Search

To obtain efficient photovoltaic (PV) systems, optimum maximum power point tracking (MPPT) algorithms are inevitable. The efficiency of MPPT algorithms depends on two MPPT parameters, i. e., perturbation amplitude and perturbation period. The optimization of MPPT algorithms affect both the tracking speed and steady-state oscillation. In this paper, optimization methods of MPPT parameters are reviewed and classified into fixed and variable methods. The fixed MPPT parameters are constant during MPPT performance, and a trade-off should be made between the tracking speed and steady-state oscillation. However, the variable MPPT parameters will be changed to improve both the tracking speed and the steady-state oscillations. Moreover, some of them are simulated, compared, and discussed to evaluate the real contributions of the optimization methods to the MPPT efficiency. Furthermore, significant features of the optimization methods, i.e., noise immunity, robustness, and computation effort, are investigated.

The traditional fiber Bragg grating (FBG) acceleration has a low operating frequency, which limits its application in transmission line galloping monitoring. We develop a slotting optimization technique to realize the accurate tracking of transmission line galloping in this work. Furthermore, this technique is applied to the development of a high-frequency FBG acceleration sensor. The width, position, and length of the slot are optimized to minimize the slot’s effect on the FBG acceleration sensor. The vibration experiment in our work studies the frequency response and the sensing property of this FBG acceleration sensor. The experimental results indicate that our high-frequency FBG acceleration sensor has not only high sensitivity but also accurate monitoring results.

To obtain a high-precision bearing fault diagnosis of different speeds under intense background noise, a novel method called state-space principal component tracking filtering (SPCTF) is proposed for fault diagnosis. SPCTF can recover the fault information through the sequence of “Prediction – Measurement – Correction - Optimal estimation - Principal component extraction” from the polluted raw signals with noise. Firstly, the switch Kalman filter (SKF) is utilized to establish a dynamic filter model for time-series signals. And then, a feature tracking matrix is generated from the principal component features extracted from the optimal estimated state matrix of each time in the model. Thirdly, the principal component analysis extracts the effective fault feature from redundant information generated in the feature tracking matrix. Finally, the fault characteristic frequency is analyzed with the envelope spectrum to achieve a high-precision fault bearing diagnosis. The proposed method is demonstrated on signals from simulation signals and laboratory tests (several speeds), outperforming traditional methods.

We consider the position control problem of the planar 3R manipulator with the middle passive joint, whose dynamic constraint is caused by the second-order non-holonomic characteristic. A drift suppression control method with two stages is proposed for positioning the system. First, we give the dynamic model and the target angle of the system solution algorithm. Then, the controllers are designed to make the active links reach to their desired states, and the second link is rotating freely caused by the drift. So, the parametric trajectory is planned to suppress the drift of the second link and tracking this trajectory can makes all links reach to their desired states. Next, we use the differential evolution algorithm to search for the suitable parameters of the parametric trajectory taking the coupling constraints among all links. Then the controllers are designed to track the planned trajectories, so that all links can be controlled to the desired states simultaneously. Finally, numerical simulation results illuminate the effectiveness of the proposed method.

The Bernoulli filter is a general, Bayes-optimal solution for tracking a single disappearing and reappearing target, using a single sensor whose observations are corrupted by missed detections and a general, known clutter process. Like virtually all target-tracking algorithms it presumes a hidden Markov model (HMM) structure on the sensor and target. Pieczynski's pairwise Markov model (PMM) relaxes this assumption, thereby addressing correlated sensor noise and non-Markovian target motion. In an earlier paper, we derived a “PMM Bernoulli filter” that obeys PMM rather than restrictive HMM sensor/target statistics. This paper generalizes both the HMM and PMM Bernoulli filters to the case of multiple, possibly correlated sensors, resulting in a general, Bayes-optimal single-target tracker for complexly correlated sensors.

In this paper, a unified distributed swarm intelligence algorithm is developed to study time-varying output formation (TVOF) for a general linear multi-agent system (MAS) with a directed network. New adaptive output-feedback formation protocols are proposed to achieve TVOF stabilization for leaderless directed networks and TVOF tracking for leader-follower networks. For the leaderless case, only agents’ outputs are required to achieve the desired time-varying formation. An adaptive observer-type formation protocol is constructed via relative outputs of neighboring agents. No global information of the directed network is used to determine the protocol. A distributed algorithm is developed to solve the TVOF stabilization problem after the observability decomposition. For the leader-follower case, only partial agents have knowledge of the leaders’ information. An adaptive formation tracking protocol is constructed using dynamic relative output-feedback for neighboring followers. Based on the distributed algorithm, it is proved that the TVOF tracking problem with multiple leaders can be solved in a fully distributed manner.

Appearance information is one of the most important matching indicators for multi-object data association. In tracking by detection model, appearance information and detection information are usually integrated in the same sub-network for learning and output. This phenomenon will result in the appearance embedding vectors to be coupled to the network inference method during learning stage. As a result, the appearance embedding vectors contains too much background information and affects the accuracy of data association. Based on the non-end-to-end tracking model, we design an appearance guidance attention module for the appearance extraction branch. This module can effectively strengthen the network’s learning of the object visual appearance features and reduce the attention in the learning of background features. Finally, we utilize the appearance embedding vectors that decoupled from the inference method as the input of the back-end tracker and perform data association. The proposed method is tested on the MOT16 and MOT17 datasets. Experiments show that the proposed method provides more high-quality appearance representation information for the back-end tracker and the tracking performance on two datasets is better than other comparison models. At the same time, our model can reach 24.9FPS on a single 1080Ti GPU. The code is available at: https://github.com/JoJoliking/AGM

