Point Tracking Research Articles

An enhanced approach for joint configuration of a robot performing in a repetitive task

Human-Centric Manufacturing considers the integration of the industrial automation systems with human capabilities. It combines the strength, speed, repeatability and precision of automation with the intelligence, flexibility and skill of human operators. This advanced manufacturing concept strongly emphasis on human-assisted robotic operation. Recently, the interest in the human-robot cooperative industrial robot which can work together with human through physical interaction in the same space has increased. The direct teaching technology for human-robot cooperation enables an operator who is not used to robot programming to control the robot easily by teaching the task trajectory directly. However, because of the industrial robot inverse kinematics characteristics, there are multiple different inverse kinematics solutions in configure space. The planned trajectory based on the track points selected by the operator may be not efficient enough for the task. Hence, optimizing the joint configurations of a robot in a repetitive task becomes one of the increasingly important issues. In this paper, a mathematical model of the robotic joint configurations based on graph theory is developed, which takes into account repeat task constraints. An enhanced approach for the joint configuration of a robot in a repetitive task is proposed. It leads to the reduction of computational complexity and computing time. A numerical experiment and a case study of the optimization of time consumption in an industrial repetitive task are reported to show the effectiveness of the proposed approach.

Modelling of the sheet forming while 3-roller bending process

3-roller bending process was investigated using physical modelling and computer simulation. Main technological parameters influence on the formation of tube billet diameter are present; these main technological parameters are upper roller displacement and distance between axes of bearing rollers. Complete factorial experiment was conducted using bending machine, radius of the produced tube billet was set as response function. Conditions for conducting the complete factorial experiment using bending machine and techniques of tube billet radius estimation by graphical-analytical method are presented. At that least square method and SolidWorks software were applied. Regression equations for calculating tube billet diameter conditionally upper roller displacement and distance between axes of bearing rollers were obtained. Influence of these two factors on tube billet radius formation was demonstrated. Finite element method (FEM) computer simulation of the forming process was done with respect to parameters corresponding to parameters of physical modelling experiment using bending machine. FEM computer simulation was done using QForm software. QForm simulation was realized for elastic-plastic bending in terms of two-dimensional deformation. Point tracking was applied to calculate coordinates of the points of the formed sheet and bending parameters. It allowed estimation of the neutral line location in the formed sheet when bending stage was finished. Presented results of computer simulation are figures with trajectories of the tracked points; figures illustrating changing of distance between tracked points; graph of accumulated strain changing through sheet’s thickness. New criterion for neutral line (neutral surface) was proposed for sheet bending process. Results of the research can be effective when exploring Heausler AG bending equipment.

A New Method of Ski Tracks Extraction Based on Laser Intensity Information

At present, the mainstream laser point cloud classification algorithms are mainly based on the geometric information of the target. Nevertheless, if there is occlusion between the targets, the classification effect will be negatively affected. Compared with the above methods, a new method of ski tracks extraction using laser intensity information based on target reflection is presented in this paper. The method can complete the downsampling of the point cloud datasets of ski tracks under the condition that the information of the target edge is complete. Then, the clustering and extraction of ski tracks are effectively accomplished based on the smoothing threshold and curvature between adjacent point clouds. The experimental results show that, different from the traditional methods, the composite classification method based on the intensity information proposed in this paper can effectively extract ski tracks from the complex background. By comparing the proposed method to the Euclidean distance method, the clustering segmentation method, and the RANSAC method, the average extraction accuracy is increased by 16.9%, while the over extraction rate is reduced by 8.4% and the under extraction rate is reduced by 8.6%, allowing us to accurately extract the ski track point cloud of a ski resort.

Multi-Objective Spotted Hyena Optimization-Based Control of Grid-Tied PV System

This article describes the multi-objective spotted hyena optimization (MOSHO) based control of a three-phase three-wire grid-tied dual-stage PV system. The MOSHO delivers an optimized step size ( δ ) for the incremental conductance (InC) based maximum power point tracking (MPPT) algorithm, as well as optimizes the PI controller gains for DC bus voltage ( V d c ) regulation. The δ optimized MPPT facilitates the faster and more accurate tracking of maximum power point with fewer fluctuations at steady-state. The MOSHO optimized PI controller regulates the V dc and delivers better stability with reduced V dc variations in DC bus voltage during steady-state and dynamic states, i.e. irradiation variation, abnormal and unbalanced grid voltage. The optimized DC bus generates an accurate loss component of current, which further enhances the voltage source converter (VSC) performance in terms of precise reference currents generation and power quality improvement. The proposed system performs satisfactorily in a MATLAB simulation environment as per IEEE519 standards.

