Motion Trajectory Analysis Research Articles

Mapping trajectories and flows: facilitating a human-centered approach to movement data analytics

ABSTRACT This paper argues for a “human-centered” approach to knowledge discovery from movement data through the use of visualization and mapping. As movement data becomes more available and diverse in dimension and resolution, mapping becomes particularly important in the exploratory analysis of movement trajectories and for capturing patterns and structures in large origin-destination flow data sets. Movement phenomena (e.g. ranging from micro-movements of humans and animals to macro-level mobility, to migration flows, to spread of viruses) are complex dynamic processes which are realized in a multidimensional location-time-context space. This paper provides a comprehensive overview of various visualization techniques for mapping movement through the lens of cartography and with a special focus on the “human user” (e.g. data scientist, analyst, domain expert, etc.). We systematically characterize and categorize available techniques based on their visual specifications and functional capacities for human control, map-interaction, and design flexibility. These elements are beneficial to enhance the user’s capacities for map reasoning and knowledge discovery. Trends and gaps in the literature on movement visualization over the past 10 years are discussed. Our review suggests that future research should focus more on the role of the “human” in the development of human-centered visual analytic and exploratory tools, while providing functionalities for mapping uncertainty and protecting individual privacy in knowledge discovery of movement. These tools should be guided by a cartographic framework and visual principles specifically pertinent to movement.

Learning Trajectory Patterns via Canonical Correlation Analysis

A substantial body of research has been devoted to the analysis of motion trajectories. Usually, a motion trajectory consists of a set of coordinates, which is called a raw trajectory. In this paper, the authors first use vectors for some artificially constructed global features, such as the mean discrete curvature and standard deviation of acceleration, to represent the raw trajectory data, and then apply a multiset canonical correlation analysis method to extract latent features from the artificially constructed features. The performance of the latent features is then measured by evaluating the accuracy and F1 score of a gradient boosting decision tree model for different datasets, which include paired sample datasets and unpaired sample datasets. The experimental results show that the classifier performance for MCCA features is much better than that obtained for the artificially constructed features, such as that for the motion distance or mean velocity.

Wind tunnel experiments for dynamic modeling and analysis of motion trajectories of wind-blown sands.

The hazards associated with travelling on highways in desert regions arise mainly from wind-borne sand disasters, such as complete or partial burial of the road surface by sand particles, and from erosion of the roadbed by the particles. To simulate the damage process caused by sand particles on roads in the desert, scaled-down tests were performed in a wind tunnel whereby sand particles of differing diameters and roadbed models of different gradients were tested and the impact trajectories of the sand particles were captured using a high-speed camera. The results showed that the impact trajectories may be classified into four types, and the proportion of each type is essentially stable with the statistical curves for the trajectories being similar to the Poisson distribution. The diameters of the sand particles and the slopes of the roadbed model influenced the impact trajectories, which also impacted the statistical values for each particle type. Owing to the Magnus force, the direction of rotation and the angular velocity of the sand particles controlled the nature of the collision trajectories; however, the direction of rotation did not remain in a fixed plane and the rotation speed only reached about 20% of the value of the first critical speed. The wind tunnel experiments enable a better understanding of the motion trajectories, rotation speed, force situation, and collision trajectories, providing a useful benchmark for research on wind-induced disasters on roads in desert regions.

Prediction and analysis of sphere motion trajectory based on deep learning algorithm optimization

Prediction and analysis of sphere motion trajectory based on deep learning algorithm optimization

Investigating the Use of Movement Kinematics to Assess Perceptual Ambiguity in Virtual Reality

With the emergence of 3D direct-selection interfaces in virtual reality (VR) displays, specialized metrics may be needed to assess the efficiency of these complex interactions. Kinematic movement trajectory analysis, an established technique in experimental psychology, may provide a useful framework for quantifying meaningful patterns of user interaction using the 3D position data recorded by most VR displays. We explored this possibility by investigating the effectiveness of a kinematic approach for identifying ambiguous interface elements in VR by detecting movements initiated toward incorrect target locations (termed “misfires”). Twenty-three participants selected 96 target objects of varying perceptual ambiguity presented in a simple VR environment with limited depth cues. Movement trajectories were recorded and evaluated using a-priori criteria to identify discontinuities consistent with misfire movements. Misfires were observed on 31.6% of trials and occurred significantly more often for movements to perceptually ambiguous targets. The findings of this study suggest that kinematic measures may be useful for quantifying patterns of user interaction in direct-selection VR interfaces.