In this article, we propose a new distributed sensors-based multi-target geolocation and tracking technique. The proposed technique is a joint time-of-arrival (TOA) and direction-of-arrival (DOA) factor graph (FG) for multi-target geolocation (FG-GE), which is further combined with another FG for extend Kalman filtering (FG-GE-EKF) for tracking. Two-dimensional (2D) and three-dimensional (3D) scenarios are considered. In the FG-GE part, a new sensor association technique is proposed to solve the matching problem, which makes the right correspondence between the DOA/TOA information gathered by the distributed sensors and each target. With the proposed sensor association technique, the measured signals from targets can adequately be matched to their corresponding FGs. Thereby, the multi-target geolocation can be reduced to multiple independent single target geolocation. In addition, in the 3D scenario, each target is projected onto three orthogonal planes in the (x,y,z) coordinate. With this operation, the 3D geolocation is decomposed into three 2D geolocation problems. In the FG-GE-EKF part, the whole tracking system can be divided into two steps: prediction step and update step. In the prediction step, the predicted state is obtained from the previous state. Then, we utilize the predicted state as a prior information, and also to update the message exchanged in FG-GE. In the update step, the estimates obtained by FG-GE are regarded as observation state which is used to refine the predicted state, and acquire the current state. With proposed the FG-GE-EKF, the position estimation accuracy and tracking performance can be improved dramatically, without requiring excessively high computational effort.

The correlation filters tracker allows features from multiple channels. The fusion of features by simply summing over them in an Euclidean space would destroy the inherent geometry among multiple features, resulting in the lose of their phase information which is crucial to tracking task. To provide a better fusion of features from multiple layers of a convolutional neural network (CNN) in the classical CNNs based correlation filters algorithm, we introduce spherical manifolds and computing intrinsic mean on spherical manifolds in the article, so that fusion of features and online update of filter kernels can be implemented over a spherical manifolds. In addition, we introduce a random projection method, imposed on CNN features before feature fusion to compress features for the sake of reducing computational complexity and modeling complexity. Extensive experiments on OTB-50 dataset demonstrate that the proposed algorithm outperforms state-of-the-art methods with respect to both precision and success rate.

Object tracking is an important basis for the autonomous navigation of unmanned surface vehicles. However, several problems still must be addressed for a wide applicating of object tracking in unmanned surface vehicles. First, if multiple objects of the same classification exist in the same field of view, then stable extraction of an object is difficult. Second, in an environment with a complex background and large changes in object shape, the tracking accuracy is low, and object tracking errors and tracking loss can easily occur. Third, much time is required to detect a high-resolution real-time video stream, not meeting the delay requirement of the photoelectric servo stable tracking. To resolve these problems, this paper proposes an object detection-tracking algorithm based on a radar-photoelectric system. The algorithm combines an object detection algorithm with an object tracking algorithm and involves the following steps. First, a first-frame object extraction algorithm is used to extract the tracking object from the first frame. Second, a region of interest (ROI)-prediction algorithm is used to predict ROIs and detect objects in these ROIs. This algorithm can effectively solve the above problems in marine tests. When multiple objects of the same classification exist in the same field of view, the algorithm can extract the radar-guided object stably. When faced with a complex background and a large change in object shape, the algorithm substantially improves the accuracy and robustness of object tracking. Compared with the conventional object detection algorithm, the time consumption of this algorithm is reduced by 25.8%.

The precise detection and tracking of multiple particles under a microscope are of significance in the research of the individual and cluster behavior of dynamic bacteria and subcellular structures. However, the existing detection algorithms cannot separate occluded particles from each other, and most of the tracking algorithms aimed to address the occlusion involve several uncertainties. In this paper, a two-step detection algorithm based on the threshold segmentation and morphological open operation has been developed for identify non-fluorescent labeled particles under microscope, which could separate micro-contact targets. Moreover, we have proposed a novel correlation algorithm that can exploit the strengths of the global shortest path algorithm and Hungarian algorithm, which updating online in real time and considering the occlusion among particles. The proposed approach could achieve the temporal optimal match and spatial optimal solution by utilizing the multi-frame information. Moreover, the proposed method could realize the tracking of occluded particles tracking, and outperform the single global shortest path algorithm and Hungarian algorithm. The proposed method was successfully applied to six real image sequences with the maximum number of particles per frame ranging from 23 to 55, as well as a synthetic and fluorescent labeled sequence. The results of the contrast experiments demonstrated that the proposed algorithm is practical and can realize real-time tracking.

In the presented work, the practical trajectory tracking controller is designed for a kind of nonholonomic system under full state constraints. Firstly, a finite-time tracking controller is proposed to drive the action of relay switching which divides the entire control process into two stages. Then, using state transformations, the remaining error original system is converted into an unconstrained system for which the tracking controller is designed based on dynamic surface control. Meanwhile, another tracking control law is also addressed to ensure the boundedness of tracking errors before the action of switching. In stability analysis, it has been shown that the developed tracking control strategy can achieve the desired tracking control objectives and the predefined full state constraints. At the same time, all signals keep bounded in the whole control process. Simulation results are provided finally to demonstrate the effectiveness of the tracking control algorithm.

This paper investigates an adaptive coordinated control problem of spacecraft formation flying (SFF) system subject to uncertain mass and external perturbations. First, a general unified structure is proposed to represent the adjustable performance functions like the exponentially and appointed-time convergent ones. Then, an adaptive coordinated controller is developed based on a two-layer performance envelope to characterize the transient and steady-state formation maneuvering behaviors quantitatively of SFF system. Compared with the existing coordinated control approaches, the prominent advantage of the proposed one is that the preassigned position tracking and consensus tracking performance is guaranteed simultaneously while maintaining the scheduled formation configuration. Meanwhile, the users can configure and adjust the convergence rate (like the exponential or finite-time convergence) of the formation tracking errors by choosing different parameters arbitrarily in the unified structure for the performance functions. Finally, a group of numerical examples are organized to validated the effectiveness of the proposed coordinated control approach.

