Trajectory Segments Research Articles

Experimental assessment of IMU data processing techniques for a backpack mobile laser scanning system

Abstract. Positioning techniques are fundamental in many automation tasks with several applications. In GNSS-denied environments like in dense forests, other alternatives are required, such as inertial and visual navigation. However, Inertial Measurement Units (IMUs) data, mainly those from microelectromechanical-system (MEMS), are noisy, which affects the orientation estimation. MEMS IMUs have been employed in mobile laser scanning systems due to their compact design and low-cost solutions for short-term navigation. In this paper, we have compared three IMU processing techniques freely available: MAH (Mahony et al., 2009), MAD (Madgwick et al., 2011) and DCM (Hyyti and Visala, 2015). These techniques implemented different approaches to estimate the attitude. They were experimentally assessed with data from a backpack mobile laser scanning system, which is composed of an OS0-128 Ouster LiDAR equipped with an internal IMU. We have used data from a 5-second trajectory segment aiming to evaluate the attitude and position estimation for a local path. The results showed that the DCM algorithm maintained a consistent velocity for 5 seconds, achieving a positional error of 1.4 m, 0.06 m, and 1.05 m along the X-, Y- and Z-axis, respectively. In contrast, MAD and MAH showed a position error over 20 m, 7 m and 3 m along the X-, Y- and Z-axis, respectively, which was affected by the velocity drift.

Augmented and Virtual Reality Based Segmentation Algorithm for Human Pose Detection in Wearable Cameras

Pose graph optimisation is a crucial method that helps reduce cumulative errors while estimating visual trajectories for wearable cameras. However, when the posture graph's size increases with each additional camera movement, the optimization's efficiency diminishes. In terms of ongoing sensitive applications, such as extended reality and computer-generated reality, direction assessment is a major test. This research proposes an incremental pose graph segmentation technique that accounts for camera orientation variations as a solution to this challenge. The computation only improves the cameras that have seen large direction changes by breaking the posture chart during these instances. As a result, pose graph optimisation is essentially slowed down and optimised more quickly. For every camera that hasn't been optimised using a pose graph, the algorithm employs the wearable cameras at the start and end of each camera's trajectory segment. The final camera in attendance is then determined by weighted average the various postures evaluated with these wearable cameras; this eliminates the need for lengthy nonlinear enhancement computations, reduces disturbance, and achieves excellent accuracy. Experiments on the EuRoC, TUM, and KITTI datasets demonstrate that pose graph optimisation scope is reduced while maintaining camera trajectories accuracy.

A note on the computation of multi-revolution NRHO under the ephemeris model

Near Rectilinear Halo Orbits (NRHOs) are vital to manned lunar and deep space exploration, which nowadays are of great interest for different space agencies and in particular with regard to the future space station. However, the required computation of multi-revolution NRHO under the ephemeris model is difficult, especially for the NRHOs with low periapsis relative to the secondary body. This paper explores this issue from the perspective of multiple shooting, first analyzing the influence of the state transition matrices by means of their condition number and then, focusing on a good selection of trajectory segments with suitable patch points. The methodology considerably improves the convergence and the computation under the ephemeris model. Numerical simulations show that at least 30 revolutions can be achieved for NRHOs with perilune radius of less than 12,000 km around L1 or period less than 8.8 days around L2; meanwhile, the number of segments used can be as low as 2 for each single revolution. As for the position of patch points, the first and last points of each revolution should be apart from the Moon, and the distance can be reduced only when the number of segments increases. The proposed method requires no dedicated optimization algorithm or commercial software to produce the multi-revolution NRHOs.

Self‐supervised vessel trajectory segmentation via learning spatio‐temporal semantics

AbstractThe study of vessel trajectories (VTs) holds significant benefits for marine route management and resource development. VT segmentation serves as a foundation for extracting vessel motion primitives and enables analysis of vessel manoeuvring habits and behavioural intentions. However, existing methods relying on predefined behaviour patterns face high labelling costs, which hinder accurate pattern recognition. This paper proposes a self‐supervised vessel trajectory segmentation method (SS‐VTS), which segments VTs based on their inherent spatio‐temporal semantics. SS‐VTS adaptively divides VTs into cells of optimal size. Then, it extracts split points on different semantic levels from the multi‐dimensional feature sequence of the VTs using self‐supervised learning. Finally, spatio‐temporal distance fusion module is performed on split points to determine change points and obtain VT segments with multiple semantics. Experiments on a real automatic identification system datasets show that SS‐VTS achieves state‐of‐the‐art segmentation results compared to seven baseline methods.