Analysis of Movement Trajectories Focusing on the Interaction Torque in Arm Movements

Analysis of Movement Trajectories Focusing on the Interaction Torque in Arm Movements

Topology Optimization Analysis of Separation Mechanism for the Rice Trans-Planter

A mechanical topology regeneration design method based on the basic chain was presented which was reducing invalid topology design workload and improving optimization design efficiency. And it is used for configuration topology research of planetary separation mechanism of rice transplanting machine to verify its feasibility and effectiveness, which mainly consists of crank-rocker-separation mechanism, mechanical frame, planet carrier, total input shaft, and seedlings folder, and moving trajectory equation of seedling folder point A for the crank-rocker-separation mechanism is obtained according to the quadrangle vector closure principle. The topological synthesis diagram for motion chain for the CRSM was analysis by means of generalized treatment method based on theoretical optimization conditions and topological regeneration path design. The 6 kinds of topology diagram satisfying the design task for motion chair with high motion pair were obtained and the implemented mechanism diagram of kinematic chair for separation mechanism was designed based on the basic chain topology design method. The results show that topology design for the CRSM is relatively simplified for basic chain structure. And theoretical analysis of motion trajectory for the CRSM is relatively the same as the experimental results in the curve trend and relative error of angular displacement is reasonable and effective through test-rig comparative analysis with motion trajectory of crank-rocker-separation mechanism.

Multiscale analyses on a massive immigration process of Sogatella furcifera (Horváth) in south-central China: influences of synoptic-scale meteorological conditions and topography

Mass landings of migrating white-backed planthopper, Sogatella furcifera (Horváth), can lead to severe outbreaks that cause heavy losses for rice production in East Asia. South-central China is the main infestation area on the annual migration loop of S. furcifera between the northern Indo-China Peninsula and mainland China; however, rice planthopper species are not able to survive in this region over winter. In this study, a trajectory analysis of movements from population source areas and a spatiotemporal dynamic analysis of mesoscale and synoptic weather conditions from 7 to 10 May 2012 were conducted using the weather research and forecasting (WRF) model to identify source areas of immigrants and determine how weather and topographic terrain influence insect landing. A sensitivity experiment was conducted with reduced topography using the WRF model to explain the associations among rainfall, topography, and light-trap catches of S. furcifera. The trajectory modeling results suggest that the source areas of S. furcifera immigrants into south-central China from 8 to 10 May were mainly southern Guangxi, northern Vietnam, and north-central Vietnam. The appearance of enormous catches of immigrant S. furcifera coincided with a period of rainstorms. The formation of transporting southerly winds was strongly associated with the topographic terrain. Additionally, the rainfall distribution and intensity over south-central China significantly decreased when topography was reduced in the model and were directly affected by wind circulation, which was associated with mountainous terrain that caused strong convection. This study indicates that migrating populations of S. furcifera were carried by the southwesterly low-level jets and that topographically induced convergent winds, precipitation, low temperatures, and wind shear acted as key factors that led to massive landings.

A comparative study of in-field motion capture approaches for body kinematics measurement in construction

SummaryDue to physically demanding tasks in construction, workers are exposed to significant safety and health risks. Measuring and evaluating body kinematics while performing tasks helps to identify the fundamental causes of excessive physical demands, enabling practitioners to implement appropriate interventions to reduce them. Recently, non-invasive or minimally invasive motion capture approaches such as vision-based motion capture systems and angular measurement sensors have emerged, which can be used for in-field kinematics measurements, minimally interfering with on-going work. Given that these approaches have pros and cons for kinematic measurement due to adopted sensors and algorithms, an in-depth understanding of the performance of each approach will support better decisions for their adoption in construction. With this background, the authors evaluate the performance of vision-based (RGB-D sensor-, stereovision camera-, and multiple camera-based) and an angular measurement sensor-based (i.e., an optical encoder) approach to measure body angles through experimental testing. Specifically, measured body angles from these approaches were compared with the ones obtained from a marker-based motion capture system that has less than 0.1 mm of errors. The results showed that vision-based approaches have about 5–10 degrees of error in body angles, while an angular measurement sensor-based approach measured body angles with about 3 degrees of error during diverse tasks. The results indicate that, in general, these approaches can be applicable for diverse ergonomic methods to identify potential safety and health risks, such as rough postural assessment, time and motion study or trajectory analysis where some errors in motion data would not significantly sacrifice their reliability. Combined with relatively accurate angular measurement sensors, vision-based motion capture approaches also have great potential to enable us to perform in-depth physical demand analysis such as biomechanical analysis that requires full-body motion data, even though further improvement of accuracy is necessary. Additionally, understanding of body kinematics of workers would enable ergonomic mechanical design for automated machines and assistive robots that helps to reduce physical demands while supporting workers' capabilities.