This work proposes a novel solution to relocalize the SLAM tracking based on spherical cameras. It focuses on the imaging method of spherical camera, the feature extracting algorithm and the relocalization of SLAM tracking based on the 3D reconstruction. In the imaging method, we design a new camera containing eight fish-eye lenses, and then we propose a calibration method to calibrate the eight fish-eye lenses spherical camera; To get the high-performance feature points of panoramic image, we propose a network based on a separate network to extract local feature accurately and quickly. With the correct key points obtained by the feature extracting method, we reoptimize the SLAM tracking after the maximum posteriori estimation usually applied in common back-end SLAM to relocalize the SLAM tracking. The experiment results show that the calibration method achieved 0.973 reprojection error, lower than the common methods like Zhang’s or DLT. The inlier rate and matching time of proposed SimpGeoDesc are all better than the reference models ContextDesc and GeoDesc. With the correct feature points, SLAM tracking is clearer and more steadily with our relocalization method. That is the solution of relocalization of SLAM tracking proposed in this work is effective. The AR application of the relocalization proves the feasibility of our propose relocalization method.

Siamese networks based visual tracking has recently drawn great attention due to their superior representation and tracking accuracy. However, the backbone networks and prediction networks still cannot fully take advantage of features from modern deep networks. In this paper, we propose an inverted residual Siamese feature-crossing network (IRSiamese-FCN) which is end-to-end trained off-line with a large amount of image pairs. Specifically, the Siamese backbone networks for feature extraction consist of an inverted residual network and a feature-crossing network (FCN). The designed IR architecture is light weighted by combination of depthwise and pointwise convolutions. Moreover, non-linearities and linearities are proceeded separately in deep and narrow layers. Feature-crossing network is to perform feature-level aggregations, which makes deep and shallow layers complement each other more closely and further improves tracking accuracy. We conduct ablation studies and comparison experiments over five large benchmarks. The results demonstrate that the proposed tracker can achieve competitive performance.

In this paper, the tracking problem for a class of nonlinearly parametric time-delay systems with arbitrary initial state errors and iteration-varying reference trajectories is studied. An adaptive iterative learning control scheme is developed by using Lyapunov approach. A time-varying boundary layer is constructed for removing the zero initial error condition, which is necessary in normal iterative learning control algorithms. The time-varying nonlinearly parametric uncertainties and time-delay uncertainties are well compensated by using parameter separation technique, signal replacement mechanism and robust strategy. As the iteration number increases, the state tracking error asymptotically converges to a tunable residual set. In the end, a simulation example further verifies the theoretical results.

Particle filter has been widely applied in nonlinear target tracking due to the ability to carry multiple hypothesis and relaxation of linearity/Gaussian assumption. In this paper, an adaptive double space-resampling particle filter is proposed to increase the efficiency and robustness of filtering by adjusting the sample size. The first resampling operation, adopted before the prediction of samples, generates a larger number of equal-weighted samples and some auxiliary samples to enhance the robustness of filtering. The second resampling, adopted between the prediction and updating step, decreases the sample size for weight updating which is the most time consumption part of particle filter. The particle space sampling technique is used in both space-resampling, which adjusts the sample size according to not only the weights of samples but also their spatial distribution. The efficiency of filtering is improved and the robustness of algorithm is enhanced, simultaneously. The degeneracy and sample impoverishment problems can be counteracted. Simulation and experiment contrast results demonstrate that the proposed method is robust and efficient.

Target tracking has been a research hotspot in computer vision, and the correlation filtered target tracking algorithm has the benefits of low computational complexity and fast speed. Still, the tracking effect is not good when dealing with complicated circumstances. This paper proposes a multi-feature fusion target repositioning tracking algorithm for the target tracking problem in complex environments. First, a multi-feature weighted fusion algorithm is presented. Since each feature has different advantages in different environments, we combine HOG, CN, ULBP, and image edge features and use the weighted coefficient method to adaptively fuse each feature component. Second, to address the target occlusion problem, an occlusion judgment mechanism is introduced, and the target is re-located by fusion weighted filtering. Third, the scale pool is established, and the scale filter is trained by the classification search method. Finally, an adaptive model update strategy is proposed. We conduct comparison experiments with current mainstream algorithms on the publicly available datasets OTB-2015, VOT2018, UAV123, and TColor-128, respectively, and the experimental results show that our proposed algorithm is more robust in complex scenarios.

Viral and bacterial pathogens can be transmitted through direct contact with contaminated surfaces. Efficient decontamination of contaminated surfaces could lead to decreased disease transmission, if optimized methods for detecting contaminated surfaces can be developed. Here we describe such a method whereby thermal tracking technology is utilized to detect thermal signatures incurred by surfaces through direct contact. This is applicable in public places to assist with targeted sanitation and cleaning efforts to potentially reduce chance of disease transmission. In this study, we refer to the touched region of the surface as a “touch-point” and examine how the touch-point regions can be automatically localized with a computer vision pipeline of a thermal image sequence. The pipeline mainly comprises two components: a single-frame and a multi-frame analysis. The single-frame analysis consists of a Background subtraction method for image pre-processing and a U-net deep learning model for segmenting the touch-point regions. The multi-frame analysis performs a summation of the outputs from the single-frame analysis and creates a cumulative map of touch-points. Results show that the touch-point detection pipeline can achieve 75.0% precision and 81.5% F1-score for the testing experiments of predicting the touch-point regions. This preliminary study shows potential applications of preventing indirect pathogen spread in public spaces and improving the efficiency of cleaning sanitation.