Long-term tracking for high-frequency surface wave radar based on heading constraint filtering combined ELM

Abstract Aiming at the problem of low measurement resolution and poor tracking accuracy in High-frequency surface wave radar (HFSWR) tracking field, a tracking method that combines the heading constraint filter and Extreme Learning Machine (ELM) is proposed. Compared with the existing research, the innovation of this study lies in proposing a two-stage tracking method based on the short-term stable state of the target, and similarity of long-term trajectory. Firstly, the heading constraint information is introduced into the estimator and improve the estimation accuracy. In multi-target tracking scenarios, many tracklets can be obtained. Then, the ELM learns robust features of tracklets to achieve the trajectory segment classification from the same target. This method can be widely applied to long-term tracking of cargo or passenger ships with fixed destinations, significantly improving tracking performance by utilizing implicit domain knowledge without additional information. The actual data of this paper comes from HFSWR on Bohai Bay. Both the simulation and actual measurement experiments show that the proposed cascaded tracking method achieves long-term continuous tracking, and generates more complete trajectories. Moreover, the proposed Extended Kalman filter based on pseudo-measurement and intercept parameters (IPM-EKF) exhibits better tracking stability and accuracy in limited scan steps. This study provides new ideas and methods for improving the tracking performance of special targets in the HFSWR field by utilizing motion features.

An adaptive trajectory segmentation and simplification algorithm based on vessel behavioral features

Existing algorithms for trajectory simplification in AIS data processing have issues such as loss of key feature points, high subjectivity in threshold selection, and incomplete consideration of factors. In this paper, an adaptive trajectory segmentation and simplification algorithm based on vessel behavioral features is proposed. The algorithm identifies behavioral feature intervals by extracting vessel behavioral features and constructs an adaptive segmentation threshold function to achieve adaptive segmentation of trajectories and extraction of key feature points. Then, considering the quality, similarity, and spatial variability of trajectory simplification, an adaptive simplification threshold function is constructed to automatically select the best threshold for each sub-trajectory to generate the simplified trajectory. Our experiments demonstrate that the algorithm maintains a high simplification rate while enabling adaptive simplification of the trajectory, and also retains the key feature points and trajectory shapes to the maximum extent. The effectiveness and robustness of the algorithm are verified through comparison with other algorithms, effectively avoiding the distortion of navigational behavior that may be caused by traditional methods. This provides reliable data support for maritime traffic management and decision-making.

Parameter optimization of the field-road trajectory segmentation model based on the chaos sensing slime mould algorithm

Parameter optimization of the field-road trajectory segmentation model based on the chaos sensing slime mould algorithm

Segmented assimilation trajectories of physician trust among internal migrants in Shanghai, China: A cross-sectional study

Physician trust is necessary for improving physician–patient relationships and maintaining an effective health-care system. Most studies on the theory of segmentation assimilation have mainly focused on comparing immigrants in different countries and few studies have applied segmented assimilation to clarify physician–patient relationships, especially physician trust among internal migrants in the context of Chinese megacities. A random sample of 1200 internal migrants was collected through an online questionnaire conducted in Shanghai from August to December 2021. An exploratory K-means cluster analysis and multivariate logistic regression models were employed to identify patterns of segmented assimilation and examine their relationships with physician trust, as well as the factors influencing physician trust among internal migrants in Shanghai. Results show four main patterns were revealed, namely first-generation classic assimilation, first-generation integrative assimilation, first-generation segmentation, and second-generation underclass assimilation, supporting the theory of segmented assimilation. Association between assimilation pattern and physician trust was observed. A relationship was found between assimilation patterns and trust in physicians. Migrants belonging to the first-generation classic and integrative assimilation groups exhibited a higher level of trust in doctors compared to those in the segmented assimilation groups. Additionally, undergraduate and postgraduate education attainment, an annual income of <400 000 yuan, visiting the physician ≥2 times in the past year, and self-rated health status before and after population floating were significant contributing factors for good physician trust. The government can implement corresponding measures to maintain physician trust, improve cultural adaptability instead of only at the economic level among internal migrants, achieving the facilitation of their understanding of the health system and health service utilization to increase physician trust.

