Real-time Tracking Performance Research Articles

Gradient projection-based trajectory tracking control for automatic guided vehicle

In order to solve the problems of long operation time for solving the trajectory tracking controller and low real-time tracking. This paper proposes an improved model predictive control algorithm. By introducing the gradient projection method (GPM), the projection direction is used as the fastest descent direction of the objective function, which is used to reduce the number of iterations of the operation. Meanwhile, this paper adds constraints and relaxation factors to improve the trajectory tracking accuracy and prevent the controller operations from falling into local optimal solutions. Simulation by Simulink, the improved model predictive control algorithm reduces the average operation time by 24.74% and the single maximum operation time by 36.04%, effectively improving the real-time trajectory tracking performance. Finally, the verification experiment of trajectory tracking control is carried out by actual vehicle, proving the method’s effectiveness.

Investigation of Legendre polynomials expanded adaptive controller with inverse compensation for high frequency tracking of electro-hydraulic force systems

Accurate force tracking of an electro-hydraulic force system (EHFS) is of great significance in various industrial applications. As the EHFS is inevitably confronted with hydraulic nonlinearities, dynamic variations and uncertain disturbances, the real-time force tracking performance is generally unsatisfactory, especially for high frequency command force signals. For reducing the force tracking error with relatively high frequency inputs, a Legendre polynomials expanded adaptive controller with inverse compensation is proposed in this paper. The proposed controller is constructed by introducing an offline designed inverse compensation (IC) controller and an online adaptive controller to the EHFS governed by traditional Proportional Integral (PI) controller, in which the former IC controller is acting as the inner loop controller and the latter adaptive controller is regarded as an outer controller. The inner loop IC controller with fixed control parameters is offline designed on the basis of traditional PI controller by means of the generalized projection identification algorithm and the zero magnitude error tracking technology, focusing on extending the real-time force tracking bandwidth of the EHFS. The outer loop online adaptive controller is developed by Legendre polynomials expanded adaptive filters with nonlinear mapping ability, whose weights are online updated by an adaptive tuning algorithm with the aim of handling system’s dynamic variations, nonlinearities and uncertain disturbances. The proposed controller is implemented on a real EHFS test rig by the xPC/Target rapid prototyping technique, and comparative experimental results demonstrate that the proposed controller can achieve much higher high frequency tracking performance than the traditional PI and IC controller commonly used in industry.

Fixed time adaptive fault tolerant sliding mode control of PEMFC air supply system

Guaranteeing rapid management of oxygen excess ratio (OER) for proton exchange membrane fuel cells (PEMFC) under load variations is a challenge with practical significance. To improve the controller response of PEMFC air supply system, a fixed time fault-tolerant control strategy is proposed in this paper. A fixed convergence time of PEMFC air supply control system is quantified and guaranteed by the proposed method and the control response can be accelerated by reducing the setting time. The contributions of this paper is fourfold. Firstly, the manifold leakage fault is estimated by fixed time fault observer, which can improve the real-time fault tracking performance of the control system. Secondly, a hierarchical fixed time sliding mode controller is proposed to regulate the OER rapidly. Furthermore, a novel adaptive term is employed to reduce the effects of the chattering from fault observer in the outer loop. Finally, the effectiveness of the proposed method is verified on a real-time PEMFC simulation platform. Experimental results on a Hardware-in-the-loop (HIL) platform show that the proposed fixed time fault tolerant control strategy has the characteristics of fast response and high robustness.

A tracking method for GEO space targets based on adaptive memory attenuation UKF

Aiming at the problem that the nonlinearity of the tracking state equation and the problem of strong noise in the measurement process in the process of tracking the target, a non-cooperative target tracking method in geostationary earth orbit based on adaptive memory attenuation UKF is proposed. Firstly, the relative motion model of the non-cooperative target is constructed, and the state equation and measurement equation are established. Use the memory attenuation adjustment factor to enhance the correction effect of the new measurement on the state estimation, improve the adaptability of the filtering method to nonlinearity and noise, and finally the relative motion trajectory of the space non-cooperative target is obtained. Finally, the standard UKF algorithm and improved UKF algorithm are applied to target tracking and compared by simulation. The deviation of the three coordinate axis components of the actual motion trajectory and the predicted trajectory of the space target is used as the evaluation index. The simulation results show that the filtering accuracy of the improved UKF algorithm is significantly improved, while taking into account the real-time performance of on-orbit tracking.