In this paper, an X-Y position stage simulates flexible loads completing handling or detection tasks in industrial applications are studied. The platform is driven by permanent magnet synchronous motors (PMSM) servo system, which has flexible beams with different natural vibration frequencies on the X-axis and Y-axis. The controller is designed to suppress the vibration of the flexible beams with different frequencies and reducing the contour error. The Euler-Bernoulli beam theory is adopted to obtain the mode shapes and natural frequencies of the flexible beam with clamped and endpoint mass boundary conditions. Analysis shows that the first-order vibration mode contributes the most to the displacement of the flexible beam. The trajectory motion profile based on time-shifted cosine jerk central angle interpolation (CJCI) contains prefilter to suppress low vibration frequencies in the two beams, which does not cause distortion of the actual contour. The linear phase lead iterative learning control (ILC) combined with the contour of CJCI is proposed to reduce the tracking errors of each axis, thereby reducing the overall contour error. The analysis and design process of ILC in frequency domains, which is applied to alleviate noise and disturbance effects. Comparison experiments confirm the effectiveness of the proposed method.

This paper proposes a new model-free sliding mode tracking differentiator with adaptive gains for reliable filtering and derivative estimations from noisy signals by improving a Levant and Yu’s sliding mode tracking differentiator. Particularly, the proposed tracking differentiator employs a nested generalized signum function for reducing overshoot during convergence. Moreover, a model-free adaptive gain scheduling is adopted for balancing the tracking and filtering performances. The advantages of the proposed tracking differentiator is validated through numerical examples.

This paper presents a disturbance observer-based nonsingular terminal sliding mode control design for a myringotomy surgical device. The methodology is established to control a semi-automated hand-held ear surgical device for the treatment of otitis media with effusion. Otitis media with effusion is the collection of bacterial fluid in the middle ear space which can potentially lead to hearing loss and chronic infections. A finite-time terminal sliding surface is proposed and a nonsingular terminal sliding control is constructed. The control approach fulfils precise tracking of the desired motion trajectory in the presence of disturbances, nonlinearities and uncertainties. The stability of the control approach is analyzed. In addition, the tracking control of the myringotomy surgical device is proven mathematically and the simulation results confirm the applicability and efficiency of the proposed approach and a precise tracking performance following desired motion trajectory is demonstrated in the simulations.

In this work, we focus on the model-mismatch problem for model-based subspace channel tracking in the correlated underwater acoustic channel. A model based on the underwater acoustic channel's correlation can be used as the state-space model in the Kalman filter to improve the underwater acoustic channel tracking compared that without a model. Even though the data support the assumption that the model is slow-varying and uncorrelated to some degree, to improve the tracking performance further, we can not ignore the model-mismatch problem because most channel models encounter this problem in the underwater acoustic channel. Therefore, in this work, we provide a dynamic time-variant state-space model for underwater acoustic channel tracking. This model is tolerant to the slight correlation after decorrelation. Moreover, a forward-backward Kalman filter is combined to further improve the tracking performance. The performance of our proposed algorithm is demonstrated with the same at-sea data as that used for conventional channel tracking. Compared with the conventional algorithms, the proposed algorithm shows significant improvement, especially in rough sea conditions in which the channels are fast-varying., Comment: Submitted to IEEE Access

This paper addresses an augmented nonlinear lateral vehicle and lane keeping dynamics in the presence of some unknown disturbances. In a geometric basin, considering unobservable spaces, their orthogonal complements, and using control invariant properties, a disturbance decoupling mechanism is designed for the mentioned dynamics. Afterward, a nonlinear tracking controller is designed to steer the vehicle on a reference path. The obtained disturbance decoupling and tracking controllers are implemented on a typical passenger car in a simulation environment to demonstrate the effectiveness and performance of the proposed method. It is shown that the controller decouples both the uniformly distributed and exponentially attenuated disturbances from the output.

Visual tracking of multiple objects in videos has a promisingly broad application in manufacturing, construction, traffic, logistics, etc., especially in large-scale applications where it is not feasible to attach markers to many objects for traditional, marker-enabled tracking methods. This paper presents a new approach, Kalman-intersection-over-union (KIOU) tracker, for multi-object tracking in videos that integrates a Kalman filter with IOU-based track association methods. The performance of the proposed KIOU tracker is quantitatively evaluated with UA-DETRAC, an open real-world multi-object detection and tracking benchmark. Experimental results show that the KIOU tracker outperforms the leading tracking methods. Additionally, the KIOU tracker has speed comparable to simple area overlap-based track association and quality close to methods with much higher computational costs, demonstrating its potential for online, real-time multi-object tracking.

Direction of arrival (DOA) tracking for multi-sources is a hot issue in array signal processing. To deal with the problem that sources DOA and their number are time-varying, a DOA tracking algorithm based on Generalized Labeled Multi-Bernoulli (GLMB) filter is proposed. Since the measurement value has only one set of data, the measurement association mapping (MAM) does not match, which leads to deviations in the GLMB filter update step. In this regard, we used the estimated sources number of the previous time step as the measurement number of the current time step, and successfully achieved MAM matching. Subsequently, particle filtering is used to approximate the posterior distribution of DOA, where the particle likelihood function can be calculated by the multi-signal classification (MUSIC) spatial spectrum function. In addition, by exponentially weighting the likelihood function, the number of particles in the high likelihood region of the posterior distribution increases, which makes the GLMB filter pruning and merging operations more effective. Simulation results show that the method is better than the probability hypothesis density DOA (PHD-DOA) algorithm in tracking state sources and estimating the number of targets.

