Three-dimensional Tracking Research Articles

Mormyroidea-inspired electronic skin for active non-contact three-dimensional tracking and sensing.

The capacity to discern and locate positions in three-dimensional space is crucial for human-machine interfaces and robotic perception. However, current soft electronics can only obtain two-dimensional spatial locations through physical contact. In this study, we report a non-contact position targeting concept enabled by transparent and thin soft electronic skin (E-skin) with three-dimensional sensing capabilities. Inspired by the active electrosensation of mormyroidea fish, this E-skin actively ascertains the 3D positions of targeted objects in a contactless manner and can wirelessly convey the corresponding positions to other devices in real-time. Consequently, this E-skin readily enables interaction with machines, i.e., manipulating virtual objects, controlling robotic arms, and drones in either virtual or actual 3D space. Additionally, it can be integrated with robots to provide them with 3D situational awareness for perceiving their surroundings, avoiding obstacles, or tracking targets.

Object detection and tracking for drones: A system design using dynamic visual SLAM

Abstract. Drones can play a quite crucial role in many walks of life today. Enhancing the visual perception ability of drones is crucial to their intelligence level. Among them, it is necessary to focus on strengthening the detection, tracking and mapping capabilities of drones for dynamic objects. However, the existing visual SLAM systems carried by drones do not perform well in dynamic environments. This project designs a monocular visual SLAM system specifically for drones, aiming to achieve efficient three-dimensional mapping and target tracking, surpassing the limitations of simple static mapping and positioning. Besides, this project constructs a drone dynamic SLAM system developed on the ORB-SLAM3 structure, uses drone images to detect, track and map object motion models, and reconstructs environmental maps to obtain motion parameters with real physical scales. This project strives to optimize the input pre-processing module, improve the validity of data and output environmental maps and raster maps. The outcomes demonstrate the system's strong accuracy and adaptability in dynamic installation procedures.

Three-dimensional localization and tracking of chromosomal loci throughout the Escherichia coli cell cycle.

The intracellular position of genes may impact their expression, but it has not been possible to accurately measure the 3D position of chromosomal loci. In 2D, loci can be tracked using arrays of DNA-binding sites for transcription factors (TFs) fused with fluorescent proteins. However, the same 2D data can result from different 3D trajectories. Here, we have developed a deep learning method for super-resolved astigmatism-based 3D localization of chromosomal loci in live E. coli cells which enables a precision better than 61 nm at a signal-to-background ratio of ~4 on a heterogeneous cell background. Determining the spatial localization of chromosomal loci, we find that some loci are at the periphery of the nucleoid for large parts of the cell cycle. Analyses of individual trajectories reveal that these loci are subdiffusive both longitudinally (x) and radially (r), but that individual loci explore the full radial width on a minute time scale.

Three-Dimensional Speckle Tracking Echocardiography Assessment of Right Ventricular Function in Chronic Coronary Syndrome Patients After Percutaneous Coronary Intervention.