Isokinetic Muscle Strength Training Strategy of an Ankle Rehabilitation Robot Based on Adaptive Gain and Cascade PID Control

Isokinetic muscle strength training refers to the mode of movement based on constant speed and variable resistance, which can guarantee the maximum resistance and force–distance output of each muscle in different angles of exercise. In this article, we develop an isokinetic muscle strength training strategy based on the adaptive gain and cascade proportion integration differentiation (PID) controller for ankle rehabilitation on our newly developed ankle robotic system. First, a heuristic threshold intention recognition method based on time-series integration was proposed to precisely recognize the motion intention, thus inducing the motion in this direction. Then, an adaptive gain algorithm was developed to provide speed gain for the isokinetic training, to avoid jitter during speed switching. Finally, the isokinetic characteristic was realized by the cascade PID controller, which can control the motion velocity in a given range with fast response speed. Experiments with healthy subjects showed good performance in the smoothness of the control system, the accuracy, and the real-time performance of velocity tracking. By introducing the isokinetic characteristic in ankle rehabilitation, the ankle robot can provide resistance training at a constant speed no matter how much force the patient uses, which is a very functional supplement and improvement for ankle rehabilitation.

A Siamese tracker with "dynamic-static" dual-template fusion and dynamic template adaptive update.

In recent years, visual tracking algorithms based on Siamese networks have attracted attention for their desirable balance between speed and accuracy. The performance of such tracking methods relies heavily on target templates. Static templates cannot cope with the adverse effects of target appearance change. The dynamic template method, with a template update mechanism, can adapt to the change in target appearance well, but it also causes new problems, which may lead the template to be polluted by noise. Based on the DaSiamRPN and UpdateNet template update networks, a Siamese tracker with "dynamic-static" dual-template fusion and dynamic template adaptive update is proposed in this paper. The new method combines a static template and a dynamic template that is updated in real time for object tracking. An adaptive update strategy was adopted when updating the dynamic template, which can not only help adjust to the changes in the object appearance, but also suppress the adverse effects of noise interference and contamination of the template. The experimental results showed that the robustness and EAO of the proposed method were 23% and 9.0% higher than those of the basic algorithm on the VOT2016 dataset, respectively, and that the precision and success were increased by 0.8 and 0.4% on the OTB100 dataset, respectively. The most comprehensive real-time tracking performance was obtained for the above two large public datasets.

A new fast nonlinear model predictive control of parallel manipulators: Design and experiments

High-speed parallel manipulators are characterized by fast sampling rates and challenges owing to the presence of constraints, high nonlinearities, uncertainties, and fast dynamics. The development of a reliable nonlinear model predictive control (NMPC) approach for this type of robotic systems is challenging because of the complex dynamics that involves high computational burden. To address this control problem, this paper proposes a new fast NMPC strategy applied to high-speed parallel robots. Based on (i) a parameterization technique, (ii) a fast gradient solver, (iii) a proportional integral derivative (PID) control term, (iv) a nonlinear dynamic model, and (v) an artificial neural network (ANN) model, two fast NMPC frameworks were developed to reduce the computational cost of the classical NMPC and address online implementation. In this study, we focus on improving the performance of the standard predictive control strategy outside of the range of its classical applicability by developing a fast NMPC controller for high-speed parallel kinematic manipulators (PKMs). Numerical simulations and real-time experimental results were presented and discussed to validate the relevance of the proposed controllers. Experiments were conducted on a four-degree-of-freedom (4-DOF) PKM called VELOCE developed in our laboratory. The results show that the proposed solution outperforms the original scheme in terms of real-time tracking performance.

Multi-Type Object Tracking Based on Residual Neural Network Model

In this paper, a tracking algorithm based on the residual neural network model and machine learning is proposed. Compared with the widely used VGG network, the residual neural network has deeper characteristic layers and special additional layer structure, which break the symmetry of the network and reduce the degradation of the neural network. The additional layer and convolution layer are used for feature fusion to represent the target. The multi-features of the object can be captured by using the developed algorithm, so that the accuracy of tracking can be improved in some complex scenarios. In addition, we defined a new measure to calculate the similarity of different image regions and find the optimal matched region. The search area is delimited according to the continuity of the target motion, which improves the real-time performance of tracking. The experimental results illustrate that the proposed algorithm achieved a higher accuracy while taking into account the real time performance, especially in dealing with some complex scenarios such as deformation, rotation changes and background clutters, in comparison with the Multi-Domain Network (MDNet) algorithm based on a convolutional neural network.