Vehicle trajectory clustering based on 3D information via a coarse-to-fine strategy

Vehicle behavior analysis is often based on the motion trajectory analysis, which lays the foundation for many applications such as velocity detection, vehicle classification, and vehicle counting. In this paper, a trajectory clustering framework is proposed for vehicle trajectory analysis. Firstly, feature points are extracted by ORB algorithm which uses binary strings as an efficient feature point descriptor. Secondly, a matching method based on Hamming distance is used to obtain the tracking trajectory points. Finally, a novel clustering method, which contains three phrases, i.e., coarse clustering, fine clustering, and agglomerative clustering, is proposed to classify vehicle trajectory points based on the 3D information in real traffic video. By applying this clustering method in actual traffic scenes, much more stable clustering results can be obtained compared with other methods. Experimental results demonstrate that the accuracy of the proposed method can reach 95%. Furthermore, vehicle type can be estimated to realize vehicle classification.

Does visuomotor adaptation contribute to illusion-resistant grasping?

Do illusory distortions of perceived object size influence how wide the hand is opened during a grasping movement? Many studies on this question have reported illusion-resistant grasping, but this finding has been contradicted by other studies showing that grasping movements and perceptual judgments are equally susceptible. One largely unexplored explanation for these contradictions is that illusion effects on grasping can be reduced with repeated movements. Using a visuomotor adaptation paradigm, we investigated whether an adaptation model could predict the time course of Ponzo illusion effects on grasping. Participants performed a series of trials in which they viewed a thin wooden target, manually reported an estimate of the target's length, then reached to grasp the target. Manual size estimates (MSEs) were clearly biased by the illusion, but maximum grip apertures (MGAs) of grasping movements were consistently accurate. Illusion-resistant MGAs were observed immediately upon presentation of the illusion, so there was no decrement in susceptibility for the adaptation model to explain. To determine whether online corrections based on visual feedback could have produced illusion-resistant MGAs, we performed an exploratory post hoc analysis of movement trajectories. Early portions of the illusion effect profile evolved as if they were biased by the illusion to the same magnitude as the perceptual responses (MSEs), but this bias was attenuated prior to the MGA. Overall, this preregistered study demonstrated that visuomotor adaptation of grasping is not the primary source of illusion resistance in closed-loop grasping.

Indoor corner recognition from crowdsourced trajectories using smartphone sensors

Recently, fingerprint crowdsourcing from pedestrian movement trajectories has been promoted to alleviate the site survey burden for radio map construction in fingerprinting-based indoor localization. Indoor corners, as one of the most common indoor landmarks, play an important role in movement trajectory analysis. This paper studies the problem of indoor corner recognition in crowdsourced movement trajectories. In a movement trajectory, smartphone internal sensor measurements experience some signal changes when passing by a corner. However, the state-of-the-art solutions based on signal change detection cannot well deal with the fake corner problem and pose diversity problem in most practical movement trajectories. In this paper, we study the corner recognition problem from an expert system viewpoint by applying machine learning techniques. In particular, we extract recognition features from both the time and frequency domain and propose a hierarchical corner recognition scheme consisting of three classifiers. The first pose classifier is to classify various poses into only two groups according to whether or not a smartphone is kept in a fixed position relative to a user upper body when collecting sensor measurements. Feature selection is then applied to train two corner classifiers each for one pose group. Field experiments are conducted to compare our proposed scheme with three state-of-the-art algorithms. In all cases, our scheme outperforms the best of these algorithms in terms of much higher F1-measure and precision for corner recognition. The results also provide insights on the potentials of using more advanced techniques from expert systems in indoor localization.