Assessing Heavy Precipitation Risk Associated with Tropical Cyclones in China

Abstract Tropical cyclone precipitation (TCP), accounting for some of the most extreme rainfall events, can lead to severe flooding and landslides, which often occur together as compound natural hazards during a tropical cyclone landfall. The impact due to TCP is largely associated with its intensity and spatial extent as the storm approaches landfall. Yet it is not entirely clear how TCP intensity and spatial extent vary from one tropical cyclone to another. In this study, we employ an advanced geostatistical framework to determine the TCP intensity and spatial extent along cyclone tracks for different cyclone categories, defined using the wind speed and tropical cyclone lifetime maximum intensity (LMI) at each track point (“point intensity-LMI”). The results show that when a tropical cyclone with an LMI of a supertyphoon makes landfall and has weakened to tropical storm strength it usually produces the most intense rainfall and covers the largest spatial extent. The total TCP amount estimated using the varying spatial extent helps to determine more accurately the amount of seasonal rainfall that is from tropical cyclones in China. We also determined the rainfall trend from 1951 to 2019 for TCP and found that when compared with the inland stations the historical TCP rainfall trend in those stations near the coastline of China is significantly increasing. Significance Statement Heavy rainfall caused by tropical cyclones has caused huge direct or indirect economic losses in the coastal areas of China. This impact is particularly significant when the rainfall intensity is high and the area of heavy rainfall is extensive. Here we investigate the rainfall intensity and spatial extent by classifying and comparing the different types of tropical cyclones impacting China with varying intensities. To do this, we group the tropical cyclone tracks of the western North Pacific Ocean during the last seven decades according to the strength of wind speed across the cyclone tracks. We found that the largest areas and heaviest intensities of rainfall occur when a supertyphoon has weakened to a tropical storm at landfall. When considering all tropical cyclones and their rainfall contribution to rainfall over land stations, we found that tropical cyclone rainfall has become heavier in most coastal areas of China.

Intraluminal Pressure, Multi‐Dimensional Field Imaging and Fluid Volume Recordings as a Useful Tool to Determine Peristaltic Propulsion

IntroductionPeristalsis is a collective process of intestinal muscle contractions for the passage of food through the gastrointestinal tract. Although, peristalsis has been extensively studied using spatiotemporal mapping and pressure transducers both in vivo and in vitro, the quantitative analysis of peristaltic propulsion is not fully understood. Lack of a definitive tool therefore, limited drug discovery in the field of constipation including IBSC. In this study, we used directional lighting, advanced field‐imaging techniques together with intraluminal pressure recordings to determine intestinal diameter, frequency of longitudinal muscle activity and pressure changes as well as velocity of anterograde and retrograde contractions and volume output measurements to help determine the net peristaltic activity.MethodsThe basal activity of intestinal peristalsis in terms of intraluminal pressure (ILP) changes, real‐time changes in longitudinal muscle activity and intestinal lumen diameter were measured in approximately 5 cm long segments from jejunum of mouse small intestine (male, NIH Swiss) in physiological Ringer solution. Intraluminal pressure was recorded using pressure transducers connected to the oral and aboral end of each segment mounted in Perfusion Bath for Tubular Organs, (Harvard apparatus, USA). Longitudinal muscle activity was studied using CVX400 series vision system, and LumiTrax™multi‐spectrum light (Keyence, USA) using multiple tracking points in each intestinal segment. The number, strength, and amplitude of oscillations in terms of intraluminal pressure changes and longitudinal muscle activity was analyzed using custom written programs. Luminal volume output was measured using a photo‐electric drop counter unit.ResultsThe number, amplitude, duration, and frequency of high and low amplitude changes in ILP and longitudinal muscle activity was determined using a lab‐written program. The frequency of longitudinal muscle activity correlated well with the frequency of low and high amplitude pressure changes. Frequency of both these oscillations were found to be 0.7 Hz. A reduction in the ILP was found to induce high amplitude contractions which subsided as the ILP increased. Changes in intestinal diameter with time correlated to ILP changes. A reduction in luminal diameter caused an increase in ILP and when not fully compensated caused increased fluid output. The mean velocity of the contractions over time in the regions tracked was determined to be 2.5 – 2.7mm/sec with peak anterograde contraction velocity of ‐4.06 mm/sec and retrograde contractions of 12 mm/sec. This mean velocity in presence of physiological Ringer solution was thought to determine the direction of contractions along the length of the GI tract under normal conditions.InferenceFrequency of longitudinal muscle activity and ILP oscillation showed similar frequency suggesting common pacemaker activity. The velocity of the contraction and volume output over time will help determine the overall peristaltic movement and could be used as a helpful index to gauge constipation.

