficiency is further reduced by the limited availability of expert instructors, which inevitably results in a long learning curve for trainees. To this end, we propose an intelligent Augmented Reality (AR) training framework that provides trainees with a complete visualization of the ETI procedure for real-time guidance and assessment. Specifically, the proposed framework is capable of capturing the motions of the laryngoscope and the manikin and offer 3D see-through visualization rendered to the head-mounted display (HMD). Furthermore, an attention-based Convolutional Neural Network (CNN) model is developed to automatically assess the ETI performance from the captured motions as well as identify regions of motions that significantly contribute to the performance evaluation. Lastly, augmented user-friendly feedback is delivered with interpretable results with the ETI scoring rubric through the color-coded motion trajectory that classifies highlighted regions that need more practice. The classification accuracy of our machine learning model is 84.6%.

A Planar Five-body Problem in a Framework of Heterogeneous and Mass Variation Effects

Abstract The aim of the present paper is to study the effects of heterogeneous oblate spheroid and variable mass on the motion of the fifth infinitesimal body in the frame of the circular restricted five-body problem, with the imposition that the three primaries are placed at the vertices of an equilateral triangle and the fourth primary is placed at the center of the equilateral triangle. By using Jeans law and Meshcherskii space transformation, we evaluate the equations of motion and find a quasiJacobian integral. We determine the locations of equilibrium points, the regions of motion, and the attracting domain of in-plane motion. Furthermore, the effects of heterogeneous oblate spheroid and variable mass have been examined with the help of Poincaré surfaces of section. We studied the linear stability of equilibrium points and found that all of them are unstable.

On the modified circular restricted three-body problem with variable mass

In the present work, we shall show an exhaustive numerical analysis of the dynamical behavior of the test particle in the modified restricted three-body problem with variable mass in which the extra effect of the three-body interaction is also taken into account. This additional force ingredient appears in the potential of the classical problem as a new extra term. As the main results, we determine the motion for test particle, under the effect of three-body interaction, which varies its mass according to Jeans’ law (Jeans (1928)). The number and existence of the libration points along with their stability have been investigated as the function of value of the parameters which occur due to variable mass of the test particle. Moreover, the regions of the possible motion are also unveiled where the test particle is free to move. Furthermore, the multivariate version of the Newton-Raphson (NR) iterative scheme is used to determine the outcomes of the used parameters on the topology of the basins of convergence (BoC) linked to the libration points. The numerical analysis shows that the topology of the basins of convergence linked with the libration points is highly influenced by the used parameters. Moreover, we perform a systematic analysis to unveil how the regions of convergence are related with the number of required iterations and also with the corresponding probability distributions.

Video classification by fusing two-stream image template classification and pretrained network

A motion energy image (MEI) is a spatial template that collapses regions of motion into a single image in which more moving pixels are brighter than others. The forward single-step history image (fSHI) is a spatiotemporal template that shows the presence and direction of motion. Each video can be described using these templates. Recently, the popularity of deep learning architectures for human activity recognition encourages us to explore the effectiveness of combining them with these templates. Hence, three new methods are introduced to convert the problem of human activity recognition in video into image templates classification. In method 1, each video is split into N groups of consecutive frames, and the MEI is computed for each group. Transfer learning with the fine-tuning technique is used for classifying these templates. fSHIs or spatiotemporal templates are used for classification in method 2, similar to method 1. Fusing the two streams of these templates is introduced as method 3. Among these methods, method 3 outperforms the others and is called the proposed method. It achieves recognition accuracies of 92.60% and 93.40% for the UCF Sport and UCF-11 action datasets, respectively. Also, it is compared with state-of-the-art approaches, and the results show that the proposed method has the best performance.

The study of the fractal basins of convergence linked with equilibrium points in the perturbed (N+ 1)‐body ring problem

AbstractThe fractal basins of convergence (BoC) linked with the equilibrium points are explored in the(N + 1)−body ring problem under the effect of small perturbations in the Coriolis and centrifugal forces when the bodies are sources of radiation. The evolution of the positions and the stability of the libration points and the possible regions of motion are determined as the function of mass parameter, the Coriolis, and centrifugal and radiation parameters. In addition, the parametric variation of the effect of the small perturbations in the Coriolis and centrifugal forces on the stability of the equilibrium points are also illustrated numerically. The multivariate version of the Newton–Raphson(NR) iterative method is used to analyze the effect of the radiation parameters and mass parameter on the topology of the BoC.