With a good balance between tracking accuracy and speed, kernelized correlation filter (KCF)-based trackers have now become dominant approaches in the field of online object tracking. However, a KCF-based tracker updates templates by linearly combining historical objects, and its performance inevitably degrades when the accumulated error causes the model to look more similar to the background than the foreground. To address this model drifting problem, we propose an incremental kernel principal component analysis (IKPCA)-based KCF (IKPCA-KCF) tracking scheme. In IKPCA-KCF, IKPCA technology is used to incrementally learn the target features to alleviate the model drifting problem. Moreover, reduced-set (RS) expansions are adopted to compress the historical target samples to maintain a constant template update rate. Additionally, KCF-based trackers use the response map generated by the correlation filter to determine the target location. However, when the target leaves the field of view, using the maximum response value to reflect the target’s position information will certainly induce tracking errors. To further solve the tracking stability problem, a simple and effective nearest neighbor classifier is used to confirm the tracking target during the tracking process. Extensive experimental results demonstrate that the proposed IKPCA-KCF tracker is competitive with state-of-the-art trackers on eight challenging video datasets.

When system parameters vary at a fast rate, identification schemes based on model-free local estimation approaches do not yield satisfactory results. In cases like this, more sophisticated parameter tracking procedures must be used, based on explicit models of parameter variation (often referred to as hypermodels), either deterministic or stochastic. Kalman filter trackers, which belong to the second category, are seldom used in practice due to difficulties in adjusting their internal parameters such as the smoothness coefficient and the order of the hypermodel. The paper presents a new solution to this problem, based on the concept of preestimation of system parameters. The resulting identification algorithms, which can be characterized as decoupled Kalman trackers, are computationally attractive, easy to tune and can be optimized in an adaptive fashion using the parallel estimation approach. The decoupled KF algorithms can be regarded as an attractive alternative to the state-of-the-art algorithms which are much more computationally demanding.

Rear-lamp tracking at nighttime plays a momentous role in the advanced driver assistance system (ADAS), involving collision mitigation, automatic cruise control, automatic headlamp dimming, etc. Most of the existing tracking methods based on monocular camera leverage on color features. However, such tracking methods can be easily influenced by background clutter, illumination change, distance variation, and occlusion. In this paper, we propose an evolutionary adaptive rear-lamp tracking method at nighttime, in which a novel genetic algorithm powered by the probabilistic bitwise operation (PBO) is utilized. Also, to improve the robustness against various environments, a balanced fitness function is proposed by taking color information, symmetry, spatial relationship, and rigidity into account. Especially, a series of adaptive thresholds based on rear data in HSV color space is proposed to exploit color information reasonably with respect to our task. A strategy to deal with occlusion is also proposed, which relies on color information and rigidity. Moreover, to our knowledge, there is no publicly available dataset for rear-lamp tracking at nighttime. To fill the gap between the real-world application and the theoretical research, we create a novel dataset, which contains diverse traffic conditions at nighttime. The experimental results indicate that our method outperforms comparative online tracking methods in terms of success rate and center location error.

Siamese network based trackers describe object tracking as a similarity matching problem and these trackers achieve state-of-the-art performance on multiple benchmarks. However, due to the non-update of the appearance template and the change of the object appearance, the tracking drift problem often occurs, especially in the background clutter scene. Effective appearance template update methods can improve tracker performance, but most trackers use simple linear interpolation to update the template or do not update the initial template at all. Through experiments, we find that the channel response of the search region with the adjacent frame appearance template is often better than that with the initial frame appearance template. So we add the results of the previous frame prediction as a new template branch to the Siamese network to form a Triplet network. We applied the Triplet network to the SiamFC and SiamCAR, called TripFC and TripCAR. We tested on four challenging benchmarks (GOT-10K, OTB2013, OTB2015, UAV123). The experiments show that our method is powerful and effective, it can be easily embedded into the Siamese trackers. TripFC has a good effect on solving the problem of tracking drift. If necessary we can publish the code to facilitate research in this area.

In Mobile Robotics, visual tracking is an extremely important sub-problem. Some solutions found to reduce the problems arising from partial and total occlusion are the use of multiple robots. In this work, we propose a three-dimensional space target tracking based on a constrained multi-robot visual data fusion on the occurrence of partial and total occlusion. To validate our approach we first implemented a non-cooperative visual tracking where only the data from a single robot is used. Then, a cooperative visual tracking was tested, where the data from a team of robots is fused using a particle filter. To evaluate both approaches, a visual tracking environment with partial and total occlusions was created where the tracking was performed by a team of robots. The result of the experiment shows that the non-cooperative approach presented a lower computational cost than the cooperative approach but the inferred trajectory was impaired by the occlusions, a fact that did not occur in the cooperative approach due to the data fusion.

Ambient intelligence aims to actualize the environment that sense and utilize information around us without making us perceive the underlying systems. This work extends this concept by allowing us to track the movement and orientation of people and objects instantly. The proposed system can sense and let us know, for example, who met or talked to each other frequently, to whom s/he is often facing in the meeting, what stuffs people often use, where the person left his/her belongings, etc. Such information will help the system to understand the behavior patterns of each person and consequently can support and improve the personal life of users and even their mutual relationship. This article proposes an instant indoor magnetic tracking system that enables us to track the movement and orientation of people and objects by only attaching tiny electronic trackers to them. The size of the prototyped tracker is only 25.4mm $\times25.4$ mm $\times10.0$ mm, and hence it can be readily attached to almost anything and immediately activated. Evaluation results show that the proposed system applies to both room-scale tracking and tabletop scale tracking with 6 DoF (Degrees of Freedom).