A trajectory map matching algorithm via exploring the average directional features of continuous windows

Many location-based services require a pre-processing step of map matching. Due to the error of the original position data and the complexity of the road network, the matching algorithm will have matching errors when the complex road network is implemented, which is therefore challenging. Aiming at the problems of low matching accuracy and low efficiency of existing algorithms at Y-shaped intersections and roundabouts, this paper proposes a space-time-based continuous window average direction feature trajectory map matching algorithm (STDA-matching). Specifically, the algorithm not only adaptively generates road network topology data, but also obtains more accurate road network relationships. Based on this, the transition probability is calculated by using the average direction feature of the continuous window of the track points to improve the matching accuracy of the algorithm. Secondly, the algorithm simplifies the trajectory by clustering the GPS trajectory data aggregation points to improve the matching efficiency of the algorithm. Finally, we use a real and effective data set to compare the algorithm with the two existing algorithms. Experimental results show that our algorithm is effective.

PARTICLE SWARM OPTIMIZATION FOR UNDERWATER GRAVITY-MATCHING: APPLICATIONS IN NAVIGATION AND SIMULATION

Abstract. This paper developed a two-stage solution for underwater gravity matching navigation based on the particle swarm optimization algorithm and affine transformation. The first stage established a starting point, and the second stage treated the matching track gained through affine transformation as a particle at the same starting point, followed by the application of the particle swarm optimization algorithm to obtain the optimal solution. To avoid falling into a local optimal solution, a convergence factor was incorporated into the optimization process in addition to the linear decreasing weight. This was followed by the addition of a constraint on the velocity and position of the particles, which was then updated in an iterating process. Two simulated navigation tracks were employed for experiments. The results revealed that the algorithm was capable of matching actual tracks in real time. Additionally, the results were found to be consistent with those obtained from the real-world tracks, with all the locations and gravity anomaly deviations falling within a tolerable range. However, when there were too many matching track points, the algorithm efficiency declined in terms of calculation time. This entails improving the algorithm through the segmentation technique.

Moving Object Tracking Based on Sparse Optical Flow with Moving Window and Target Estimator.

Moving object detection and tracking are technologies applied to wide research fields including traffic monitoring and recognition of workers in surrounding heavy equipment environments. However, the conventional moving object detection methods have faced many problems such as much computing time, image noises, and disappearance of targets due to obstacles. In this paper, we introduce a new moving object detection and tracking algorithm based on the sparse optical flow for reducing computing time, removing noises and estimating the target efficiently. The developed algorithm maintains a variety of corner features with refreshed corner features, and the moving window detector is proposed to determine the feature points for tracking, based on the location history of the points. The performance of detecting moving objects is greatly improved through the moving window detector and the continuous target estimation. The memory-based estimator provides the capability to recall the location of corner features for a period of time, and it has an effect of tracking targets obscured by obstacles. The suggested approach was applied to real environments including various illumination (indoor and outdoor) conditions, a number of moving objects and obstacles, and the performance was evaluated on an embedded board (Raspberry pi4). The experimental results show that the proposed method maintains a high FPS (frame per seconds) and improves the accuracy performance, compared with the conventional optical flow methods and vision approaches such as Haar-like and Hog methods.