Human field of regard, field of view, and attention bias

Background and objectiveHuman field of regard (FOR) is an important concept that should be considered along with field of view (FOV) for people with/without handicaps, but previous studies have neglected this aspect of human perception. In the current study, we suggest and test a new virtual reality (VR) software with which to evaluate individual's detection abilities in the human FOR. MethodsWe conducted measurements of human FOV, FOR, and FOR with visual cue (FOR-cue), and we evaluated healthy adults' responses in a first experiment. Participants were asked to detect targets on a head-mounted display (HMD) as quickly as possible in three conditions: (a) FOV: the head rotation doesn't change the view of the screen in the HMD; (b) FOR: the head rotation changes the view of the screen in the HMD; and (c) FOR-cue: same with the FOR condition but an endogenous visual cue indicating the direction of stimulus. To address the need to increase the number of trials in the FOR condition, we also conducted a second experiment with new samples and four times of trial numbers. ResultsThe participants' detection time results indicated that the FOV condition was faster than the FOR-cue and FOR conditions, and the FOR-cue was faster than the FOR condition. Interestingly, we found a unique characteristic in the FOR conditions that did not exist in the FOV condition: The target responses were faster for the left side than the right side. The results of the second experiment were consistent with the first, and head motion trajectory analysis showed that participants had more movement toward the left side than the right side in the early parts of each trial. ConclusionsIn this study, we suggested a new virtual reality (VR) evaluation technique and measured the human searching pattern in the FOR condition. We found a unique left-side attention bias in the FOR condition, and discussed implication of these results and potential attention bias factors. We believe this work is an important foundation for interactive 3D UI design, and we hope it will help people who have FOR handicaps.

A context-sensitive conceptual framework for activity modeling

Human motion trajectories, however captured, provide a rich spatiotemporal data source for human activity recognition, and the rich literature in motion trajectory analysis provides the tools to bridge the gap between this data and its semantic interpretation. But activity is an ambiguous term across research communities. For example, in urban transport research activities are generally characterized around certain locations assuming the opportunities and resources are present in that location, and traveling happens between these locations for activity participation, i.e., travel is not an activity, rather a mean to overcome spatial constraints. In contrast, in human-computer interaction (HCI) research and in computer vision research activities taking place "along the way," such as "reading on the bus," are significant for contextualized service provision. Similarly activities at coarser spatial and temporal granularity, e.g., "holidaying in a country," could be recognized in some context or domain. Thus the context prevalent in the literature does not provide a precise and consistent definition of activity, in particular in differentiation to travel when it comes to motion trajectory analysis. Hence in this paper, a thorough literature review studies activity from different perspectives, and develop a common framework to model and reason human behavior flexibly across contexts. This spatio-temporal framework is conceptualized with a focus on modeling activities hierarchically. Three case studies will illustrate how the semantics of the term activity changes based on scale and context. They provide evidence that the framework holds over different domains. In turn, the framework will help developing various applications and services that are aware of the broad spectrum of the term activity across contexts.

Analysis on the damage behavior of mixed ground during TBM cutting process

Accurate prediction of rock cutting forces of disc cutters is especially significant for the design and construction of tunnel boring machine (TBM). Through the analysis of motion trajectory of TBM disc cutters, a three-dimensional model of rock breaking process of disc cutters is established. In terms of the rock strain which is resulted from the interaction between disc cutters and rock during the process of rock breaking, a three-dimensional cutting forces model is proposed with disc cutters set at certain parameters and in certain sizes. Subsequently, the equation of contacting forces between rock and disc cutter is derived. Moreover, a new method has been presented for the study of the rock breaking theory of the disc cutter and it also provides guidance for the design and application of TBM in tunnel excavation. The three-dimensional model for the rock breaking mechanism is used for predicting the cutting force for the situation of mixed ground.The damage field and the rock failure zone induced by disc cutter for mixed ground are also discussed in this study. In detail, the rock damage zones are divided into two parts, one is the left damage field which located in the outside of disc cutter. The other is the right damage field which located in the outside of disc cutter. The influence of the rock ground dip on the rock failure zone was also studied by parameter analysis.

Establishment of tunnel-boring machine disk cutter rock-breaking model from energy perspective

As the most important cutting tools during tunnel-boring machine tunneling construction process, V-type disk cutter’s rock-breaking mechanism has been researched by many scholars all over the world. Adopting finite element method, this article focused on the interaction between V-type disk cutters and the intact rock to carry out microscopic parameter analysis methods: first, the stress model of rock breaking was established through V-type disk cutter motion trajectory analysis; second, based on the incremental theorem of the elastic–plastic theory, the strain model of the relative changes of rock displacement during breaking process was created. According to the principle of admissible work by energy method of the elastic–plastic theory to analyze energy transfer rules in the process of breaking rock, rock-breaking force of the V-type disk cutter could be regarded as the external force in the rock system. Finally, by taking the rock system as the reference object, the total potential energy equivalent model of rock system was derived to obtain the forces of the three directions acting on V-type disk cutter during the rock-breaking process. This derived model, which has been proved to be effective and scientific through comparisons with some original force models and by comparative analysis with experimental data, also initiates a new research strategy taking the view of the micro elastic–plastic theory to study the rock-breaking mechanism.

