Joint Tracking Research Articles

Joint tracking and classification with constraints and reassignment by radar and ESM

We consider the problem of joint tracking and classification using the information from radar and electronic support measure. For each target class, a separate filter is operated in parallel, and each class-dependent filter is implemented by interacting multiple model regularized particle filter. The speed likelihood for each class is defined using a priori information about speed constraint and combined with the likelihoods from two sensors to improve tracking and classification. Moreover, the output of classifier is also used for particle reassignment of different classes, which might lead to better performance. Simulations show that our proposed method can provide reliable tracking and correct classification.

Using MEMS-based inertial sensor with ankle foot orthosis for telerehabilitation and its clinical evaluation in brain injuries and total knee replacement patients

Telerehabilitation is an emerging field of rehabilitation. Combining medicine and engineering, telerehabilitation provides an alternative method of rehabilitation therapy in areas lacking medical resources, and an easy way to resolve the inconvenience for the disabled patients to seek rehabilitation services. This study developed a device that integrates inertial measurement units (IMU) and an ankle foot orthosis (AFO) named AFO-IMU module. We further demonstrate the AFO-IMU module on telerehabilitation diagnostic including patients with muscle weakness due to brain injuries and patients who will receive total knee replacement surgery due to osteoarthritis of knee joints to determine the feasibility in clinical usage. The results from this study indicate that AFO-IMU module is a simple and effective telerehabilitation system to correctly assess knee joint activity and track knee joint rehabilitation diagnosis.

Joint detection, tracking and classification of a manoeuvring target in the finite set statistics framework

Target detection, tracking and classification are three essential and closely coupled subjects for most surveillance systems. In the finite set statistics (FISST) framework, this paper presents a Bayesian and recursive solution to joint detection, tracking and classification (JDTC) of a manoeuvring target in a cluttered environment, which is inspired by previous work on joint target tracking and classification in the classical Bayesian filter framework. The derived JDTC algorithm exploits the dependence of target state on target class by using class-dependent dynamical model sets. The relative merits of this JDTC algorithm are demonstrated via a two-dimensional example using a sequential Monte Carlo implementation. It is shown that handling those three closely coupled subjects jointly can achieve comparable detection and tracking performance to that of the exact filter in the FISST framework with a prior known class. The classification results are consistent with the previous work.

Proof of Concept for Robot-Aided Upper Limb Rehabilitation Using Disturbance Observers

This paper presents a wearable upper body exoskeleton system with a model-based compensation control framework to support robot-aided shoulder–elbow rehabilitation and power assistance tasks. To eliminate the need for EMG and force sensors, we exploit off-the-shelf compensation techniques developed for robot manipulators. Thus, target rehabilitation tasks are addressed by using only encoder readings. A proof-of-concept evaluation was conducted with five able-bodied participants. The patient-active rehabilitation task was realized via observer-based user torque estimation, in which resistive forces were adjusted using virtual impedance. In the patient-passive rehabilitation task, the proposed controller enabled precise joint tracking with a maximum positioning error of 0.25 $^\circ$ . In the power assistance task, the users’ muscular activities were reduced up to 85% while exercising with a 5 kg dumbbell. Therefore, the exoskeleton system was regarded as being useful for the target tasks, indicating that it has a potential to promote robot-aided therapy protocols.

Body-IMU autocalibration for inertial hip and knee joint tracking

Sensor to body calibration is a key requirement for capturing accurate body movements in applications based on wearable systems. In this paper, we consider the specific problem of estimating the positions of multiple inertial measurement units (IMUs) relative to the adjacent body joints. To derive an efficient, robust and precise method based on a practical procedure is a crucial as well as challenging task when developing a wearable system with multiple embedded IMUs. In this work, first, we perform a theoretical analysis of an existing position calibration method, showing its limited applicability for the hip and knee joint. Based on this, we propose a method for simultaneously estimating the positions of three IMUs (mounted on pelvis, upper leg, lower leg) relative to these joints. The latter are here considered as an ensemble. Finally, we perform an experimental evaluation based on simulated and real data, showing the improvements of our calibration method as well as lines of future work.

Development of a probabilistic buckling analysis scheme for continuous welded rail track

Continuous welded rail (CWR) track has several advantages when compared with conventional jointed rail track. However, a thermally induced axial load can lead to the buckling of CWR tracks, which can result in train derailment. The buckling of CWR tracks is affected by several parameters, including the rail’s neutral temperature, misalignment of the rails and ballast resistance. Most of these parameters can be considered as random variables. A deterministic analysis approach is generally used to predict the buckling of CWR tracks; however, it can provide conservative results since it is based on the worst-case scenario of these buckling parameters. This paper presents a probabilistic buckling analysis scheme for CWR tracks.