Sperm motility measurement using computer assisted sperm analysis (CASA) has been widely accepted as a substitute for manual measurement but still faces several challenges. In the tracking phase, tracking errors caused by detection failure often occur when measuring fresh bull semen. Tracking errors occur for two reasons: (1) the sperm move very fast, which makes them appear blurry, and (2) partial occlusion, which frequently occurs. This study proposes the mean angle of sperm motion and Tracking-Grid to predict the position of the sperm that failed to be detected. The Tracking-Grid has also been found useful in tracking fast-moving sperm. The proposed methods reduce identity switch (ID-switch) and achieve a multi-object tracking overall accuracy (MOTAL) of 73.2. The MOTAL result exhibits 5% less ID-switch and is 15.6 MOTAL points higher than state-of-the-art simple online and real-time tracking with a deep association metric (Deep SORT). The speed achieved is 41.18 frames per second (fps), which is 1.8 times faster than Deep SORT. In sperm motility classification, most researchers use one or several CASA parameters with a static threshold value. Such a method is effective for motile-progressive sperm classification but is less reliable for identifying non-motile-progressive sperm such as vibrating and floating sperm. This study proposes a machine learning-based motility classifier using a support vector machine with three CASA parameters: curvilinear velocity (VCL), straight-line velocity (VSL), and linearity (LIN), which we call the bull sperm progressive motility classifier (BSPMCsvm3casa). Experimental results show that BSPMCsvm3casa’s mean accuracy is 92.08%, which is 2.51–9.67 points higher than other classification methods.

This paper aims to assess the possibilities of using current and incoming fifth generation (5G) devices as millimeter wave (mmWave) imagers. For this purpose, previous works about freehand scanning with compact devices working at mmWave frequencies are herein extended. In particular, a new tracking unit is now attached to the scanning device so the main parts of the freehand imager, namely the radiofrequency (RF) and tracking subsystems, become portable and not depend on external systems. Specifically, this work illustrates the possibilities of 5G devices working at the mmWave band as imagers. Results supporting that the embedded tracking unit provides enough accuracy are described and compared with an accurate reference system. The impact of the final image is also considered revealing that the shape of imaged objects can be easily identified.

Many visual simultaneous localization and mapping (SLAM) systems have been shown to be accurate and robust, and have real-time performance capabilities on both indoor and ground datasets. However, these methods can be problematic when dealing with aerial frames captured by a camera mounted on an unmanned aerial vehicle (UAV) because the flight height of the UAV can be difficult to control and is easily affected by the environment. For example, the UAV may be shaken or experience a rapid drop in height due to sudden strong wind, which may in turn lead to lost tracking. What is more, when photographing a large area, the UAV flight path is usually planned in advance and the UAV does not generally return to the previously covered areas, so if the tracking fails during the flight, many areas of the map will be missing. To cope with the case of lost tracking, we present a method of reconstructing a complete global map of UAV datasets by sequentially merging the submaps via the corresponding undirected connected graph. Specifically, submaps are repeatedly generated, from the initialization process to the place where the tracking is lost, and a corresponding undirected connected graph is built by considering these submaps as nodes and the common map points within two submaps as edges. The common map points are then determined by the bag-of-words (BoW) method, and the submaps are merged if they are found to be connected with the online map in the undirect connected graph. To demonstrate the performance of the proposed method, we first investigated the performance on a UAV dataset, and the experimental results showed that, in the case of several tracking failures, the integrity of the mapping was significantly better than that of the current mainstream SLAM method. We also tested the proposed method on both ground and indoor datasets, where it again showed a superior performance.

We present an iterative approach for planning and controlling motions of underactuated robots with uncertain dynamics. At its core, there is a learning process which estimates the perturbations induced by the model uncertainty on the active and passive degrees of freedom. The generic iteration of the algorithm makes use of the learned data in both the planning phase, which is based on optimization, and the control phase, where partial feedback linearization of the active dofs is performed on the model updated on-line. The performance of the proposed approach is shown by comparative simulations and experiments on a Pendubot executing various types of swing-up maneuvers. Very few iterations are typically needed to generate dynamically feasible trajectories and the tracking control that guarantees their accurate execution, even in the presence of large model uncertainties.

Conventional multi-sensor multi-target multi-Bernoulli (MS-MeMBer) filters are based on the assumption that each target produces at most one measurement per time step. However, this assumption is not always reasonable in practice as an extended target can generate multiple measurements per step due to the recent improvement in the sensor resolution. In this case, a potential estimation bias may occur in the current MS-MeMBer filters. Therefore, a novel extended target MS-MeMBer filter and its Gaussian inverse Wishart mixture implementation are given in this paper. Specifically, we modify the update process of the MS-MeMBer filter by assuming that the generation of extended target measurements follows an approximate Poisson-Body model. Simulation results validate that the proposed filter can effectively estimate the shape and position of the extended target.

Correlation filter based tracking algorithms have received significant attention in visual tracking due to their accuracy and speed. However, it is susceptible to distractors and performs poor when it is faced with occlusion and severe deformation. In this paper, we introduce a distractor-aware long-term correlation tracking to distinguish the target and the background. Firstly, the information entropy weighted feature is utilized to deal with different scenarios dynamically. Secondly, in order to facilitate the tracker to distinguish the target from the distractors which lead to inaccurate localization, we propose a novel distractor-aware mask processing. We sample distractor patches and incorporate a binary mask to attenuate the possible negative influences. Thirdly, an improved fast scale searching scheme based on dichotomy is incorporated to provide a tradeoff between the accuracy and efficiency. Finally, the localization ambiguity is detected by using a new criterion based on the variance. It is concluded that introducing the re-detection technique and solving the occlusion play a critical role to facilitate the tracking progress. Furthermore, an adaptive model update strategy is utilized to update the long-term model for alleviating the model drift. Experiments on benchmark database demonstrate that the proposed method achieves good performance compared with other trackers and the strategy can be applied to other trackers.

