Proposed Motion Model Research Articles

Dynamic Multi-Target Self-Organization Hunting Control of Multi-Agent Systems

In this paper, we present a novel coordinated method tailored to address the dynamic multi-target hunting control problem in multi-agent systems, offering significant practical value. Our approach encompasses several key components: initially, we introduce a task allocation model that integrates a fuzzy inference system with a particle swarm optimization algorithm. This hybrid model efficiently allocates hunting tasks for scattered evading targets, effectively transforming the dynamic multi-target hunting problem into multiple dynamic single-target-hunting problems. This transformation enhances the speed and efficacy of task allocation. Subsequently, we propose an attraction/repulsive model grounded in potential field theory. This model facilitates the coordinated hunting of each target by organizing agents into subgroups. Relying solely on relative position and velocity information between agents and targets, our model simplifies computation, while maintaining effectiveness. Furthermore, the coordination of hunting activities for each target is achieved through a series of agent subgroups, guided by our proposed motion model. This systematic approach ensures a cohesive and efficient hunting strategy. Finally, we validate the effectiveness and feasibility of our proposed method through simulation results. These results provide empirical evidence of the method’s efficacy and potential applicability in real-world scenarios.

Target tracking and detection based on YOLOv5 algorithm

The YOLOv5 algorithm has gained popularity in recent years as an effective solution for real-time object detection in images and videos. This paper explores its potential for solving the problem of target tracking detection by proposing a modified YOLOv5 architecture that integrates object detection and tracking capabilities.The proposed YOLOv5-based tracking system includes three major components: object detection, object tracking, and object association. The object detection component uses a YOLOv5 model to detect and localize the target object in each frame of the video. The object tracking component then tracks the target object across frames using a Kalman filter and a Hungarian algorithm for data association. Finally, the object association component uses a motion model to handle occlusions and re-identifies the target object when it reappears in the field of view.The performance of the proposed YOLOv5-based tracking system is evaluated on several benchmark datasets, and its results are compared to state-of-the-art tracking algorithms. The experimental results show that the system achieves competitive tracking accuracy and real-time processing speed. Additionally, the effectiveness of the proposed motion model for handling occlusions and re-identification of the target object is demonstrated. In conclusion, the YOLOv5 algorithm has promising potential for target tracking detection in real-world scenarios, and it could have various applications in surveillance, robotics, and autonomous driving.

A Maneuvering Model for an Underwater Vehicle Near a Free Surface—Part II: Incorporation of the Free-Surface Memory

Using energy-based modeling techniques, we propose a nonlinear, time-dependent, parametric motion model for an underwater vehicle maneuvering near an otherwise undisturbed free surface. By augmenting the system Lagrangian used to derive Kirchhoff's equations for a rigid body moving through an unbounded fluid, we directly incorporate the free surface into the derivation of the equations of motion. This is done using a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">free-surface Lagrangian</i> , which accounts for the instantaneous energy stored within the free surface due to an impulsive vehicle motion as well as fluid memory effects. The system Lagrangian then enables us to derive the six-degree-of-freedom nonlinear equations of motion using the Euler–Lagrange equations. The model structure is similar to standard maneuvering models for surface ships, although additional complexities are present since the hydrodynamic parameters are shown to depend on the vessel position and orientation relative to the free surface. For the proposed model, the vessel motion is unrestricted. This is in contrast to traditional seakeeping models, which use convolution integrals to incorporate memory effects for a vessel, which experiences only small perturbations from steady, forward motion. The proposed motion model is amenable to real-time simulation, design performance analysis, and nonlinear control design. Other important hydrodynamic effects due to viscous flow, for example, may then be incorporated into a robust, nonlinear, closed-loop control system as lumped parameter effects or model uncertainties.

The application of body symbols in contemporary art from the perspective of Da Vinci’s theory

Abstract Motion recognition methods can distinguish body symbols and play an important role in real-time safety monitoring of pedestrians. In order to solve the problem of lack of data for deep learning-based action recognition models, a human motion synthesis method with hidden state initialization is proposed. Commonly used human motion synthesis methods utilize Recurrent Neural Network (RNN) to automatically generate subsequent motion sequences by taking several frames of motion data as input. In previous work, the initial hidden state of the RNN is usually set to zero or randomly initialized hidden state, resulting in a jump between the end frame of motion input and the first frame of motion synthesis, which affects the quality of the generated motion. To solve this problem, a method for estimating the initial hidden state estimation is proposed, which takes the initial hidden state as the independent variable, uses the objective function of the neural network as the optimization objective, and uses the gradient descent method to optimize the solution to obtain a suitable initial hidden state. The proposed motion model with initial hidden state estimation reduces the prediction error in the first frame by 63.51% and 6.90%, respectively, and the total error in 10 frames by 50.00% and the total errors of 10 frames were reduced by 50.00% and 4.89%, respectively. The experimental results show that the proposed motion model with initial hidden state estimation has better motion synthesis quality and motion prediction accuracy than the method without initial hidden state estimation; the proposed method improves the quality of motion synthesis by accurately estimating the first frame hidden state of the RNN human motion model, which can provide reliable data support for motion recognition models in real-time security monitoring.