This study aimed to assess alterations in right ventricular (RV) function following percutaneous coronary intervention (PCI) in patients with chronic coronary syndromes utilizing three-dimensional speckle tracking echocardiography (3D-STE). A prospective study was conducted involving 136 patients diagnosed with chronic coronary syndromes undergoing PCI, constituting the study group, alongside 110 age- and gender-matched healthy volunteers serving as the control group. Echocardiographic evaluations, including both conventional and three-dimensional assessments, were performed on all study participants at 1-week, 6, and 12 months post-PCI. Parameters such as tricuspid annular plane systolic excursion (TAPSE) were derived from conventional echocardiography, while tricuspid lateral annular systolic velocity (S') was measured via tissue Doppler imaging. 3D-STE was utilized to quantify metrics including right ventricular fractional area change (RVFAC), right ventricular free wall longitudinal strain (RVFWLS), right ventricular global longitudinal strain (RVGLS), right ventricular stroke volume (RVSV), and right ventricular ejection fraction (RVEF). TAPSE, S', RVFAC, RVFWLS, RVGLS, RVSV, and RVEF exhibited significant increases from 1-week to 6 months post-PCI (p < 0.05). However, from 6 to 12 months post-PCI, RVFAC, RVGLS, RVSV, and RVEF demonstrated no notable changes (p > 0.05). Meanwhile, TAPSE, S', and RVFWLS sustained significant elevations: TAPSE (19.63±3.253% to 22.603±2.885%, p < 0.001); S' (10.57±2.643 to 12.61±2.189cm/s, p < 0.001); RVFWLS (18.64±2.745% to 19.926±3.291%, p = 0.002). At 12 months post-PCI, S', RVFAC, RVGLS, RVSV, and RVEF remained lower than those of the healthy control group, but the differences were not statistically significant (p > 0.05). However, RVFWLS was significantly lower compared to the healthy control group (19.926 ± 3.291%vs. 22.10 ± 1.994%, p < 0.001). Following PCI, right ventricular systolic function in patients with chronic coronary syndromes improves significantly over time. However, even at the 12-month post-PCI mark, RVFWLS remains lower than that of the control group. Notably, 3D-STE emerges as a noninvasive method for quantifying right ventricular systolic function post-PCI in chronic coronary syndrome patients.

Passive vision based three-dimensional seam tracking using a stereo vision system with a single HDR camera

Seam tracking is a crucial feature that an automatic welding system must have. The laser tracking algorithm offers high accuracy but faces challenges in identifying seams with extremely narrow gaps, as the deformation of the laser stripe becomes difficult to detect in such cases. In contrast, the passive vision-based algorithm can effectively capture narrow gap information from the welding scene, making it more suitable for recognizing narrow seams. However, most of proposed passive vision-based seam tracking is based on “teaching and playback” mode and can only realize planar tracking. In medium and thick steel plate welding, the workpieces are so large that the “teaching and playback” based control algorithm is unsuitable. Therefore, in this paper, a stereo vision system with a single camera and the corresponding calibration algorithm are developed to achieve three dimensional seam tracking. Compared to stereo system with dual camera, the proposed system is cheaper and easier to synchronize acquisition. Moreover, to get out of the “teaching and playback” control strategy, a vector control algorithm without cumulative error is proposed. Results of nine experiments show that the average error of the proposed seam tracking system is less than 1.0662mm and the maximum error is 1.8030mm.

Double refractive particle tracking and sizing

We present a novel bifocal imaging method enabling three-dimensional particle tracking and size determination employing a single camera only. The method is based on double refraction causing a particle to be imaged twice, each particle image of different blur. From these double images, a linear calibration function can be derived allowing to determine the three-dimensional particle position unambiguously over the entire depth of measurement volume. As this calibration function is independent of the particle size used, the particle size can be determined simultaneously by relating size of the double images and depth position of the particle. To prove the applicability, a co-laminar flow of two particle suspensions with particles of 1.14 μ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\upmu$$\\end{document}m and 2.47 μ\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\upmu$$\\end{document}m in diameter was measured in a Y-shaped microchannel. While the laminar flow field was measured with very low uncertainty and independent of the particle size, the particle size distributions determined reproduced reliably the size distributions expected for the co-laminar flow applied, with a precision of about 98.6 %\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\%$$\\end{document} regarding the particle size discrimination. The progress for research is a new method readily to implement in common optical setups, promising, for example, valuable insights in polydisperse suspension flows—the vast majority of flows in fundamental research and applications.Graphical abstract

The predictive value of left atrial functional parameters for recurrence of atrial fibrillation after catheter ablation in patients