Siamese trackers learn the appearance model of the target in the first frame and then exploit the model to locate the target in the subsequent frames. Meanwhile, the appearance model remains unchanged in the subsequent frames. Due to the powerful feature extraction capability of the deep convolutional neural networks, Siamese trackers achieve advanced performance. However, due to the non-update of the appearance model and the changing appearance of the target, the problem of tracking drift occurs frequently, especially in the background clutters scenarios. In order to tackle this issue, we propose a motion model and a discriminative model. Firstly, the motion model of the target is constructed to determine whether the tracking drift occurs or not since the position of the target predicted by the motion model is smooth in timing but the position of the target predicted by the Siamese tracker may be not smooth. In this case, the temporal information is utilized to supplement the Siamese tracker which only employs the spatial information. Secondly, the discriminative model is learned to determine the final position of the target when the tracking drift happens. Finally, a flexible model update strategy of the discriminative model is presented. In order to demonstrate the generality of the proposed method, we apply it for two famous Siamese trackers, SiamFC and SiamRPN_DW. Extensive experiments on OTB2013, OTB2015, VOT2016, VOT2019 and GOT-10k benchmarks demonstrate that the proposed trackers outperform the baseline trackers and achieve the state-of-the-art performance, especially in the background clutters scenarios. To the best of our knowledge, we are the first time to propose motion guided Siamese trackers. Moreover, We can release our code to encourage more researches in this direction.

Motion blur is a quite tricky issue in object tracking community. In recent years, many trackers have been explored to address this issue without sensational performance. This paper proposes a novel correlation tracking framework with Recurrent Neural Network (RNN) deblurnet and proposal detection to handle motion blur and heavy occlusion in object tracking tasks. We take advantage of high efficient Kernelized Correlation Filter (KCF) tracker, a typical method that exploits the circulant structure and the kernel trick to enhance the performance, and furthermore incorporate two regression methods in it. We employ RNN as our baseline of deblurnet, and introduce residual block and ConvLSTM in our deblur network to improve the result of deblurring. In addition, we suggest an edge information based rectification system to overcome the challenge of target occlusion. Finally, we update the model adaptively in term of the feedback from high-confidence tracking results to avoid the model degradation. Extensive experimental results demonstrate our tracker outperforms several state-of-the-art trackers on the OTB-2015 and VOT-2016 datasets.

Multi-object tracking (MOT) constructs multiple object trajectories by associating detections between consecutive frames while maintaining object identities. In many autonomous systems equipped with a camera and a radar, an amplitude and visual features can be measured. Therefore, our goal is to solve a MOT problem by associating detections with both features. To achieve it, we propose a unified MOT framework based on object model learning and confidence-based association. For improving discriminability between different objects, we present a method to learn several visual and amplitude object models during online tracking. By applying the learned object models for the affinity evaluation, we improve the confidence-based association further. In addition, we present a practical track management method to initialize and terminate tracks, and eliminate duplicated false tracks. We implement several MOT systems with different object model learning and association methods, and compare our system with them on challenging visual MOT datasets. We further compare our method with the recent deep appearance learning methods. These comparisons verify that our method can achieve the competitive tracking accuracy while maintaining a low MOT complexity.

In this paper, a MDSPF method is proposed to learn a robust observation model for representing the targets by training a CNN with a number of video sequences. The CNN architecture is composed of three shared convolutional units, two shared fully connected (Fc) units and a multiple domain Fc unit, and it is offline trained by a multi-domain learning strategy. After training, the shared convolutional units are remained as an observation model for our tracking framework. The features from the shared convolutional units can well adapt to the challenges in tracking tasks. A scale-adaptive particle filter is also proposed in our framework to improve the robustness of particle filter method. Different from most existing particle filter tackers, it can efficiently shepherd each particle towards a more precise location and scale through similarity evaluation. Extensive experiments are conducted on Object Tracking Benchmark (OTB), UAV123 and LaSOT datasets to verify the efficiency of our proposed method.

This research focuses on motion control of hydraulic servo-mechanism and presents a novel quasi-adaptive sliding mode control algorithm with barrier function-based control gain. The mathematical model of the system is established in integral series format to contribute to the controller design. The utilized sliding mode control gain is designed to be adapted with the change of design error related to tracking error. It can first increase until the design error reaches to a small domain at a designed time by utilizing constant gain. And then the control gain will automatically switch to barrier function form to hold design error within a predefined domain un-depending on the modeling uncertainties theoretically. Correspondingly, the tracking error will converge to a small domain. The system stability is proved via Lyapunov analysis. By comparing to three classic controllers with motion tracking experiments, the achievable higher tracking accuracy of the proposed new control law are validated sufficiently.

Most existing trackers perform well in the occurrence of short-term occlusions and appearance and illumination variations, but struggle with the challenges of long-term tracking which include heavy or long-term occlusions, and out-of-view objects. We propose a spatial-temporal aware long-term object tracking method in this paper, to manage the challenges of long term tracking. Firstly, we present a spatial-temporal aware correlation filter, which jointly models the spatial and temporal information of the target within the correlation filter framework to locate a visible target from frame to frame. Then, we design a tracking uncertainty detection mechanism to activate the re-detector in case of track failure. The mechanism relies on the variations of correlation response measured spatially, and the appearance similarity estimated temporally. Finally, we propose a spatial-temporal aware long-term re-detector to recover the target when it becomes visible. In the re-detection process, a large number of candidates are sampled, evaluated, and refined spatially to obtain accurate locations. Additionally, reliable memory retained through conservative template updating enables the recovery of the target by similarity matching. The spatial-temporal information is explicitly encoded in each component, which operates collaboratively to boost the overall performance. Extensive experimental results conducted on publicly available benchmark datasets demonstrate that the proposed method performs favorably when compared to other state-of-the-art trackers.