Analysis methodology of compatibility between motion control and mechanical architecture of a newly designed gantry virtual track train and the path-tracking control strategy

This study aimed to propose a gantry virtual track train (G-VTT) architecture and investigate the path-tracking control of it. Based on the decoupling control theory, the concept and judgment criterion of the path-tracking independence of the G-VTT was proposed to provide a method to analyzing the compatibility between motion control and mechanical architecture, and instructing the design of the architecture of the G-VTT that could realize autonomous path-tracking with simple control strategy. The controllability and observability of the path-tracking control system were discussed from the perspective of vehicle kinematics and the decouplibility of each tracking point's lateral motion and the path-tracking independence of the vehicle was proved. The distributed virtual driving (DVD) model based on self-adaptive preview PID algorithm was proposed to achieve independent path-tracking of each axle. This model consists of two parts: forward preview model based on the fractional calculus theory simulating the driver's visual field and the parameter self-tuning PID controller based on variable universe fuzzy control theory (VUF-PID controller). The effectiveness and adaptability of the DVD model were verified by co-simulation test. The results show that the VUF-PID controller has an excellent control performance and could realize the self-tuning of PID parameters effectively and could adapt to the noticeable hysteresis effect with the forward preview model introduced. Moreover, the VUF-PID controller could significantly improve the curve-passing stability of the G-VTT, and exhibits excellent adaptability to the traveling speed, curve radius, and vehicle payload. Even when the train travels under an adverse operating condition with lateral acceleration about 3.2m/s2, the maximum tracking error could still be kept below ±0.02 m.

Applicability of wind products retrieved from wind lidar in the winter games

Abstract Based on the 10-min average wind speed and wind direction data observed by automatic stations at the starting point and midway of the snow track in the “14th National Winter Games”, the wind product accuracy of wind lidar from December 1, 2019 to January 31, 2020 was analyzed. The results show that the mean relative deviation (MRD), standard deviation of relative deviation (STDRD ) and correlation coefficient (R) of wind direction data are better than wind speed data. The MRD is largest when the average wind speed of the ground observation is about 3 m/s, reaching 55%. The wind speed retrieved by the lidar is higher than that observed by automatic station when the average wind speed is lower than 10 m/s. When the average wind speed is higher than 10 m/s, the wind speed retrieved by the lidar is lower than ground observations. The detection accuracy of the lidar wind direction at the automatic station No.4 is better than that at the automatic station No.3. For the detection of wind speed, the mean absolute error (MAE) is larger, the R was slightly lower, but the mean error (ME), the MRD and the STDRD are better at the automatic station No.4. As the SNR increases, ME of the average wind speed decreases, and the relative deviations (RD) of wind speed and wind direction gradually concentrate on zero.

Latent variable point-to-point iterative learning model predictive control via reference trajectory updating

A latent variable point-to-point iterative learning model predictive control algorithm (LV-PTP-ILMPC) that is combined with the reference trajectory updating strategy is proposed in this paper. It is different from the traditional point-to-point iterative learning model predictive control (PTP-ILMPC), which is developed in the original variable space to track a fixed reference trajectory. The proposed algorithm uses a model constructed by dynamic partial least squares (DyPLS) to extract the principal components of multiple input variables in each batch and designs the PTP-ILMPC controller in the latent variable space. Moreover, creating a reference trajectory updated along the batch direction through the desired points. The updating reference trajectory, modified according to the tracking error information, fully utilizes the degrees of freedom of nonspecific tracking points in the latent variable space. The proposed algorithm uses DyPLS to decouple the multiple-input, multiple-output system (MIMO) into a single-input, single-output system, simplifying the multivariable control problem. In addition, the updated reference relaxes the constraints on the system output so that the algorithm has a faster convergence speed and a more comprehensive range of applications. Two studies are proposed to show the effectiveness of the algorithm.