Abstract Background Catheter ablation (CA) is a first-line treatment option for patients with symptomatic or drug-refractory atrial fibrillation (AF), yet the recurrence rate of AF post-CA remains considerably high. Studies have reported that left atrial (LA) functional parameters can serve as predictive factors for AF recurrence, however, the results remains controversial. Purpose This study aims to investigate the predictive value of LA functional parameters for AF recurrence following CA in patients. Methods We prospectively enrolled patients with AF who underwent CA for the first time from June 2022 to May 2023 and met the inclusion criteria at our institution. All patients underwent pre-ablation evaluation of LA structure and function, including LA diameter (LAD), LA maximum volume (LAVmax), LA minimum volume (LAVmin), LA pre-systolic volume (LAVpre), LA reservoir strain (LASr), LA strain conduit (LAScd), LA contraction strain (LASct), and LA ejection fraction (LAEF) using three-dimensional speckle tracking echocardiography. AF recurrence was defined as atrial tachycardia occurring 3 months after ablation and lasting longer than 30s. Patients were followed up for 9 months post-CA , and the primary end point was any atrial tachycardia occurring at 3 months after ablation. Results A total of 85 patients with AF were ultimately included in this study, with an average age of 68.9±11.0 years, 54.2% of whom were male. During the 9-month follow-up, 30 patients (35.29%) experienced recurrence postoperatively, while 55 patients (64.71%) still maintained sinus rhythm. Compared with the AF non-recurrence group, the AF recurrence group had significantly increased LAD (46.4±5.5mm vs. 42.3±4.5mm, p&amp;lt;0.05), LAVmax (80.7±21.3mL vs. 67.1±22.0mL, p&amp;lt;0.05), LAVmin (63.8±18.0mL vs. 42.8±16.9mL, p&amp;lt;0.05) and LAVpre (72.4±19.4mL vs. 53.9±16.8mL, p&amp;lt;0.05). Meanwhile, in AF recurrence group, LAEF (21.7±6.8% vs. 37.5±8.0%, p&amp;lt;0.05), LASr (5.1±3.1% vs. 12.0±5.4%, p&amp;lt;0.05), LAScd (-4.0±3.6% vs. -7.3±5.7%, p&amp;lt;0.05), and LASct (-1.0±3.8% vs. -3.3±4.9%, p&amp;lt;0.05) were significantly decreased. Multivariate logistic regression analysis revealed that LASr (OR=0.640, 95%CI 0.425-0.964, p&amp;lt;0.05) and LAEF (OR=0.816, 95%CI 0.694-0.960, p&amp;lt;0.05) were independent risk factors for predicting AF recurrence. ROC curve analysis showed that both LAEF (AUC=0.935, 95%CI 0.871-0.999) and LASr (AUC=0.903, 95%CI 0.833-0.973) possess high predictive values. Furthermore, the combined model of LAEF and LASr (AUC=0.954, 95%CI 0.905-1.000) had a greater predictive value than any one of the two indicators (p&amp;lt;0.05). Conclusion Taken together, these findings indicate that LAEF and LASr are independent predictors of AF recurrence following CA in patients with AF. Combination of the two indicators can more accurately assess the risk of recurrence in AF patients post-CA.

Long-Range Three-Dimensional Tracking of Nanoparticles Using Interferometric Scattering Microscopy.

Tracking nanoparticle movement is highly desirable in many scientific areas, and various imaging methods have been employed to achieve this goal. Interferometric scattering (iSCAT) microscopy has been particularly successful in combining very high spatial and temporal resolution for tracking small nanoparticles in all three dimensions. However, previous works have been limited to an axial range of only a few hundred nanometers. Here, we present a robust and efficient measurement and analysis strategy for three-dimensional tracking of nanoparticles at high speed and with nanometer precision. After discussing the principle of our approach using synthetic data, we showcase the performance of the method by tracking gold nanoparticles with diameters ranging from 10 to 80 nm in water, demonstrating an axial tracking range from 4 μm for the smallest particles up to over 30 μm for the larger ones. We point out the limitations and robustness of our system across various noise levels and discuss its promise for applications in cell biology and material science, where the three-dimensional motion of nanoparticles in complex media is of interest.