Unsupervised Approach for Multimodality Telerobotic Trajectory Segmentation

Unsupervised Approach for Multimodality Telerobotic Trajectory Segmentation

Vehicle Ego-Trajectory Segmentation Using Guidance Cues

Computer vision has significantly influenced recent advancements in autonomous driving by providing cutting-edge solutions for various challenges, including object detection, semantic segmentation, and comprehensive scene understanding. One specific challenge is ego-vehicle trajectory segmentation, which involves learning the vehicle’s path and describing it with a segmentation map. This can play an important role in both autonomous driving and advanced driver assistance systems, as it enhances the accuracy of perceiving and forecasting the vehicle’s movements across different driving scenarios. In this work, we propose a deep learning approach for ego-trajectory segmentation that leverages a state-of-the-art segmentation network augmented with guidance cues provided through various merging mechanisms. These mechanisms are designed to direct the vehicle’s path as intended, utilizing training data obtained with a self-supervised approach. Our results demonstrate the feasibility of using self-supervised labels for ego-trajectory segmentation and embedding directional intentions within the network’s decisions through image and guidance input concatenation, feature concatenation, or cross-attention between pixel features and various types of guidance cues. We also analyze the effectiveness of our approach in constraining the segmentation outputs and prove that our proposed improvements bring major boosts in the segmentation metrics, increasing IoU by more than 12% and 5% compared with our two baseline models. This work paves the way for further exploration into ego-trajectory segmentation methods aimed at better predicting the behavior of autonomous vehicles.

BAD-NEUS: Rapidly converging trajectory stratification.

An issue for molecular dynamics simulations is that events of interest often involve timescales that are much longer than the simulation time step, which is set by the fastest timescales of the model. Because of this timescale separation, direct simulation of many events is prohibitively computationally costly. This issue can be overcome by aggregating information from many relatively short simulations that sample segments of trajectories involving events of interest. This is the strategy of Markov state models (MSMs) and related approaches, but such methods suffer from approximation error because the variables defining the states generally do not capture the dynamics fully. By contrast, once converged, the weighted ensemble (WE) method aggregates information from trajectory segments so as to yield unbiased estimates of both thermodynamic and kinetic statistics. Unfortunately, errors decay no faster than unbiased simulation in WE as originally formulated and commonly deployed. Here, we introduce a theoretical framework for describing WE that shows that the introduction of an approximate stationary distribution on top of the stratification, as in nonequilibrium umbrella sampling (NEUS), accelerates convergence. Building on ideas from MSMs and related methods, we generalize the NEUS approach in such a way that the approximation error can be reduced systematically. We show that the improved algorithm can decrease the simulation time required to achieve the desired precision by orders of magnitude.

Aerial Hybrid Adjustment of LiDAR Point Clouds, Frame Images, and Linear Pushbroom Images

In airborne surveying, light detection and ranging (LiDAR) strip adjustment and image bundle adjustment are customarily performed as separate processes. The bundle adjustment is usually conducted from frame images, while using linear pushbroom (LP) images in the bundle adjustment has been historically challenging due to the limited number of observations available to estimate the exterior image orientations. However, data from these three sensors conceptually provide information to estimate the same trajectory corrections, which is favorable for solving the problems of image depth estimation or the planimetric correction of LiDAR point clouds. Thus, our purpose with the presented study is to jointly estimate corrections to the trajectory and interior sensor states in a scalable hybrid adjustment between 3D LiDAR point clouds, 2D frame images, and 1D LP images. Trajectory preprocessing is performed before the low-frequency corrections are estimated for certain time steps in the following adjustment using cubic spline interpolation. Furthermore, the voxelization of the LiDAR data is used to robustly and efficiently form LiDAR observations and hybrid observations between the image tie-points and the LiDAR point cloud to be used in the adjustment. The method is successfully demonstrated with an experiment, showing the joint adjustment of data from the three different sensors using the same trajectory correction model with spline interpolation of the trajectory corrections. The results show that the choice of the trajectory segmentation time step is not critical. Furthermore, photogrammetric sub-pixel planimetric accuracy is achieved, and height accuracy on the order of mm is achieved for the LiDAR point cloud. This is the first time these three types of sensors with fundamentally different acquisition techniques have been integrated. The suggested methodology presents a joint adjustment of all sensor observations and lays the foundation for including additional sensors for kinematic mapping in the future.