Graphical model for joint segmentation and tracking of multiple dividing cells

To gain fundamental insight into the development of embryos, biologists seek to understand the fate of each and every embryonic cell. For the generation of cell tracks in embryogenesis, so-called tracking-by-assignment methods are flexible approaches. However, as every two-stage approach, they suffer from irrevocable errors propagated from the first stage to the second stage, here from segmentation to tracking. It is therefore desirable to model segmentation and tracking in a joint holistic assignment framework allowing the two stages to maximally benefit from each other. We propose a probabilistic graphical model, which both automatically selects the best segments from a time series of oversegmented images/volumes and links them across time. This is realized by introducing intra-frame and inter-frame constraints between conflicting segmentation and tracking hypotheses while at the same time allowing for cell division. We show the efficiency of our algorithm on a challenging 3D+t cell tracking dataset from Drosophila embryogenesis and on a 2D+t dataset of proliferating cells in a dense population with frequent overlaps. On the latter, we achieve results significantly better than state-of-the-art tracking methods. Source code and the 3D+t Drosophila dataset along with our manual annotations will be freely available on http://hci.iwr.uni-heidelberg.de/MIP/Research/tracking/

ToA-TS: Time of arrival based joint time synchronization and tracking for mobile underwater systems

Time synchronization and localization are key requirements for distributed underwater systems consisting of numerous low-cost submersibles. In these systems, submersibles are highly resource constrained and typically have limited acoustic communication capability. We investigate the problem of tracking submersibles that only have the capability of receiving acoustic signals. Traditional Long Base Line (LBL) systems track the location of submersibles by providing a GPS-like infrastructure that consists of a few reference beacons at known locations. In these systems the unknown positions of submersibles are estimated from beacon transmissions using time-difference-of-arrival (TDoA) based localization. As such TDoA makes the key assumption that beacon transmissions occur nearly concurrently in time. While this assumption is ensured in small LBL deployments it does not hold as the size of the system scales up. In this paper we identify scenarios where signals from multiple beacons are significantly lagged in time. We further identify the motion of the submersible between signal arrivals as a key factor that deteriorates the performance of TDoA, when transmissions are not concurrent. To address this problem we propose to track the submersible while performing time-synchronization. Our proposed technique, called Time of Arrival based Tracked Synchronization (ToA-TS) essentially extends GPS like localization for scenarios where beacon transmissions are not concurrent and submersibles are not capable of two-way communication. We show the benefit of our proposed scheme by comparing its performance to other localization techniques using experimentally obtained data.

Near-infrared vision system for monitoring arc welding processes

Throughout the years, vision, human beings' favourite sense, along with our great capacity to obtain, process and interpret a great amount of visual data, has been a great inspiration for development of techniques and technological devices that reproduce it into a computational system. In welding processes, vision can supply information on inspection and quality of the welded joint, monitoring of parameters, trajectory correction and even study of the phenomena involved in the process. However, the light radiation emitted from the weld arc is a barrier to studies based on the viewing process. One form currently used to visualize the process, without the interference of the arc's light, consists of illuminating the process with the near-infrared (NIR) light and using interference (band pass) filters, around this same wavelength, during acquisition of the images. One solution for the NIR light that is being increasingly used involves the use of high-power laser diodes, of low-cost and less complex installation than conventional lasers. The proposal of this study is the design, construction and assessment of a low-cost, highly flexible vision system for welding processes. It is based on characterization of the spectrum of the weld arc, definition of a drive topology for the high-power laser diode in NIR within its limitations of use, and maximizing the light power emitted, creation of control circuits, selection of optical equipment and components and, finally, design and apply a prototype for visualization of welding processes. As a whole, the limitations of the viewing system were encountered through their application with tungsten inert gas and metal inert gas/metal active gas welding. In these trials, although it had not been capable of overcoming the arc radiation, the system developed provided homogenous lighting synchronized with the camera, whereby the main limitation was long exposure time of the camera. In conclusion, the use of employing the system to assist with joint tracking is suggested.

Joint Target Detection Tracking and Classification Based on Finite-Set Statistics Theory

In traditional target tracking methods, the target number, target states and target class can not be estimated in same time. This paper investigated the joint target detection, tracking and classification method which is based on finite-set statistics theory. First, the random set and finite-set statistics theory are introduced for theoretic analysis. Second, the finite-set model for target tracking is given to construct a generalized nonlinear fusion framework. Finally, the finite-set based Bayesian filter is developed to track the targets in surveillance region. By recursively calculating the probabilistic hypothesis density, the target number, target states and target class can be evaluated simultaneously.