Robust sliding mode prediction path tracking control for intelligent vehicle

Because of the characteristics of nonlinearity, strong coupling, fast time-varying, and uncertainty of the intelligent vehicle movement, the accurate path tracking control of the intelligent vehicle becomes a challenge. Considering a variety of complex constraints from the control system, this article combines sliding mode control and model prediction control to improve the intelligent vehicle real-time path tracking performance and proposes a robust sliding mode predictive controller for intelligent vehicle path tracking control. The sliding mode predictive controller uses the sliding mode surface in sliding mode control to construct the prediction model and corrects the sliding mode control output through continuous feedback correction and rolling optimization and then obtains the optimal control input which makes sure optimal performance control under system various constraints. The sliding mode predictive controller can simultaneously consider the tracking performance and system complex constraints, which effectively improves the dynamic performance and robustness of the control system. Related simulation results show that sliding mode predictive controller not only solves the problem of system constraints but also improves the accuracy of intelligent vehicle path tracking and the robustness of the system.

Moving Object Tracking Using Multiple Cameras in Network

In real time object tracking is an important task in various surveillance application. Nowadays, surveillance system very common in offices, collage campus, shopping malls etc. In this paper, an automated video surveillance system presented. Althrough tracking and counting system are commercially available today; there is need for further reaserach to address the challenges of real world scenarios. There is lot of surveillance cameras installed around us but there are no means to monitor all of them continuously. It is necessary to develop a computer vision based technologies that automatically process those images in order to detect situations or unusual behavior. In order to solve the problem of poor real time tracking performance using convolutional neural network. This paper proposes a fast and accurate real time video detection and tracking algorithm. Keyword: - Video surveillance system, Moving object detection, Tracking, Background subtraction. I. Introduction Real time human body detection and tracking in indoor environment deals with the concept of higher level application of image processing and computer vision. The following key components of identify to path of real time tracking are extracting a feature, background image subtraction. If two similar color objects come to close the tracker of one object can jump to associated object. The problem is called hijacking problem. Drifting problem occur when an object abruptly changes its direction to reverse. In that case it’s become very difficult to track the object because the motion model does not work. An object tracking can be understood as the problem of finding the path (i.e. Trajectory).

A Robust 6-D Pose Tracking Approach by Fusing a Multi-Camera Tracking Device and an AHRS Module

Optical tracking technique based on multiple cameras is widely employed in robots, virtual reality, and industrial measurements due to its excellent position accuracy. However, its 6-dimensional (6D) tracking practicability is impaired by the line-of-sight issue and the complicated tracker based on multiple markers. Hence, we implemented a custom-built hybrid tracking system consisting of four-camera equipment and a 6D tracker comprising a single optical marker and an automatic heading reference system (AHRS). AHRS provides the 3D orientation of the tracked object directly and compensates for the 3D position when the optical tracking is occluded. A two-stage cascaded adaptive Unscented Kalman Filtering (CAUKF) was proposed to enhance real-time fusion tracking performance. The CAUKF not only provides a reliable frequency enhancement solution for the optical tracking adapting to various frequencies, but also improves the continuality of prediction on fusion state variables and the corresponding covariance matrix, which helps to initialize the occlusion tracking accurately. When an occlusion occurs, a learning-based adaptive Unscented Kalman Filter (LAUKF) module can adaptively adjust noise estimation matrices in the unscented transformation according to the AHRS data, thereby significantly reducing the position estimation error. Experimental results reveal that the proposed tracking approach achieved 6D tracking at 100 Hz with 0.32 mm position error (mean absolute error) and 0.1° orientation error. This study furnishes a novel implementation method for the full 6D pose tracking with a simplified tracker structure and improved accuracy, continuity, and stability.

AOH: Online Multiple Object Tracking With Adaptive Occlusion Handling

Multiple object tracking has improved drastically in recent years due to one-shot tracking methods. These methods design joint-detection-and-tracking structures to achieve real-time tracking performance and introduce more powerful detectors to deal with missed objects. However, most of them perform poorly in crowded scenes because of frequent occlusions. Several previous works have attempted to alleviate the occlusion issue, but they hardly involve the essence of the problem. In this letter, we suppose that occlusion is closely related to crowd density, so the degree of occlusion can be estimated. Therefore, we propose a Potential Object Mining strategy to adaptively obtain occluded objects for reducing broken trajectories, which re-weights detections based on the predicted density map. Additionally, for the strategy, Dense Estimator is designed to predict the density of each region in an image by employing a Transformer-based structure. Combining them together forms our Adaptive Occlusion Handling (AOH) tracking framework. Extensive experiments on MOTChallenge benchmarks (MOT17 and MOT20) demonstrate that our AOH achieves the state-of-the-art performance, especially on the heavily occluded MOT20.