Motion trajectory analysis for evaluating the performance of functional upper extremity tasks in daily living: a pilot study.

Since 1998, tele-rehabilitation has been extensively studied for its potential capacity of saving time and cost for both therapists and patients. However, one gap hindering the deployment of tele-rehabilitation service is the approach to evaluate the outcome after tele-rehabilitation exercises without the presence of professional clinicians. In this paper, we propose an approach to model jerky and jerky-free movement trajectories with hidden Markov models (HMMs). The HMMs are then utilised to identify the jerky characteristics in a motion trajectory, thereby providing the number and amplitude of jerky movements in the specific length of the trajectory. Eventually, the ability of performing functional upper extremity tasks can be evaluated by classifying the motion trajectory into one of the pre-defined ability levels by looking at the number and amplitude of jerky movements. The simulation experiment confirmed that the proposed method is able to correctly classify motion trajectories into various ability levels to a high degree.

Group Activity Recognition with Group Interaction Zone Based on Relative Distance Between Human Objects

In this paper, we address the problem of recognizing group activities of human objects based on their motion trajectory analysis. In order to resolve the complexity and ambiguity problems caused by a large number of human objects, we propose a Group Interaction Zone (GIZ) to detect meaningful groups in a scene to effectively handle noisy information. Two novel features, Group Interaction Energy (GIE) feature and Attraction and Repulsion Features, are proposed to better describe group activities within a GIZ. We demonstrate the performance of our method in two ways by (i) comparing the performance of the proposed method with the previous methods and (ii) analyzing the influence of the proposed features and GIZ-based meaningful group detection on group activity recognition using public datasets.

On Integral Invariants for Effective 3-D Motion Trajectory Matching and Recognition.

Motion trajectories tracked from the motions of human, robots, and moving objects can provide an important clue for motion analysis, classification, and recognition. This paper defines some new integral invariants for a 3-D motion trajectory. Based on two typical kernel functions, we design two integral invariants, the distance and area integral invariants. The area integral invariants are estimated based on the blurred segment of noisy discrete curve to avoid the computation of high-order derivatives. Such integral invariants for a motion trajectory enjoy some desirable properties, such as computational locality, uniqueness of representation, and noise insensitivity. Moreover, our formulation allows the analysis of motion trajectories at a range of scales by varying the scale of kernel function. The features of motion trajectories can thus be perceived at multiscale levels in a coarse-to-fine manner. Finally, we define a distance function to measure the trajectory similarity to find similar trajectories. Through the experiments, we examine the robustness and effectiveness of the proposed integral invariants and find that they can capture the motion cues in trajectory matching and sign recognition satisfactorily.

A novel PSO algorithm based on an incremental-PID-controlled search strategy

Many variants of Particle Swarm Optimization (PSO) algorithm have been proposed in literature in the past two decades. The two research major topics, namely particle movement trajectory analysis and parameter selection, have also been intensively explored. Focused on the two issues, this paper transforms the velocity updating strategy in PSO algorithm to an incremental PID controller and thus develops a new incremental PID controlled search strategy. To endow this new PID-controlled deterministic search strategy with a stochastic nature, a mutation operation is applied on the particles and their exemplars. Based on such learning concepts, a novel incremental PID-controlled PSO, called IPID-PSO in short, algorithm is proposed. The proposed IPID-PSO algorithm is applied to eight benchmark problems of function optimization widely considered in literature. Compare with other two PSO variants, the IPID-PSO algorithm outperforms them on most of the eight functions. This superiority shows the usefulness of the proposed search strategy. Finally, the IPID-PSO is employed to estimate the parameters of the Jiles---Atherton (J---A) model, which is usually adopted to describe the hysteresis loop of magnetic materials. The results demonstrate that the proposed IPID-PSO is also effective for the J---A model parameter estimation. Therefore it can be concluded that the IPID-PSO algorithm provides a promising and satisfactory solution to real-world applications.