TrajPredRNN+: A new approach for precipitation nowcasting with weather radar echo images based on deep learning

：Short-term rainfall prediction is a crucial and practical research area, with the accuracy of rainfall prediction, particularly for heavy rainfall, significantly impacting people's lives, property, and even their safety. Existing models, such as ConvLSTM, TrajGRU, and PredRNN, exhibit limitations in capturing fine-grained appearances due to insufficient memory units or addressing positional misalignment issues, thereby compromising the accuracy of model predictions. In this study, we propose trajPredRNN+, an innovative approach that integrates the trajectory segmentation model and the PredRNN deep learning model to address both limitations in nowcasting precipitation using weather radar echo images. By incorporating attention mechanisms, the model demonstrates an enhanced focus on short-term and imminent heavy rainfall events. To ensure improved stability during training, a residual network is introduced. Lastly, a more rational and effective training loss function is proposed, encompassing weight mechanism, SSIM index, and GAN loss. To validate the proposed model, we conducted a comparative experiment and an ablation experiment using the radar echo map dataset obtained from the Shenzhen Meteorological Bureau. The results of these experiments demonstrate that our model has achieved significant improvements across multiple key performance indicators.

A segmented trajectory planning and guidance method for hypersonic glide vehicles considering target detection performance

This paper proposes a closed-loop detection and guidance method for optimizing the detection effectiveness of Radio Frequency (RF) stealth targets by terminal-guided hypersonic glide vehicles (HGV) during the terminal-guidance phase. This method divides the guidance process into two stages based on the detectability of the target. In the search stage, the Twin Delayed Deep Deterministic Policy Gradient (TD3) coupled with Successive Convex Optimization (SCO) guidance method is employed. This approach separates the detection performance from the numerical solution process of the optimization problem, enabling online adjustment of performance indicator functions to refine trajectory configurations. In the tracking phase, the dynamic characteristics of the target's Radar Cross Section (RCS) are convexified and discretized, incorporated into the objective function of the optimization problem as performance indicators. The Higher-Order Soft-Trust-Region Sequential Convex Programming (HSSCP) method is employed to improve the convergence of the algorithm. Additionally, the online trajectory planning problem is integrated into the Model Predictive Control (MPC) framework to achieve closed-loop guidance. Simulation results indicate that this method can improve the detection performance of RF stealthy targets during the terminal guidance phase, the cumulative detection information for the target increased by approximately 20.6%, and the maximum instantaneous detection probability improved by about 14.3%. Moreover, it can achieve convergence of complex multi-constraint problems within a limited number of iterations.

Port performance indicators construction based on the AIS-generated trajectory segmentation and classification

AbstractWith coverage of worldwide shipping routes and straightforward accessibility, vessels’ navigational data from AIS have emerged as a potential leading source of knowledge for maritime stakeholders. However, transforming the raw AIS messages into meaningful indicators requires comprehensive work that involves enrichment with multiple relevant data sources. In this study, a fain-grained technique to process AIS tracks for the purpose of constructing port performance indicators is proposed. The technique involves trajectory segmentation to separate the stopping and underway segments of AIS-generated trajectories and trajectory classification to identify moored and at-anchor vessels from the stopping segments. With the fusion of relevant information, the method estimates the port boundary and identifies the associated berthing and anchorage locations to estimate turnaround time and construct port connectivity indicators. AIS datasets recorded over eight months covering the waters of Indonesia, Malaysia, and Singapore, known as one of the world’s busiest shipping routes, are selected to evaluate the proposed method. The trajectory segmentation demonstrated 98–99% accuracy, while the classification achieved 95–97%. The estimation of the vessel turnaround time closely matched the UNCTAD data with an error rate of 2.9%. These results prove the proposed approach’s practicality in contributing to the real-world scenario.

Informer-Based Model for Long-Term Ship Trajectory Prediction

Ship trajectory prediction is a complex time series forecasting problem that necessitates models capable of accurately capturing both long-term trends and short-term fluctuations in vessel movements. While existing deep learning models excel in short-term predictions, they struggle with long-sequence time series forecasting (LSTF) due to difficulties in capturing long-term dependencies, resulting in significant prediction errors. This paper proposes the Informer-TP method, leveraging Automatic Identification System (AIS) data and based on the Informer model, to enhance the ability to capture long-term dependencies, thereby improving the accuracy of long-term ship trajectory predictions. Firstly, AIS data are preprocessed and divided into trajectory segments. Secondly, the time series is separated from the trajectory data in each segment and input into the model. The Informer model is utilized to improve long-term ship trajectory prediction ability, and the output mechanism is adjusted to enable predictions for each segment. Finally, the proposed model’s effectiveness is validated through comparisons with baseline models, and the influence of various sequence lengths Ltoken on the Informer-TP model is explored. Experimental results show that compared with other models, the proposed model exhibits the lowest Mean Squared Error, Mean Absolute Error, and Haversine distance in long-term forecasting, demonstrating that the model can effectively capture long-term dependencies in the trajectories, thereby improving the accuracy of long-term vessel trajectory predictions. This provides an effective and feasible method for ensuring ship navigation safety and advancing intelligent shipping.