This article focuses on the fixed-time trajectory tracking problem for surface vehicles (SVs) with prescribed performance. First, to realize prescribed performance, the error transformation and fixed-time prescribed performance function are proposed. In this way, the constrained tracking error problem can be solved by the stabilization of the transformed system. Second, by introducing a reduced-order disturbance observer, a fixed-time sliding mode controller is developed to realize trajectory tracking control while satisfying both predefined performance and perturbance rejection. It notices that the associated settling time can be preselected by parameters and independent of system initial conditions. Finally, some simulation examples are provided to illustrate the effectiveness of our theoretical results.

Navigation, environment perception and localization are important capabilities of intelligent vehicles. In this paper, environmental perception and localization from binocular vision are studied. First, an outdoor feature point extraction algorithm that uses a local adaptive threshold is proposed to acquire environmental information. The algorithm filters feature points by setting adaptive parameters and calculating each pixel threshold with a dynamic local threshold. Second, an accurate method for feature point tracking is proposed for localization. We present exhaustive evaluation in 4 major scenarios from the most popular datasets. Evaluating the proposed method with traditional and state-of-the-art extraction methods and experimental results demonstrates that when the brightness decreases or increases, the performance of the proposed method is stable in terms of the number of feature points, the calculation speed and the overall repetition rate. Our proposed tracking method outperforms state-of-the-art tracking methods in terms of the root mean square error (RMSE) and the errors in the dimensions in the scenarios.

Due to the deficiency of prior information for online updating process, the tracking accuracy of fully-convolutional Siamese network (SiamFC) in complex scenes such as similar object interference, fast moving, and appearance change is not good. To solve the problem, a new object tracker based on a dynamic template updating strategy and the re-location mechanism based on the adaptive Kalman is proposed. To suppress the object interference and overcome the instability of fast-moving object tracking, an adaptive Kalman filter method is designed to change the selection method of search region and select the bounding box of the object closest to the predicted position. For the adaptation of appearance change, the high-confidence tracking results are fused with the initial template to dynamic update the template. Compared with traditional Kalman filter, the expectation of residual error for the adaptive Kalman filter method can be controlled in a low range by the adjustment of the gain online. The introduction of the adaptive Kalman based re-location mechanism improves the discriminative ability of SiamFC in interference scene. With the dynamic template updating strategy, the tracker obtains strong generalization capability to adapt to the appearance change of the tracking target. It is demonstrated that the proposed method performs real-time object tracking at the speed of 43fps and achieves competitive performance on OTB, VOT and TC128 datasets compared with other state-of-the-art trackers.

In a standard state-of-the-art measurement the head-related transfer function (HRTF) is obtained in an anechoic room with an elaborate setup involving multiple calibrated loudspeakers. In search for a simplified method that would open up the possibility for an HRTF measurement in a home environment, it has been suggested that this setup could be replaced with one with a single, fixed loudspeaker. In such a setup, the subject samples different directions by moving the head with respect to this loudspeaker, while the head movements are tracked in some way. In this paper, the feasibility of such an approach is studied. To this end, the HRTF is measured in an unmodified (non-anechoic) room by means of a single external speaker and a high resolution head tracking system. The differences between the dynamically obtained HRTF and the standard static HRTF are investigated, and are shown to be mostly due to variable torso reflections.

An optimal fuzzy controller design scheme is proposed to address the influence of time delay and disturbance on the control performance of nonlinear batch processes. First, a two-dimensional (2D) equivalent Takagi-Suguno (T-S) fuzzy error model is formulated. By introducing a quadratic performance index function and adopting 2D Lyapunov-Krasovskii theory, the existence condition of the optimal fuzzy control law is given. Furthermore, its solvable condition, which depends on time-delay bounds, is constructed in terms of linear matrix inequalities, and its gain is obtained by using an optimization algorithm. This design has the advantages of faster tracking and better tracking performance. Finally, two different algorithms (with and without optimization) are used to control the water level of a triple-capacity water tank. The results show that the presented strategy is more effective and feasible.

In order to improve the polishing efficiency and aim at the problem that the positioning error of industrial robot will cause the fluctuation of polishing force and the instability of removal function, a novel force-controlled spherical polishing tool combined with self-rotation and co-rotation motion for automatic polishing process is presented. The spherical polishing tool, which is integrated into the end of arm of an industrial robot for workpiece profile polishing has a linear voice coil motor to provide compliance and polishing force in the polishing process. The fluctuation of the polishing force caused by the positioning error of the robot can be effectively reduced, and a stable symmetric Gaussian removal function can be obtained by optimizing the ratio of co-rotation to self-rotation speed of the end-effector. The main advantage of the polishing method is that the polishing force can be actively controlled according to the pre-planned polishing requirements. By measuring the responsiveness and the stability of the polishing force using the proposed end-effector, it is verified that the polishing method can better adapt to the fluctuation of the polishing force and has a good performance in achieving remarkable polishing force tracking. The effectiveness of the proposed polishing method in ensuring the stability of removal function and surface convergence efficiency is verified through polishing experiments. The robotic flexible polishing method has great application prospect in processing large-sized optical components. It significantly improves the precision of polishing force and the surface convergence efficiency of the workpiece.