Adaptive hierarchical interval type-2 fuzzy control for trajectory tracking of an underactuated AUV with uncertain dynamics

In this study, an adaptive hierarchical interval type-2 fuzzy control (AHIT2FC) scheme is presented for three-dimensional (3D) trajectory tracking control of an underactuated autonomous underwater vehicle (AUV), which has only three independent control inputs and is subject to partially parametric uncertainty and unknown external disturbances. To decrease reliance on hydrodynamic parameters, an interval type-2 fuzzy logic system (IT2FLS) is utilized, which exhibits superior capabilities in handling high levels of uncertainties prevalent in the underwater environment as compared to a type-1 fuzzy logic system. However, the traditional fuzzy system structure encounters the “curse of dimensionality” issue, which results in high computational complexity and imposes a significant burden on the limited computing resources underwater. The proposed AHIT2FC framework, based on a hierarchical structure, can substantially enhance computational speed while ensuring excellent control performance. Subsequently, Lyapunov’s theory is adopted to guarantee that all the tracking errors in the closed-loop system are semiglobally uniformly bounded (SGUB). Finally, comparative simulation results demonstrate the effectiveness and superiority of the proposed AHIT2FC scheme.

Assessment of Left Ventricular Functional Impairment in Patients With Chronic Kidney Disease Using Three-Dimensional Speckle Tracking Imaging.

Chronic kidney disease (CKD) is strongly linked to the incidence and mortality of cardiovascular diseases (CVDs), with left ventricular myocardial damage being the most prevalent. This study aimed to assess left ventricle (LV) dysfunction using three-dimensional speckle tracking imaging (3D-STI) in CKD patients. A total of 110 CKD patients and 55 healthy volunteers underwent echocardiography. CKD patients were divided into CKD1 group and CKD2 group based on the estimated glomerular filtration rate (eGFR). Assessing cardiac function via two-dimensional speckle tracking echocardiography (2D-STE) and three-dimensional speckle tracking echocardiography (3D-STE) parameters, with strain presented in absolute terms. Collecting and comparing clinical and echocardiographic parameters from three groups, assessing 3D-STI's value in evaluating LV functional impairment in CKD patients via correlation and receiver operating characteristic (ROC) curve analyses, and identifying risk factors for CKD progression to end-stage renal disease (ESRD) through univariate and multivariate analyses. In CKD2 group, 2D-left ventricular ejection fraction (LVEF), 3D-LVEF, 2D left ventricular global longitudinal strain (2D-LVGLS), 3D-LVGLS, and 3D-left ventricular global circumferential peak strain (LVGCS) significantly worsen compared to the control and CKD1 groups, with statistically significant distinctions between the latter two (all p < 0.05). The absolute value of 3D-LVGLS shows a robust correlation with N-terminal pro-B-type natriuretic peptide (NT-proBNP) and serum creatinine (Scr) (r = -0.598, -0.649, both p < 0.001). ROC curve analysis indicates higher diagnostic efficacy of 3D-LVGLS and 3D-LVGCS for LV systolic function than 2D-LVGLS. Univariate and multivariate analyses reveal an independent association of 3D-LVGLS with the progression to ESRD in CKD. 3D-LVGLS and 3D-LVGCS effectively detect LV dysfunction in CKD patients. Specifically, 3D-LVGLS demonstrates a robust correlation with NT-proBNP and Scr and is independently linked to CKD progressing to ESRD.