Low-Energy Transfers to Lunar Distant Retrograde Orbits from Geostationary Transfer Orbits

This study focuses on the low-energy transfers to lunar distant retrograde orbits (DROs) from geostationary transfer orbits (GTOs) in the bicircular-restricted sun–Earth–moon four-body problem. The low-energy transfer is essential for low-cost small satellites reaching out to the Moon, and the departure from GTO allows more rideshare opportunities. We first created several large-scale databases of trajectory segments, such as GTO to apogee in the weak-stability area, apogee to perilune, and DRO to perilune. Then, millions of GTO–DRO transfer trajectories with double powered lunar flybys (PLFs) and weak stability boundary (WSB) ballistic transfer were constructed through trajectory patching. The key flight information, such as the ΔV–time-of-flight Pareto fronts, launch windows, and the flight mode via WSB ballistic transfer, is obtained from feasible solutions. Results show that low-energy GTO–DRO transfers can be achieved by exploiting PLFs and WSB ballistic arcs, which suggests potential applications in the cislunar space.

Surgical robot open surgery trajectory planning based on machine vision and improved genetic algorithm

Aiming at the difficulty of trajectory planning for open surgery of surgical robot, a method based on machine vision and improved genetic algorithm is proposed to solve the trajectory planning of open surgery of surgical robot. This method extracts the contour curve of the incision site of human open surgery from the image through the feature recognition algorithm, and discretizes it into the trajectory planning stage. Based on the discretized model, the optimal surgical incision trajectory is obtained. Combined with the biological characteristics of the human abdomen and the improved genetic algorithm (GA), the spline curve is segmented trajectory planning, and the minimum number of segments is optimized. Finally, the trajectory planning results are converted to Cartesian space for programming according to the spatial pose relationship, and the optimal surgical trajectory is obtained to realize the preoperative planning of the content of open surgery.

Transient Plasma Wind Tunnel Testing Under Thermomechanical Loads for Reentry Break-Up Analysis

This paper introduces a novel approach for transient plasma wind tunnel testing in an arcjet facility, enabling the experimental simulation of the aerothermal loads along reentry trajectory segments. Such experiments newly allow for the investigation of the causes of break-up events. The trajectory segment is simulated by duplicating the time-resolved profiles of the characteristic flow parameters, namely, heat flux and stagnation pressure as well as the mechanical load, which represents the aerodynamic forces. In arcjet facilities, the parameters that govern the plasma condition are split into variable and constant parameters, which define the available altitude range that can be replicated. The variable conditions arc current and ambient pressure were determined with steady-state trajectory points and traces determined between these conditions resulting in a full trajectory segment. The test time then relates directly to an altitude on the trajectory segment, which allows for an experimental determination of the main break-up altitude. The methodology is applied to a trajectory segment of the transport vehicle CYGNUS OA6, covering an altitude range from 85 to 70 km. A transient break-up experiment on an aluminum bar yielded a failure at an altitude corresponding to 77.6 km, showing a thermomechanical characteristic. These results align well with the observed break-up altitude of CYGNUS OA6, showing the potential of the proposed method.

Research on differential data fusion processing method for dual GNSS base stations

Abstract In the differential processing of global navigation and positioning system (GNSS) trajectory data from dual base stations, a hierarchical fusion processing method is proposed based on the trajectory parameter layer for two trajectory parameters generated by the different dual base stations according to the distribution pattern. Trajectory segment that satisfies the differential baseline of a priori data accuracy are given high weight to prioritize for fusion, and the portion exceeding the maximum differential baseline distance is weighted fusion according to the sliding window plus polynomial fitting to determine the weighted coefficients. By practical testing, the statistical residuals of the weighted fusion trajectory in the horizontal and vertical directions reduced by 32.83% and 30.19% respectively compared to the unfused trajectory.