The parametric oscillations of rotating rods under action of the axial beat load

The paper presents the results of investigation of the axial beat loads’ influence on the transverse rotating rods’ oscillations and their stability. The perforator's long drills are considered as objects of investigation.The analysis of different author’s papers that are studded the dynamics of oscillations of shafts and rotating rods is carried out. The relevance of the research topic is substantiated. The model of the considered dynamic system is described and equations of oscillations in space are given.The technique for investigation is presented. This technique is based on search for new bend forms of rotating rod by solving the equations of oscillations with using the Hubbolt time integration method and the polynomial functions (splines) that are described the current bend form. In it, the spline functions are found by current bend form approximation where each of the found functions is responsible to certain point of rod elastic line and describes the position of nearby points.Described technique was realized in a computer program with graphic user interface that is developed by author. Program allows to monitor for dynamics of the oscillatory motion of the modeled system in real-time by calculating and drawing the current band forms of the rotating rod during the oscillation.Diagrams with regions of stable and instable motion of the rods, that were found by different parameters and boundary conditions are shown. The analysis of the results is obtained and the conclusion about possibility of operating the equipment in certain frequency ranges is done. The space oscillating process of rotating rods is considered with account of the gyroscopic loads and geometric nonlinearity.

Research on the Dynamic Characteristics of Magnetic Bearing-rotor System with Auxiliary Bearing

Non-linear factors such as magnetic force and rub-impact force are comprehensively considered on the basis of the classic Jeffcott rotor system model, and the dynamic model of the magnetic bearing-rotor system is established. The dimensionless motion equation is obtained by introducing dimensionless parameters. The pattern types and distribution regions of adjacent fundamental periodic motions of the system are obtained based on multi-objective and multi-parameter co-simulation analysis, and the dynamic behaviour is analysed through three-dimensional bifurcation diagram, two-parameter bifurcation diagram, single-parameter bifurcation diagram and axis locus diagram. The reasonable matching range of parameters of system and speed ratio is obtained in this paper, which optimizes the structural parameter design of the rotor system and determines its reasonable and stable working interval.

Stability of the coplanar planetary four-body system

We consider the coplanar planetary four-body problem, where three planets orbit a large star without the cross of their orbits. The system is stable if there is no exchange or cross of orbits. Starting from the Sundman inequality, the equation of the kinematical boundaries is derived. We discuss a reasonable situation, where two planets with known orbits are more massive than the third one. The boundaries of possible motions are controlled by the parameter c2E. If the actual value of c2E is less than or equal to a critical value (c2E)cr, then the regions of possible motions are bounded and therefore the system is stable. The criteria obtained in special cases are applied to the Solar System and the currently known extrasolar planetary systems. Our results are checked using N-body integrator.

Calculation of the Thermohydraulic Efficiency of Porous Direct-Flow Steam-Generating Channels

Results of calculation of the efficiency of porous direct-flow steam-generating channels in the transition region of motion of a heat-transfer agent with boundary conditions of the first kind have been presented. The obtained data have been compared with the results of calculations for a smooth-walled tube. It has been shown that positive values of geometric coefficients of efficiency of such a channel can be obtained when water is used as the heat-transfer agent. For the investigated parametric range of the indicated channels, no positive values of energy coefficients of efficiency were found. The dependences of the efficiency coefficients of a porous model channel on its basic operating-structural parameters have been analyzed.

Smoke Image Recognition Method Based on the optimization of SVM parameters with Improved Fruit Fly Algorithm

The traditional method of smoke image recognition has low accuracy. For this reason, we proposed an algorithm based on the good group of IMFOA which is GMFOA to optimize the parameters of SVM. Firstly, we divide the motion region by combining the three-frame difference algorithm and the ViBe algorithm. Then, we divide it into several parts and extract the histogram of oriented gradient and volume local binary patterns of each part. Finally, we use the GMFOA to optimize the parameters of SVM and multiple kernel learning algorithms to Classify smoke images. The experimental results show that the classification ability of our method is better than other methods, and it can better adapt to the complex environmental conditions.