Event-Based Measurement of Aeroelastic Structure in High-Speed Flow

In high-speed aerodynamics research, point sensors are ideal for embedding in test models but lack spatial resolution, whereas high-speed cameras offer spatiotemporally resolved measurement but involve significant footprint, cost, and data size. To address these tradeoffs, this study explores the application of nascent event-based cameras for high-speed tests. Event-based cameras support continuous, data-sparse kilohertz-equivalent imaging at 720p resolution, on form factors as small as 36 mm and 40 grams in mass, combining the benefits of point sensors and high-speed cameras. However, these attributes come from asynchronous pixels that necessitate unique operating and postprocessing approaches. Here, the authors adapted event-based cameras for two-/three-dimensional photogrammetric tracking of aeroelastic structures, demonstrating an event-based workflow and two tracking algorithms (mean-shift filtering and circle fit). Bench-top validations achieved three-dimensional precision of 0.35 mm/s on 20 mm/s motion across a 259 mm field of view, while two-dimensional measurements of an aeroelastic titanium panel in Mach 0.76 transonic flow successfully identified millimeter-scale vibrations at 43.7, 120, and 270 Hz, validated against a laser displacement and high-speed camera. The transonic test’s raw data were 145.8 MB on the event-based camera, compared to 88.5 GB on the high-speed camera. The presented results demonstrated the viability of event-based techniques in high-speed aerodynamic testing, while highlighting challenges such as polarity switching and pixel latency.

Multidimensional social influence drives leadership and composition-dependent success in octopus-fish hunting groups.

Collective behaviour, social interactions and leadership in animal groups are often driven by individual differences. However, most studies focus on same-species groups, in which individual variation is relatively low. Multispecies groups, however, entail interactions among highly divergent phenotypes, ranging from simple exploitative actions to complex coordinated networks. Here we studied hunting groups of otherwise-solitary Octopus cyanea and multiple fish species, to unravel hidden mechanisms of leadership and associated dynamics in functional nature and complexity, when divergence is maximized. Using three-dimensional field-based tracking and field experiments, we found that these groups exhibit complex functional dynamics and composition-dependent properties. Social influence is hierarchically distributed over multiscale dimensions representing role specializations: fish (particularly goatfish) drive environmental exploration, deciding where, while the octopus decides if, and when, the group moves. Thus, 'classical leadership' can be insufficient to describe complex heterogeneous systems, in which leadership instead can be driven by both stimulating and inhibiting movement. Furthermore, group composition altered individual investment and collective action, triggering partner control mechanisms (that is, punching) and benefits for the de facto leader, the octopus. This seemingly non-social invertebrate flexibly adapts to heterospecific actions, showing hallmarks of social competence and cognition. These findings expand our current understanding of what leadership is and what sociality is.

Quantitative evaluation of radiation-induced heart disease in patients with lung cancer: a three-dimensional speckle tracking imaging study.

Adverse cardiovascular events due to radiation-induced heart disease (RIHD) have become the leading cause of death in cancer survivors, and early screening for RIHD has become an important clinical issue. Our objective was to determine the utility of three-dimensional speckle tracking echocardiography (3D-STE) for detecting RIHD. According to inclusion and exclusion criteria, patients with lung cancer who received radiotherapy in our hospital for the first time were recruited as subjects. All subjects underwent the conventional echocardiography and 3D-STE examination at six time points (1 day before radiotherapy, 2.5-3 and 5-6 weeks after beginning radiotherapy, and 3-, 6- and 12-month after ending radiotherapy). Routine electrocardiogram, serum cardiac troponin I (cTnI) and clinical data were detected simultaneously. A total of 105 patients with lung cancer were included in the study. Conventional echocardiography found a small amount of pericardial effusion occurred in 8 subjects at 5-6 weeks after beginning radiotherapy. 3D-STE showed that, compared with before radiotherapy, the absolute values of global longitudinal strain (GLS) and global strain (GS) were significantly decreased at 5-6 weeks after beginning radiotherapy (PGLS<0.001, PGS=0.002), and the absolute values of GLS, global radial strain, global circumferential strain, GS were gradually decreased further at 3-, 6- and 12-month after ending radiotherapy (P<0.001). Electrocardiograph showed that 32 subjects had electrocardiograph abnormalities during radiotherapy and 3 had electrocardiograph abnormalities at 3-month after ending radiotherapy, and most returned to normal within 6 months after ending radiotherapy. Patients with lung cancer undergoing radiation therapy have shown a decrease in the function of the left ventricle of the heart while receiving treatment. Combining the assessment of cTnI with GLS can enhance the early detection of radiation-induced heart damage.