Study on the effect of curvature radius sudden change on mechanism characteristics for the constant-breadth two circular-arc cam mechanism with an inclined flat-faced follower

A two circular-arc cam mechanism is a special kind of constant-breadth cam. At the junction point of each cam contour, a mutation of the curvature radius may be produced, which affects the motion performance of the mechanism, especially its jerk performance at high speed. Based on a proposed motion model, the follower movements of the constant-breadth two circular-arc cam mechanism with an inclined flat-faced follower are analyzed. Bezier Curve is proposed to fit the driving law of the cam mechanism, while variable speed law is adopted to drive the cam mechanism motion, thus reducing motion characteristic value (AV)max (i.e., the maximum value of the velocity multiplied by acceleration for the follower’s motion law of the cam mechanism at the same motion time point) and the jerk of the follower. In this paper, the establishment of the optimization objective functions and constraint conditions, and the control node selections of the cam drive function are researched. The optimization results are obtained by using the primary objective method. The results of a test case calculation and simulation show that, the optimized drive function, according to the variable motor speed, can significantly reduce the value of (AV)max of the follower, while the jerks of the follower system are also reduced considerably. More precisely, the (AV)max value is reduced by 11.63% and the jerks are reduced on average by 15.35%, at the three jerk positions. The proposed methods provide a new approach to improving the kinematic performance of similar cam mechanisms.

Modeling Pedestrian Motion in Crowded Scenes Based on the Shortest Path Principle

In the computer vision field, understanding human dynamics is not only a great challenge but also very meaningful work, which plays an indispensable role in public safety. Despite the complexity of human dynamics, physicists have found that pedestrian motion in a crowd is governed by some internal rules, which can be formulated as a motion model, and an effective model is of great importance for understanding and reconstructing human dynamics in various scenes. In this paper, we revisit the related research in social psychology and propose a two-part motion model based on the shortest path principle. One part of the model seeks the origin and destination of a pedestrian, and the other part generates the movement path of the pedestrian. With the proposed motion model, we simulated the movement behavior of pedestrians and classified them into various patterns. We next reconstructed the crowd motions in a real-world scene. In addition, to evaluate the effectiveness of the model in crowd motion simulations, we created a new indicator to quantitatively measure the correlation between two groups of crowd motion trajectories. The experimental results show that our motion model outperformed the state-of-the-art model in the above applications.

Nearly constant acceleration model for state estimation in the range‐Doppler plane

The problem of motion modelling in the range-Doppler (R-D) plane as well as range and Doppler estimation for the Cartesian nearly constant acceleration motion, which is a common manoeuvering motion, is investigated. The temporal evolution equation is derived based on the state vector consisting of target range, Doppler and derivatives of the product of range and range rate versus time. In this way, the measurement equation of range and Doppler measurements can be maintained in a desirable linear-Gaussian structure. Based on the non-linear state equation and the linear measurement equation, the unscented Kalman filter is adopted to tackle the non-linear filtering problem. The corresponding filter initialisation method is developed based on the two-point differencing method. Explicit expressions of the initial state estimates and the initial covariance matrix are presented in analytic forms where the correlation among the state components is handled properly. The posterior Cramer–Rao lower bound (PCRLB) is provided for state estimation in the R-D plane. Comprehensive comparisons of the proposed method against the existing R-D state estimation methods using approximate models, Cartesian state estimator and PCRLB are carried out in simulations to demonstrate the validity and correctness of the proposed motion model and estimation method.

Video anomaly detection and localization based on appearance and motion models

In this paper, we present an approach to detect and localize anomalies in the surveillance videos. Precise detection, modeling the normality in a context and dealing with false alarms are the major challenges to cope with while performing detection and localization of anomalies. We propose appearance and motion models to detect an anomalous event at the frame level in a video. In the anomalous frames, we localize the anomaly using appearance and connected component analysis cues. The proposed appearance model utilizes the mask-rcnn for scene semantic analysis. The proposed motion model constructs frame descriptors based on the histograms of the intensity difference maps of the consecutive video frames. A one class support vector machine (OCSVM) is used to detect motion based anomalous event. In order to eliminate the false alarms of anomaly detection and localization emerging due to camera jitter and object movements in unlikely motion regions of a video frame, we exploit the connected component analysis. Experiments on the Avenue and UMN datasets reveal that the proposed approach achieves high accuracy and outperforms the existing methods.