Analysis and Modeling of Uncertain System in Complex Environment

In complex battlefield environment all kinds of the uncertainties for target tracking make the analysis and modeling of tracking system irresolvable. Aiming at different levels of system uncertainty, the correspondent modeling methods are introduced. First, the stochastic process model is investigated which includes target process equation and sensor measurement equation. Second, joint state-class probabilistic density is given for realizing target tracking and classification simultaneously. Finally, the joint target detection, tracking and identification based on finite-set statistics theory is represented for multi-sensor multi-target tracking.

Finite-Time Neural Network Adaptive Control of Under-Actuated Robots

The finite-time neural network adaptive control of under-actuated robot is investigated, and a kind of multistep control strategy is used. First the transformation of dynamics model is made, and the passive joints are driven to desire positions by the coupling among joints, then the passive joints are locked. When the passive joints are locked to other operating point, the system becomes the one with structure uncertain. Combining the theory of finite-time control with neural network adaptive control, a finite-time neural network adaptive controller is got which can make the position tracking of joint rapidly. The simulation shows the effectiveness of the controller.

RGB cams vs RGB-D sensors: Low cost motion capture technologies performances and limitations

Motion capture of the human body has being performed for decades with a growing number of technologies, aims and application fields; but only recent optical markerless technologies based on silhouette recognition and depth sensors which have been developed for videogames control interface have brought motion capture to a broad diffusion. Actually, nowadays there are low cost hardware and software suitable for a wide range of applications that may vary from entertainment domain (e.g., videogames, virtual characters in movies) to the biomechanical and biomedical domain (e.g., gait analysis or orthopedic rehabilitation) and to a huge number of industrial sectors. In this quick evolving scenario it is hard to tell which technology is the most suitable for any desired goal. The aim of the paper is to answer to this issue by presenting a benchmark analysis that compares RGB and RGB-D technologies used to track performing people in a variety of conditions. In order to contrast the solutions, several different tasks have been selected, simultaneously captured and post-processed exactly in the same way. The test campaign has been designed to evaluate pros and cons according to the most important feature of a motion capture technology, such as volume of acquisition, accuracy of joint position and tracking of fast movements. Actors were asked to perform a number of tasks, among which free movements of arms, legs and full body, gait, and tasks performed interacting with a machine. The number of sensors around the scene and their disposition have been considered as well. We used Sony PS Eye cameras and Microsoft Kinect sensors as hardware solutions and iPisoft for data elaboration. The gathered results are organized, compared and discussed stressing performances and limitations of any combination and, at last, we proposed the best candidate technology for some key applications.

Position Tracking Control of Flexible Robot Joints Using Model Predictive Control

In this paper, a model predictive controller for the position tracking of flexible robot joints with harmonic drive gears is presented. The control methodology enables the drive's safety and physical constraints on torque and speed variables while guaranteeing the stability of the system. The effect of the predictive horizon on the drive performance is examined. Moreover, the influence of parameter changes is tested in this paper. Experimental results demonstrate the proposed controller is very effective in tracking position references while meeting the demanding drive constraints requirements during operation.

OTHR multipath tracking using the bernoulli filter

A multipath target tracking and recognition algorithm is proposed for an over-the-horizon radar (OTHR) tracking system in the presence of detection uncertainty and clutter. This algorithm, multipath Bernoulli filter (MPBF), uses a generalization of the Bernoulli filter for joint detection and tracking of a single target. Due to multiple ionospheric propagation paths between the radar sites and the target, finite set statistics (FISST) is used to derive the likelihood function of MPBF. While the measurement models in OTHR are nonlinear, a closed-form solution in the form of Gaussian mixture is implemented by extended Kalman filter (EKF). Since multipath tracks occur in the multipath probabilistic data association (MPDA) algorithm and the original MPBF, a method is added in MPBF to identify which are the real or multipath tracks. Simulation results are presented to demonstrate that the proposed algorithm is capable of recognizing multipath tracks and has better performance over the MPDA.

Through arc sensing for reciprocating wire feed gas metal arc welding

An arc sensor for reciprocating wire feed gas metal arc welding was developed to detect the torch height and track weld joints. The welding voltage waveform was adopted for the characteristic signal because the welding current remains almost constant with a change in the contact tip-to-workpiece distance. During reciprocating wire feed gas metal arc welding, the voltage waveform changes in an inherently complicated but periodic manner. After recognizing the voltage waveform pattern, the voltage characteristic for each phase was analyzed for arc sensing, and it was revealed that the short-circuit and cycle voltage characteristics were good estimators for torch height sensing. The dynamic arc sensing characteristics for reciprocating wire feed gas metal arc welding were investigated and found to be similar to those of a conventional constant voltage welding system. The seam tracking capability was evaluated by using the voltage integration difference method with transverse torch weaving. The voltage integration difference showed a linear relationship with the offset distance, and the reliability of the joint tracking sensor could be increased by using the moving average algorithm.