Influence of texting while walking on lower extremity gait function in young adults

Texting while walking (TWW) is a dual-task activity that young adults perform in their everyday lives. TWW has been reported to affect gait characteristics such as gait speed, stride length, and cadence. However, the influence of TWW on lower extremity gait function has not been investigated. Therefore, the purpose of this study was to quantify gait function by examining gait symmetry and using a time series analysis. Twenty-eight young adults (14 males, 14 females) walked at their preferred speed for 10 m as a baseline condition and a 10 m TWW task. Three-dimensional segment tracking was achieved utilizing a lower extremity and trunk marker set and the Model Statistic was used to test for statistical differences between the hip, knee, and ankle angular joint positions. The hip yielded the most asymmetries (25 out of 101 points) throughout the gait cycle, while asymmetries for the knee and ankle joints yielded 16 out of 101 points and 11 out of 101 points, respectively. The outcomes of this study suggest there are differences between baseline and TWW gait symmetry, however, the percentage of the gait cycle affected was less than 25 % - indicating gait function is not strongly influenced by texting while walking in young adults.

Viscosity-dependent swimming patterns assist Aliivibrio fischeri for symbiont partner finding

Bacteria employ diverse swimming patterns for chemotaxis, influenced by factors including flagellar arrangements, motor rotation, flagellar filament configurations, and polymorphism. Understanding the chemotactic strategy of in locating a squid partner is paramount for comprehending this highly species-specific symbiosis. In this study, we applied three-dimensional swimming tracking and real-time visualization of lophotrichous flagellar configurations. These techniques unveiled viscosity-dependent transitions in swimming patterns, shifting from push-pull to push-wrap modes. Notably, our research also revealed coupled flagellar switching and polymorphic transformations during the wrap mode, significantly extending 's backward swimming duration and, consequently, its overall runtime. This strategic adaptation allows to broaden its effective search range, particularly within high-viscosity environments like the squid light organ. In response to attractants, the coupling rate is reduced to facilitate efficient short-range searching. These innovative chemotactic strategies ensure precise navigation for in locating and colonizing its symbiotic partner, the squid . Published by the American Physical Society 2024

Three-dimensional positioning and trajectory tracking of pigeons in large indoor spaces

Animal localization and trajectory tracking are of great value for the study of brain spatial cognition and navigation neural mechanisms. However, traditional optical lens video positioning techniques are limited in their scope due to factors such as camera perspective. For pigeons with excellent spatial cognition and navigation abilities, based on the beacon positioning technology, a three-dimensional (3D) trajectory positioning and tracking method suitable for large indoor spaces was proposed, and the corresponding positioning principle and hardware structure were provided. The results of in vitro and in vivo experiments showed that the system could achieve centimeter-level positioning and trajectory tracking of pigeons in a space of 360 cm × 200 cm × 245 cm. Compared with traditional optical lens video positioning techniques, this system has the advantages of large space, high precision, and high response speed. It not only helps to study the neural mechanisms of pigeon 3D spatial cognition and navigation, but also has high reference value for trajectory tracking of other animals.

Trajectory tracking control of vectored thruster autonomous underwater vehicles based on deep reinforcement learning

ABSTRACT Vectored thruster autonomous underwater vehicles (AUVs) offer superior manoeuvrability compared to traditional fin and rudder systems, especially at low or zero velocities. However, controlling these AUVs becomes challenging in the presence of unpredictable interference forces and external water flow velocities. This paper introduces a novel three-dimensional trajectory tracking method for vectored thruster AUVs using reinforcement learning, enabling the system to learn optimal control policies through environmental interaction. A 5-degree of freedom (5-DOF) model is developed from the kinematics and dynamics equations of the underactuated AUV. An extended state observer (ESO) is used to estimate the differential expansion state based on observed variables. A reinforcement learning-based trajectory tracking strategy is then implemented. Simulation experiments demonstrate the method’s effectiveness in precisely controlling AUVs under varying environmental conditions, achieving exceptional tracking accuracy even in the presence of random interference forces and external water flow velocities.