Deep flight track clustering based on spatial–temporal distance and denoising auto-encoding

The rapid development of the aviation industry imposes an urgent need for airspace traffic management. Meaningful clustering of flight tracks is of paramount importance for efficient operation and management of increasingly complex aerial space and traffic. Two key components exist in track clustering: similarity metric and clustering method. Most of the existing studies on track similarity metrics only consider the spatial coordinates of the track points without taking into consideration of the rich information of the track data, such as flight heading and flight speed, on the measurement of track similarity. In addition, temporal properties and the derived features of the flight tracks shall be utilized to reveal the underlying patterns and overcome distortions from noise. In this paper, we propose a track similarity based on the spatial–temporal characteristics of flight tracks and a Deep Temporal Clustering method using a denoising autoencoder. Our proposed method employs the Deep Temporal Denoising Auto-encoding network to extract the latent representations of the track sequences. By extending the idea of k-means clustering, Deep Temporal Clustering groups the flight tracks with a Time Clustering Layer. Experiments are conducted using Automatic Dependent Surveillance-Broadcast track data. In comparison with classical and state-of-the-art methods, among all cases, our Deep Temporal Clustering method achieved a much-improved performance of more than 57.3%. When we introduce noise to the track records and increase its magnitude, the performance of our method degrades but the trend slows down as the noise magnitude increases. The change is less than 7% and, in some cases, is close to zero, which demonstrates the robustness of our method to noise.

Concentric Scanning Strategies for Laser Powder Bed Fusion: Porosity Distribution in Practical Geometries.

Besides the optimisation of process parameters such as laser power or scan speed, the choice of the scan path represents a possibility to optimise the laser powder bed fusion process even further. The usual hatching strategy creates a homogeneous microstructure but makes it necessary to switch the laser off and on after each scan vector, which can slow down the fabrication. Moreover, the end of each scan vector is a location susceptible to the creation of keyhole pores. In this work, these disadvantages were meant to be avoided by using scan strategies that consist of longer paths and thus less end of track points. To this end, an open-source tool to tailor the LPBF G-code to geometric part features and advanced path configurations was developed and embedded into a co-visualization platform. With this tool, specimens built with four different types of paths were fabricated and the effect of these alternative scan strategies on pore distributions and path neighbourhood was investigated using micro-computed tomography. In the examined example geometry, a spiral scan pattern reduced the distance the laser had to jump between scanning by 78%. However, with the alternative path patterns, the defect architecture was strongly dependant on the part geometry and increased the overall porosity to 0.42%. Respective alleviation approaches are therefore necessary and are discussed in the remainder of this work.

Based on 0.35 T magnetic resonance-guided radiotherapy, what are the nonisotropic PTV margins required for conventional prostate radiotherapy?

This study aims to calculate planning target volume (PTV) margins for the prostate and seminal vesicles (SVs) from the use of magnetic resonance-guided radiation therapy (MRgRT). And whether nonisotropic PTV margins are beneficial for these structures. Organ motion is linked to the displacement of the prostate and SVs. From the use of MRgRT, the nearby organs at risk (OAR) can be visualized both inter- and intrafraction. This study looked to determine if there is a correlation between interfractional OAR changes and displacements to the prostate and SVs. Inter- and intrafractional data from 20 consecutive prostate cancer patients treated using extreme hypofractionated 0.35 T MRgRT indicated prostate and SV motion during treatment. Tracking points (TPs) on 2D sagittal cine-MRI enabled assessment of this intrafractional motion. To determine a correlation between rectal changes and target displacements, the rectal diameter (RD) changes were compared against the displacement differences (DDs) at the prostate and SVs. Eighty percent of patients required intrafractional imaging corrections during radiotherapy, including 16/100 fractions due to rectal volume increases and 24/100 fractions due to bladder volume increases. The frequency of ≥3 mm intrafraction displacement was considerably greater in TPs in the SV than in the prostate. A moderate positive correlation (R2 = 0.417) was shown between RD changes and DDs at the level of the prostate and SVs. The PTV margins required for 90% of the patient cohort for prostate and SVs are nonuniform in different directions, and the margin is larger for SVs. Organ motion contributed toward prostate and SV displacements and showed the importance of a robust bladder and rectal-filling protocol.

Tracking and impact point of survey rocket by Telemetry and Slant-Range device.