A resistance force model for spherical projectiles penetrating ballistic gelatin based on cavity expansion theory

To investigate the penetration mechanism of spherical projectiles into soft tissues, ballistic gelatin was used as tissue substitute in ballistic tests. A theoretical motion model was established based on the cavity expansion theory. We first presented a quasi-static cylindrical cavity expansion model for the radial stress at the cavity wall of a cracked-hyperelastic material. The pressure on the cavity surface, PS, was also defined as the energy required to open a unit volume in the medium quasi-statically. Based on this interpretation, we proposed an approximate expression for the dynamic pressure, P, acting on the surface of the cavity by analyzing the energy transformation and conservation. Then, based on the analysis and solutions of the cylindrical cavity expansion model, we obtained a resistance force model for spherical projectiles, which consisted of an inertial term and a rate-dependent strength term. Subsequently, ballistic tests, in which gelatin blocks were penetrated by spherical projectiles of different materials and sizes, were analyzed, and the parameters in the resistance model were identified using the test results obtained from the 3 mm steel projectile. Further, the ability of the motion model to describe the motion of spherical projectiles penetrating ballistic gelatin was verified by comparing the calculated and measured results from projectiles of different materials and sizes. The proposed motion model based on the cavity expansion theory can therefore provide a basis for understanding the interaction of small arms ammunition and soft tissues.

AN INTEGERATED NAVIGATION SYSTEM FOR AUTONOMOUS MOBILE ROBOT IN DYNAMIC ENVIROMENTS

To enable an autonomous mobile robot to navigate safely in a dy- namic environment, the mobile robot must address four typical functional blocks of the navigation system including perception, localization, motion planning, and motor control. In this study, we present an integrated navigation system for the autonomous mobile robot in the dynamic environment by incorporating the techniques proposed in our previous studies, including object detection and tracking system, localization system and motion planning system, into a completed navigation system. In addition, we propose an extended timed elastic band (ETEB) technique for online trajectory planning, which allows the mobile robot to proactively avoid obstacles in the surrounding environment. We validate the effectiveness of the proposed model through a series of experiments in both simulated and real-world environments. The experimental results show that our proposed motion model is capable of driving the mobile robots to proactively avoid dynamic obstacles, providing safe navigation for the robots.

Coupled Motion Characteristics of Offshore Wind Turbines during the Integrated Transportation Process

The offshore wind turbine (OWT) supported by bucket foundations can be installed in the integrated transportation process by a dedicated vessel. During the integrated transportation process, the wind turbine is considered as a coupling system with the transport ship, which is easily influenced by waves and storms. In view of the motion response and influential factors, the heave and rock stiffness of the entire floating system was proposed, and then the analytical dynamic motion model of the coupling system was established based on the movement mechanism of the traditional floating body in the wave in this paper. Subsequently, the rationality of the proposed motion model was verified based on the field observation data, with the maximum deviation of the motion responses less than 14%. Further, the influence on the heave and pitch motion of the coupling system considering different factors (vessel speed, wave height, wind speed and wave angle) and the factor sensitivity were discussed by the novel analytical model. It is explained that the heave and pitch motion responses rise with the increase of the wave height and wave angle. Simultaneously, the responses decrease as the vessel speed increases considering sailing along the waves. On the contrary, the responses show an obvious increasing trend with the increase of vessel speed in the case of the top wave sailing. In addition, it is also illustrated that the wave height has the greatest influence on the heave and pitch motion responses, followed by the vessel speed. The wave angle has the lowest sensitivity when the heave and pitch motion are far away from its harmonic resonance region.

Spherical Coordinates Transform-Based Motion Model for Panoramic Video Coding

Panoramic video is produced and displayed as if it is supported on sphere, but it is usually mapped to two-dimensional (2D) plane for compression purpose. The mapping from sphere to 2D plane inevitably causes deformation of video content, which shall be taken into account in panoramic video coding. In this paper, we propose a new motion model based on spherical coordinates transform to explicitly address the deformation problem. Different from the traditional 2D translational motion model, our model assumes a 3D translational motion, which is characterized by a 2D motion vector and a relative depth parameter. Based on spherical coordinates transform, we can deduce the motion compensation and motion estimation algorithms for our proposed motion model. We then integrate the algorithms into the joint exploration model (JEM) scheme for panoramic video coding, and perform experiments on some typical equirectangular projection format video sequences. Experimental results show that our proposed method leads to up to 10.7% and on average 2.6% BD-rate reduction compared to the JEM anchor on our test sequences, with no increase of decoding time.