A Robot Dynamic Target Grasping Method Based on Affine Group Improved Gaussian Resampling Particle Filter

Tracking and grasping a moving target is currently a challenging topic in the field of robotics. The current visual servo grasping method is still inadequate, as the real-time performance and robustness of target tracking both need to be improved. A target tracking method is proposed based on improved geometric particle filtering (IGPF). Following the geometric particle filtering (GPF) tracking framework, affine groups are proposed as state particles. Resampling is improved by incorporating an improved conventional Gaussian resampling algorithm. It addresses the problem of particle diversity loss and improves tracking performance. Additionally, the OTB2015 dataset and typical evaluation indicators in target tracking are adopted. Comparative experiments are performed using PF, GPF and the proposed IGPF algorithm. A dynamic target tracking and grasping method for the robot is proposed. It combines an improved Gaussian resampling particle filter algorithm based on affine groups and the positional visual servo control of the robot. Finally, the robot conducts simulation and experiments on capturing dynamic targets in the simulation environment and actual environment. It verifies the effectiveness of the method proposed in this paper.

Real-time embedded object detection and tracking system in Zynq SoC

With the increasing application of computer vision technology in autonomous driving, robot, and other mobile devices, more and more attention has been paid to the implementation of target detection and tracking algorithms on embedded platforms. The real-time performance and robustness of algorithms are two hot research topics and challenges in this field. In order to solve the problems of poor real-time tracking performance of embedded systems using convolutional neural networks and low robustness of tracking algorithms for complex scenes, this paper proposes a fast and accurate real-time video detection and tracking algorithm suitable for embedded systems. The algorithm combines the object detection model of single-shot multibox detection in deep convolution networks and the kernel correlation filters tracking algorithm, what is more, it accelerates the single-shot multibox detection model using field-programmable gate arrays, which satisfies the real-time performance of the algorithm on the embedded platform. To solve the problem of model contamination after the kernel correlation filters algorithm fails to track in complex scenes, an improvement in the validity detection mechanism of tracking results is proposed that solves the problem of the traditional kernel correlation filters algorithm not being able to robustly track for a long time. In order to solve the problem that the missed rate of the single-shot multibox detection model is high under the conditions of motion blur or illumination variation, a strategy to reduce missed rate is proposed that effectively reduces the missed detection. The experimental results on the embedded platform show that the algorithm can achieve real-time tracking of the object in the video and can automatically reposition the object to continue tracking after the object tracking fails.

A Nonlinear Backstepping Controller Design for High-Precision Tracking Applications with Input-Delay Gimbal Systems

This paper proposes a novel nonlinear control approach for a two-axis gimbal to achieve accurate real-time tracking performance in maritime surveillance applications. For this objective, the control system must overcome system complexities and limitations, including nonlinear dynamics, coupled Euler angle-based measurements, and delay time constraints. The nonlinear backstepping controller was designed, taking into consideration the nonlinearities and system couplings to preserve the system stability. Then, an extra backstep was incorporated to minimize the control errors due to the delay time. The proposed control scheme enhances the tracking performances and expands the system’s bandwidth, which is validated in the simulations and experimental studies in comparison with a super-twisting sliding mode controller introduced in a previous study.

TRex, a fast multi-animal tracking system with markerless identification, and 2D estimation of posture and visual fields.

Automated visual tracking of animals is rapidly becoming an indispensable tool for the study of behavior. It offers a quantitative methodology by which organisms' sensing and decision-making can be studied in a wide range of ecological contexts. Despite this, existing solutions tend to be challenging to deploy in practice, especially when considering long and/or high-resolution video-streams. Here, we present TRex, a fast and easy-to-use solution for tracking a large number of individuals simultaneously using background-subtraction with real-time (60 Hz) tracking performance for up to approximately 256 individuals and estimates 2D visual-fields, outlines, and head/rear of bilateral animals, both in open and closed-loop contexts. Additionally, TRex offers highly accurate, deep-learning-based visual identification of up to approximately 100 unmarked individuals, where it is between 2.5 and 46.7 times faster, and requires 2-10 times less memory, than comparable software (with relative performance increasing for more organisms/longer videos) and provides interactive data-exploration within an intuitive, platform-independent graphical user-interface.