Intra-Frame Graph Structure and Inter-Frame Bipartite Graph Matching with ReID-Based Occlusion Resilience for Point Cloud Multi-Object Tracking

Three-dimensional multi-object tracking (MOT) using lidar point cloud data is crucial for applications in autonomous driving, smart cities, and robotic navigation. It involves identifying objects in point cloud sequence data and consistently assigning unique identities to them throughout the sequence. Occlusions can lead to missed detections, resulting in incorrect data associations and ID switches. To address these challenges, we propose a novel point cloud multi-object tracker called GBRTracker. Our method integrates an intra-frame graph structure into the backbone to extract and aggregate spatial neighborhood node features, significantly reducing detection misses. We construct an inter-frame bipartite graph for data association and design a sophisticated cost matrix based on the center, box size, velocity, and heading angle. Using a minimum-cost flow algorithm to achieve globally optimal matching, thereby reducing ID switches. For unmatched detections, we design a motion-based re-identification (ReID) feature embedding module, which uses velocity and the heading angle to calculate similarity and association probability, reconnecting them with their corresponding trajectory IDs or initializing new tracks. Our method maintains high accuracy and reliability, significantly reducing ID switches and trajectory fragmentation, even in challenging scenarios. We validate the effectiveness of GBRTracker through comparative and ablation experiments on the NuScenes and Waymo Open Datasets, demonstrating its superiority over state-of-the-art methods.

Enhanced three-dimensional trajectory tracking control for AUVs in variable operating conditions using FMPC-FTTSMC

In addressing the variable operating conditions encountered in complex underwater tasks, an enhanced three-dimensional tracking control method is proposed for autonomous underwater vehicle (AUV) based on fuzzy model predictive control-finite time terminal sliding mode control (FMPC-FTTSMC). Firstly, to enhance adaptability to tasks and environments, fuzzy model predictive control method is designed to achieve precise three-dimensional trajectory tracking. Additionally, a fuzzy weight allocator is employed to enable AUV to autonomously adjust optimization strategies based on real-time states such as task type, speed, and distance from the seabed, thus better coping with changing conditions and improving the universality of the control method. Secondly, a dynamic controller is designed using the finite-time terminal sliding mode control method, combined with a finite-time radial basis function neural network (FTRBFNN) disturbance observer to accurately estimate disturbances. Finally, simulation results demonstrate that the proposed method effectively reduces optimization solving time compared to traditional model predictive control, achieves trajectory tracking control under various conditions, meets preset state constraints, and demonstrates excellent tracking accuracy and robustness.

The speed and phase of locomotion dictate saccade probability and simultaneous low-frequency power spectra.

Every day we make thousands of saccades and take thousands of steps as we explore our environment. Despite their common co-occurrence in a typical active state, we know little about the coordination between eye movements, walking behaviour and related changes in cortical activity. Technical limitations have been a major impediment, which we overcome here by leveraging the advantages of an immersive wireless virtual reality (VR) environment with three-dimensional (3D) position tracking, together with simultaneous recording of eye movements and mobile electroencephalography (EEG). Using this approach with participants engaged in unencumbered walking along a clear, level path, we find that the likelihood of eye movements at both slow and natural walking speeds entrains to the rhythm of footfall, peaking after the heel-strike of each step. Compared to previous research, this entrainment was captured in a task that did not require visually guided stepping - suggesting a persistent interaction between locomotor and visuomotor functions. Simultaneous EEG recordings reveal a concomitant modulation entrained to heel-strike, with increases and decreases in oscillatory power for a broad range of frequencies. The peak of these effects occurred in the theta and alpha range for slow and natural walking speeds, respectively. Together, our data show that the phase of the step-cycle influences other behaviours such as eye movements, and produces related modulations of simultaneous EEG following the same rhythmic pattern. These results reveal gait as an important factor to be considered when interpreting saccadic and time-frequency EEG data in active observers, and demonstrate that saccadic entrainment to gait may persist throughout everyday activities.