Energy-Efficient Swarm Behavior for Indoor UAV Ad-Hoc Network Deployment

Building an ad-hoc network in emergency situations can be crucial as a primary tool or even when used prior to subsequent operations. The use of mini and micro Unmanned Aerial Vehicles (UAVs) is increasing because of the wide range of possibilities they offer. Moreover, they have been proven to bring sustainability to many applications, such as agriculture, deforestation and wildlife conservation, among others. Therefore, creating a UAV network for an unknown environment is an important task and an active research field. In this article, a mobility model for the creation of ad-hoc networks using UAVs will be presented. This model will be based on pheromones for robust navigation. We will focus mainly on developing energy-efficient behavior, which is essential for this type of vehicle. Although there are in the literature several models of mobility for ad-hoc network creation, we find that either they are not adapted to the specific energy requirements of UAVs or the proposed motion models are unrealistic or not sufficiently robust for final implantation. We will present and analyze the operation of a distributed swarm behavior able to create an ad-hoc network. Then, an analytical model of the swarm energy consumption will be proposed. This model will provide a mechanism to effectively predict the energy consumption needed for the deployment of the network prior to its implementation. Determining the use of the mobility behavior is a requirement to establish and maintain a communication channel for the required time. Finally, this analytical model will be experimentally validated and compared to the Random Waypoint (RWP) mobility strategy.

GSI: efficient spatio-temporal template for human gait recognition

Human gait recognition is a challenging task in computer vision community. In order to represent the gait, the most common feature is a gait template. Many efficient templates have been developed recently, however, the effectiveness of the proposed motion models is still under investigation. A novel template feature, named gait salient image (GSI) is introduced in this paper. The main contribution of the proposed GSI is encoding the motion energy of gait into a single template. This idea is being conceptualised by applying appropriate spatio-temporal filter for extracting motion features and averaging it over a gait period. To show how GSI-based feature is being efficient, the proposed template is classified using PCA+LDA. Extensive experiments on popular gait databases reveal an improvement over the available methods in terms of efficiency and accuracy. The value of recognition rate is 58.44% for Rank1 and 76.60% for Rank5 based on the USF database.

Modeling of natural sit-to-stand movement based on minimum jerk criterion for natural-like assistance and rehabilitation

Designing a sit-to-stand (STS) assistive system that mimics the normal transfer is important for improving the quality of life for elderly and mobility impaired people while reducing the burden on the caregivers. This paper presents a robotic-based STS assisting system that can provide assistance at the shoulder and the buttock. The minimum jerk criterion is used to model the natural STS motion. Anthropometry and characteristics of the natural STS motion are used to increase the simplicity and applicability of the STS motion model. This model can generate the shoulder and hip trajectories during STS. This enables the system to provide assistance either at the upper trunk or at the upper trunk and the hip simultaneously without inducing abnormal motion kinematics. The assisting system is used to assist subjects with different heights using the trajectories generated by the proposed motion model. In addition, the proposed trajectory is compared to the one that is resulted from a commercial lifter. The results show that the proposed method can accurately replicate the natural STS motion and results in a lower interaction force. Moreover, the subjects are more satisfied when they are assisted using the proposed method as indicated by the results of the post-experiment questionnaire.

Video Stabilization for Strict Real-Time Applications

Offline or deferred solutions are frequently employed for high quality and reliable results in current video stabilization. However, neither of these solutions can be used for strict real-time applications. In this paper, we propose a practical and robust algorithm for real-time video stabilization. To achieve this, a novel and efficient motion model based on inter-frame homography estimation is proposed to represent the video motion. An important feature of the proposed motion model is that it updates at each frame input to reduce the accumulation errors caused by parallax or scene changes. We also propose a novel Kalman filter for the motion smoothing and a unique mosaic algorithm for the video completion. The proposed Kalman filter and mosaic algorithm enable the development of a practical real-time video stabilizer that not only produces steady video but also retains the full resolution of the original video. We verify the proposed algorithm through a broad range of video sequences that demonstrate that the proposed algorithm is computationally efficient while being able to robustly stabilize videos with various challenges.

