3D Tracking Model Research Articles

Towards 3D Centimeter-Level Passive Gesture Tracking With Two WiFi Links

WiFi-based passive gesture tracking plays a crucial role in promoting human-computer interface, due to its pervasive availability and cost-effectiveness. Prior works focus on tracking gestures on 2D sensing plane by aggregating multiple WiFi links (typically 2), with Uniform Linear Arrays (ULAs). However, gestures actually contain 3D spatial information instead of just 2D, thus interpreting the 3D traces as 2D may lead to enormous tracking errors. This paper aims at exploring the possibility of passively tracking 3D hand traces likewise leveraging two WiFi links with standard 3-element ULAs, and presents a generic 3D centimeter-level passive gesture tracking system, called CentiTrack-3D. To this end, we make two key observations: (1) The ULA-resolved angle contains the integrated information of the azimuth and elevation in 3D space, despite its inability to estimate azimuth and elevation separately. (2) The radial motion deviating from the sensing plane also leads to length variations of paths. Motivated by the observations, a 3D tracking model named <i>Chaos</i> is elaborately designed to deduce the hand 3D coordinates, so as to track the traces. Extensive experiments yield that CentiTrack-3D achieves an overall median tracking granularity of 2.5 cm in 3D space in case of diverse users and environment conditions.

A High Reliability 3D Object Tracking Method for Robot Teaching Application

3D Object tracking is the task of capturing the 3D position and pose of an object from each time-series image frame. As we known, 3D sensing technique can be realized by stereo vision, structured light, and ToF (time-of-flight) camera. All of them can capture the point cloud data for describing the depth information in a workspace. In past research, the reliability in 3D object tracking was a big problem for real industrial application, therefore, we address a different way to enhance the tracking accuracy and stabilize the tracing path for raising the reliability. In order to build a 3D tracking model and the workspace environment, we adopted an RGB-D camera which is the Intel® RealSense™ D400 Series depth modules to collect the cloud point data and RGB values. The built 3D tracking model should contains the information which includes points, normal and texture for producing many 2D object images with different perspectives. Then the produced images were fed to a SSD (single-shot detector) neural network to learn the object’s features for 2D tracking. In dynamic tracking process, the image frames were through the sematic image segmentation by DeepLabV3+ for only extracting the object information without hands and background. Thus, the reserved data only included object’s cloud point data and texture information in workspace. Then we use the iterative closest point (ICP) algorithm and the RGB intensity correlation method to confirm the object’s position and posture in workspace. The result shows that our method has a better performance than SSD method for tracking a self-predefined object.

A time domain model for the study of high frequency 3D wheelset–track interaction with non-Hertzian contact

A novel numerical model for train-track interaction is proposed in this paper to deal with wheel–rail interface dynamics in high frequency range. The complete model consists a 3D rotating flexible wheelset model, a 3D track model considering the discrete support of the rail and a non-linear, non-Hertzian model of wheel–rail contact. The wheelset and the track models are both defined using an ‘Arbitrary Lagrangian–Eulerian’ Finite Element approach in combination with modal synthesis. This allows an efficient treatment of the problem, compared to a classical Finite Element approach. The proposed model is suitable to represent train-track interaction effects in a frequency range up to 7 kHz thanks to the detailed description of wheelset and rail deformability. Wheel–rail contact forces and rail vibration under excitation produced by different types of railhead irregularity are investigated in the paper, assessing the effect of different models of wheelset and track flexibility. The results obtained show that the outputs of the model mostly relevant to the investigation of rail corrugation and rolling noise, i.e. wheel–rail contact forces and rail vibration, are highly sensitive to the wheelset and track model adopted.

Improved railway wheelset–track interaction model in the high-frequency domain

As it is well known, there are various phenomena related to railway train–track interaction, some of them caused by the high frequency dynamics of the system, such as rolling noise when the vehicle runs over the track, as well as squeal noise and short-pitch rail corrugation for curved tracks. Due to these phenomena and some others unsolved so far, a large effort has been made over the last 40 years in order to define suitable models to study the train–track interaction. The introduction of flexibility in wheelset and rail models was required to have a more realistic representation of the wheel–rail interaction effects at high frequencies. In recently published train–track interaction models, the rails are modelled by means of Timoshenko beam elements, valid up to 1.5 kHz for lateral rail vibration and up to 2 kHz for vertical vibration. This confines the frequency range of validity for the complete train–track model to 1.5 kHz.With the purpose of extending the range of validity above 1.5 kHz, a 3D track model based on the Moving Element Method (MEM) is developed in this paper to replace the Timoshenko beam considered in earlier studies, adopting cyclic boundary conditions and Eulerian coordinates. The MEM approach considers a mobile Finite Element (FE) mesh which moves with the vehicle, so the mass of the rail ‘flows’ with the vehicle speed but in the opposite direction through the mesh. Therefore, the MEM permits to fix the contact area in the middle of a finitely long track and to refine the mesh only around the contact area, where the forces and displacements will be more significant. Additionally, a modal approach is adopted in order to reduce the number of degrees of freedom of the rail model. Both strategies lower substantially the computational cost. Simulation results are presented and discussed for different excitation sources including random rail roughness and singularities such as wheel flats. All the simulation cases are carried out for a Timoshenko beam and a 3D MEM track model in order to point out the differences in the contact forces above the range of validity of the Timoshenko beam.

Three-Dimensional Finite Element Analysis Model of High-Speed Train-Track-Bridge Dynamic Interactions

The dynamic behavior is a complicated characteristic in analysis of a railway bridge when it is incorporated with the effect of railway track. Even though it is not an ignorable component, the coupling effect with the railway track in the dynamic response of a railway bridge has been ignored or just simplified in the past researches. Therefore, this study conducts a numerical analysis of track effect on the railway bridge, and the comparison between the dynamic responses with three-dimensional (3D) discrete support track model and those without it is examined. Dynamic amplitude incorporated with 3D track model is decreased when the train velocity goes up over 250 km/h. This phenomenon shows that the resonance effect has been shifted by the 3D track model, which results in the changes in dynamic characteristics of a railway bridge. Consequently, the coupling effect between bridge and track should be taken account for in the analysis of dynamic response of a railway bridge.

Neutron-induced complex reaction analysis with 3D nuclear track simulation

Complex (multiple) etched tracks are analysed through digitised images and 3D simulation by a purpose-built algorithm. From a binary track image an unfolding procedure is followed to generate a 3D track model, from which several track parameters are estimated. The method presented here allows the deposited energy, that originated from particle fragmentation or carbon spallation by means of induced tracks in commercially available PADC detectors, to be estimated. Results of evaluated nuclear tracks related to 12C ( n , 3 α n ′ ) reaction are presented here. The detectors were exposed on the ISS in 2001.