Scanning control based on real-time contact force feedback for ultrasonic thickness measurement

An effective contact force control strategy is of great significance for accurate and stable ultrasonic thickness on-machine measurement. However, it is difficult to adjust the contact force dynamically due to the uncertainty of the geometric characteristics of the measured workpiece. In this paper, a contact force control method based on the combination of adaptive impedance controller and sliding mode variable structure position controller is proposed. First, the control process with the force tracking impedance control and a normal contact force calculation model is established. Then, a force-position conversion model and a sliding mode variable structure controller are proposed. Further, a simulation with a typical S-shaped measured surface is given to show that the algorithm for controlling contact force can achieve good real-time tracking performance and has stronger robustness than traditional methods. Finally, an arc-shaped aluminum alloy thin-wall part thickness is sampled along the scan trajectory to verify the effectiveness of the algorithm. The experimental results show that the proposed algorithm for controlling contact force can quickly adjust the measuring device to the target position and maintain the stability of the normal contact force to ensure the accuracy of ultrasonic thickness on-machine measurement.

Event-triggered nonlinear model predictive control for trajectory tracking of unmanned vehicles

In order to increase the real-time performance of lateral trajectory tracking of unmanned vehicles, this paper designs an event-triggered nonlinear model predictive controller, which can save computation resource to a large extent while the tracking accuracy is still guaranteed. Firstly, a simplified vehicle is established using a two-degree-of-freedom dynamics model. Then, according to the theory of model predictive control, a nonlinear model predictive controller (NMPC) is designed. Since traditional NMPCs often have poor real-time control performance, this paper introduces an event-triggered mechanism, which allows the remaining elements of the control variables in the control horizon to be applied to the system once a specific condition is satisfied. Finally, the proposed controller is established by Matlab/Simulink, and the different trigger conditions are compared and verified in a double lane change maneuvers Then a system for evaluation is designed to quantify the performance of the controller in different trigger conditions. For further verification of the proposed controller, a Hard-in-the-loop simulation system based on Xpack package is established to conduct an HIL experiment. The results show that compared with traditional nonlinear model predictive control, our method offers greatly improved real-time performance while the tracking accuracy is guaranteed.

A Real-Time Structured Output Tracker with Scale Adaption for Visual Target Tracking

The structured output tracking algorithm is a visual target tracking algorithm with excellent comprehensive performance in recent years. However, the algorithm classifier will produce error information and result in target loss or tracking failure when the target is occluded or the scale changes in the process of tracking. In this work, a real-time structured output tracker with scale adaption is proposed: (1) the target position prediction is added in the process of target tracking to improve the real-time tracking performance; (2) the adaptive scheme of target scale discrimination is proposed in the structured support to improve the overall tracking accuracy; and (3) the Kalman filter is used to solve the occlusion problem of continuous tracking. Extensive evaluations on the OTB-2015 benchmark dataset with 100 sequences have shown that the proposed tracking algorithm can run at a highly efficient speed of 84 fps and perform favorably against other tracking algorithms.

Real-Time Multiobject Tracking Based on Multiway Concurrency.

This paper explored a pragmatic approach to research the real-time performance of a multiway concurrent multiobject tracking (MOT) system. At present, most research has focused on the tracking of single-image sequences, but in practical applications, multiway video streams need to be processed in parallel by MOT systems. There have been few studies on the real-time performance of multiway concurrent MOT systems. In this paper, we proposed a new MOT framework to solve multiway concurrency scenario based on a tracking-by-detection (TBD) model. The new framework mainly focuses on concurrency and real-time based on limited computing and storage resources, while considering the algorithm performance. For the former, three aspects were studied: (1) Expanded width and depth of tracking-by-detection model. In terms of width, the MOT system can support the process of multiway video sequence at the same time; in terms of depth, image collectors and bounding box collectors were introduced to support batch processing. (2) Considering the real-time performance and multiway concurrency ability, we proposed one kind of real-time MOT algorithm based on directly driven detection. (3) Optimization of system level—we also utilized the inference optimization features of NVIDIA TensorRT to accelerate the deep neural network (DNN) in the tracking algorithm. To trade off the performance of the algorithm, a negative sample (false detection sample) filter was designed to ensure tracking accuracy. Meanwhile, the factors that affect the system real-time performance and concurrency were studied. The experiment results showed that our method has a good performance in processing multiple concurrent real-time video streams.