Human-inspired motion model of upper-limb with fast response and learning ability – a promising direction for robot system and control

Purpose – Human movement system is a Multi-DOF, redundant, complex and nonlinear system formed by coordinating combination of neural system, bones, muscles and joints, which is robust and has fast response and learning ability. Imitating human movement system can improve robustness, fast response and learning ability of the robots. Design/methodology/approach – In this paper, we propose a new motion model based on the human motion pathway, especially the information propagation mechanism between the cerebellum and spinal cord. Findings – The proposed motion model proves to have fast response and learning ability through experiments, which matches the features of human motion. Originality/value – The proposed model in this paper introduces the habitual theory in kinesiology and neuroscience into robot control, and improves robustness, fast response and learning ability of the robots. This paper proves that introduction of neuroscience has an important guiding significance for precise and adaptive robot control, such as assembly automation.

A Precise State Transition Model for Aircraft Navigation

This article considers the problem of accurately modeling the kinematic state transition of an Unmanned Aerial Vehicle (UAV). The full 3D range of motion is accurately captured using compact equations for position update derived in this work. This derivation makes use of the independence of the rotation and translation components of a 3D rigid motion. The proposed motion model is transparent to the sensors used in the system; it is particularly useful in GPS-denied environments and can contribute to different aspects of robust navigation, such as accurate state estimation, sensor fault tolerance and sensor bias estimation. Experimental results comparing the performance of the proposed kinematic model with those typically used demonstrate its superiority.

Combining Multiple Dynamic Models and Deep Learning Architectures for Tracking the Left Ventricle Endocardium in Ultrasound Data

We present a new statistical pattern recognition approach for the problem of left ventricle endocardium tracking in ultrasound data. The problem is formulated as a sequential importance resampling algorithm such that the expected segmentation of the current time step is estimated based on the appearance, shape, and motion models that take into account all previous and current images and previous segmentation contours produced by the method. The new appearance and shape models decouple the affine and nonrigid segmentations of the left ventricle to reduce the running time complexity. The proposed motion model combines the systole and diastole motion patterns and an observation distribution built by a deep neural network. The functionality of our approach is evaluated using a dataset of diseased cases containing 16 sequences and another dataset of normal cases comprised of four sequences, where both sets present long axis views of the left ventricle. Using a training set comprised of diseased and healthy cases, we show that our approach produces more accurate results than current state-of-the-art endocardium tracking methods in two test sequences from healthy subjects. Using three test sequences containing different types of cardiopathies, we show that our method correlates well with interuser statistics produced by four cardiologists.

Modeling respiratory motion for reducing motion artifacts in 4D CT images

Four-dimensional computed tomography (4D CT) images have been recently adopted in radiation treatment planning for thoracic and abdominal cancers to explicitly define respiratory motion and anatomy deformation. However, significant image distortions (artifacts) exist in 4D CT images that may affect accurate tumor delineation and the shape representation of normal anatomy. In this study, the authors present a patient-specific respiratory motion model, based on principal component analysis (PCA) of motion vectors obtained from deformable image registration, with the main goal of reducing image artifacts caused by irregular motion during 4D CT acquisition. For a 4D CT image set of a specific patient, the authors calculated displacement vector fields relative to a reference phase, using an in-house deformable image registration method. The authors then used PCA to decompose each of the displacement vector fields into linear combinations of principal motion bases. The authors have demonstrated that the regular respiratory motion of a patient can be accurately represented by a subspace spanned by three principal motion bases and their projections. These projections were parameterized using a spline model to allow the reconstruction of the displacement vector fields at any given phase in a respiratory cycle. Finally, the displacement vector fields were used to deform the reference CT image to synthesize CT images at the selected phase with much reduced image artifacts. The authors evaluated the performance of the in-house deformable image registration method using benchmark datasets consisting of ten 4D CT sets annotated with 300 landmark pairs that were approved by physicians. The initial large discrepancies across the landmark pairs were significantly reduced after deformable registration, and the accuracy was similar to or better than that reported by state-of-the-art methods. The proposed motion model was quantitatively validated on 4D CT images of a phantom and a lung cancer patient by comparing the synthesized images and the original images at different phases. The synthesized images matched well with the original images. The motion model was used to reduce irregular motion artifacts in the 4D CT images of three lung cancer patients. Visual assessment indicated that the proposed approach could reduce severe image artifacts. The shape distortions around the diaphragm and tumor regions were mitigated in the synthesized 4D CT images. The authors have derived a mathematical model to represent the regular respiratory motion from a patient-specific 4D CT set and have demonstrated its application in reducing irregular motion artifacts in 4D CT images. The authors' approach can mitigate shape distortions of anatomy caused by irregular breathing motion during 4D CT acquisition.