Extended C37.118.1 PMU Algorithms for Joint Tracking of Fundamental and Harmonic Phasors in Stressed Power Systems and Microgrids

This paper extends synchrophasor algorithms approximating C37.118.1 filtering requirements to provide phasor measurement units (PMUs) with the capability of accurately tracking single-phase harmonic phasors subject to varying nominal frequency and out-of band interharmonic interference. The fastest solution is built on a Kalman filter (KF) bank responding with notches at harmonic frequencies, while the most accurate solution relies on a five-cycle finite-impulse-response filter with more than 80-dB harmonic rejection. Highly distorted standardized test signals following WECC and Hydro-Québec experiences for stressed transmission systems and IEC recommendations for medium- and low-voltage system distortions are used to demonstrate the good performance of the two algorithms in tracking nonstationary fundamental and harmonics quantities. The two schemes are compared advantageously in terms of computation speed and performance with a four-cycle short-time fast Fourier transform algorithm. Finally, the effectiveness of harmonic phasors-enabled PMUs is demonstrated on a generation-rich microgrid subjected to a severe fault, followed by an offnominal frequency operation in islanded mode and subsequent grid re synchronization.

Design and experimental implementation of a hybrid zero dynamics-based controller for planar bipeds with curved feet

This paper extends the use of virtual constraints and hybrid zero dynamics (HZD), a successful control strategy for point-foot bipeds, to the design of controllers for planar curved foot bipeds. Although the rolling contact constraint at the foot–ground interface increases complexity somewhat, the measure of local stability remains a function of configuration only, and a closed-form solution still determines the existence of a periodic orbit. The formulation is validated in experiment using the planar five-link biped ERNIE. While gaits designed for point feet yielded stable walking when ERNIE was equipped with curved feet, errors in both desired speed and joint tracking were significantly larger than for gaits designed for the correct radius curved feet. Thus, HZD-based control of this biped is shown to be robust to some modeling error in the foot radius, but at the same time, to require consideration of foot radius to achieve predictably reliable walking gaits. Additionally, under HZD-based control, this biped walked with lower specific energetic cost of transport and joint tracking errors for matched curved foot gait design and hardware compared to matched point-foot gait design and hardware.

Hemiarthroplasty of the elbow: the effect of implant size on kinematics and stability

Distal humeral hemiarthroplasty is a treatment option for distal humeral fractures, nonunions, and avascular necrosis. The biomechanical effects, however, have not been reported. The purpose of this in vitro study was to quantify the effects of hemiarthroplasty and implant size on elbow joint kinematics. Eight fresh-frozen cadaveric arms were mounted in an in vitro motion simulator. An electromagnetic tracking system quantified elbow kinematics. A custom distal humeral stem was implanted by use of navigation, and 3 humeral articular spools were evaluated: optimally sized, undersized, and oversized. Statistical analysis was performed with repeated-measures analysis of variance. Distal humeral hemiarthroplasty altered elbow kinematics, regardless of implant size. In the valgus position, the optimally sized implant resulted in a mean increase in valgus angulation of 3° ± 1° (P = .003) as compared with the osteotomy control. In the varus position, the optimal and undersized implants both resulted in significant increases in varus angulation: 3° ± 1° (P = .01) and 3° ± 1° (P = .001), respectively. The undersized implant had the greatest alteration in kinematics, whereas the oversized implant best reproduced native elbow kinematics. This study showed a small but significant alteration in elbow joint kinematics with placement of a distal humeral hemiarthroplasty implant, regardless of implant size. This could be due to errors in implant positioning and/or differences in the shape of the humeral implant relative to the native elbow. These changes in joint tracking may cause abnormal articular contact and loading, which may result in pain and cartilage degeneration over time.

Position Sliding Mode Control of Manipulator Joint Based on Genetic Algorithm

In order to improve the control performance of position trajectory tracking of manipulator joint, a sliding mode control (SMC) method based on genetic algorithm(GA) is proposed in this paper. In this method, the performance of SMC algorithm is improved through adjusting the parameters of switching function and exponential approach law by genetic algorithm. The method was applied to accomplish the precise position control of manipulator joint. Simulation experiments show that the response time in manipulator joint control system by the SMC method based on GA is reduced 0.62s than the ordinary SMC algorithm. And the system restore stability time with a load change is also reduced 0.7s. External disturbance has no significant effect on the control system. The chattering of controller output is significantly reduced.