This work presents an alternative method of getting tracking, and the impact point of the actual flight of a rocket, by telemetry data and slant-range device. The tracking and impact point data were obtained from an actual flight path by merging the angular components of a telemetry antenna (Azimuth, and Elevation) and the radial distance information provided by the slant-range device. The position components were analyzed with the telemetry antenna in automatic mode, target tracking, comparing with the tracking results performed by the radar. The result obtained by the composition of the coordinates of the telemetry/slant-range set, it was observed that the point of impact generated by this group had a distance of 237.64 (meters), in relation to the impact generated by the tracking of the radar. Indicating a significant reduction of the search area and can be used as na alternative form of use. It allows you to provide additional location information for payload recovery around the actual point of impact.

Perception of interestingness at the insertion point of laugh track

Perception of interestingness at the insertion point of laugh track

Robust Intelligent Learning Algorithm Using Random Forest and Modified-Independent Component Analysis for PV Fault Detection: In Case of Imbalanced Data

Photovoltaic (PV) systems are vulnerable to failures due to undesired conditions. Faults can occur unpredictably and remain challenging to recognize. In this study, inverter fault, voltage sag, partial shading, and open circuit were considered as the PV faults. However, the faults become eight target classes since each fault considers two different conditions: intermediate power point tracking and maximum power point tracking. Machine learning techniques have recently become the most interesting methods for solving PV failures. This paper proposes a random forest and modified independent component analysis (RF-MICA) to detect the occurrence of PV faults. The MICA was developed for dimensionality reduction for enhanced performance, whereas previous studies only focused on principal component analysis. Two strategies are introduced to address an imbalanced dataset: the synthetic minority oversampling technique as scenario 1 and random undersampling as scenario 2 for oversampling and undersampling methods, respectively. These techniques are essential for investigation because PV fault data can become unbalanced, and they have not been fully addressed in previous studies. The results indicated that the proposed model performs better than other algorithms, with high accuracy and low computational time. RF-MICA yielded accuracy rates of 99.88% and 99.43% for scenarios 1 and 2, respectively.

On-Board Flickering Pixel Dynamic Suppression Method Based on Multi-Feature Fusion

The blind pixel suppression is the key preprocess to guarantee the real-time space-based infrared point target (IRPT) detection and tracking. Meanwhile, flickering pixels, as one of the blind pixels, is hard to suppress because of randomness. At present, common methods adopting a single feature generally need to accumulate dozens or hundreds of frames to ensure detection accuracy, which cannot update flickering pixels frequently. However, with low detection frequency, the flickering pixels are easily miss detected. In this paper, we propose an on-board flickering pixel dynamic suppression method based on multi-feature fusion. The visual and motion features of flickering pixels are extracted from the result of IRPT detection and tracking. Then, the confidence of flickering pixel evaluation strategy and selection mechanism of flickering pixel are introduced to fuse the above features, which achieves accurate flickering pixel suppression using a dozen frames. The experimental results evaluated on the real image of four scenarios show that the blind pixel false detection rate of the proposed method is no more than 1.02%. Meanwhile, evaluated on the simulated image, the flickering pixel miss suppression rate is no more than 2.38%, and the flickering pixel false suppression rate is 0. The proposed method could be an addition to most other IRPT detection methods, which guarantees the near-real-time and reliability of on-board IRPT detection applications.

EVALUATION METHODOLOGY ON TRAJECTORY OF INBOUND SINGLE SHIP USING SIMILARITY MEASUREMENT BETWEEN PLANAR CLOUDS

In order to evaluate the ship trajectory more reasonable based on the quantitative information. This paper presents a new approach to evaluate the inward-port single ship trajectory quantitatively based on ship-handling simulator. First, a ship tracking points generating algorithm is proposed to generate sufficient tracking points in order to address the issue that the sample information is not enough on the ship simulator. Second, three reference tracking belts are established based on the sample data and cloud drop contribution degrees for the scenario that the collected samples information are enough. Finally, a quantitative score evaluation method that combines the qualitative information and the quantitative information is proposed, the similarity measurement results verify that the MES algorithm is more reasonable, the evaluation results of inward-port single ship trajectory illustrative that the proposed method is effective when applied to quantitative evaluation problems.