Moving Target Tracking Research Articles

Application of Video Abnormal Behavior Detection Algorithm in Evaluation of Track and Field Teaching and Training Effect

With the development of track and field, people pay more and more attention to the quality of classroom teaching of track and field technology, and the evaluation of teaching quality plays a key role in it. In today's educational reform, teaching evaluation plays an important role as an important method to test teachers' teaching and students' learning. With the rapid development of machine learning, especially deep learning, image-based individual abnormal behavior detection technology is becoming more and more mature, but there are still many difficulties to be solved in video-based group abnormal behavior detection technology. Therefore, it is necessary to study the detection algorithm. Based on machine vision theory, image processing theory and video analysis technology, this paper studies three key technologies involved in human abnormal behavior detection in video: moving target detection, moving target tracking and abnormal behavior detection.

Visual-Based Moving Target Tracking With Solar-Powered Fixed-Wing UAV: A New Learning-Based Approach

Visual-Based Moving Target Tracking With Solar-Powered Fixed-Wing UAV: A New Learning-Based Approach

Parallel dual adaptive genetic algorithm: A method for satellite constellation task assignment in time-sensitive target tracking

The evolution of satellite surveillance technology, bolstered by advanced onboard intelligent systems and enhanced attitude maneuver capabilities, has thrust mission scheduling and execution into the spotlight as a prominent and dynamic research field in recent years. As the demand intensifies for mission scheduling and execution to transition from static ground targets to time-sensitive moving targets, conventional scheduling methods often fall short of delivering satisfactory results for continuously tracking these dynamic targets with constellation. The paper introduces a rapid yet efficacious satellite constellation task assignment method, termed the Parallel Dual Adaptive Genetic Algorithm (PDA-GA), for the task assignment of multiple moving target tracking. Specifically, the dual adaptive mechanism isolates the genetic algorithm’s sensitivity to parameters, while the parallel mechanism increases the evolutionary process’s computation speed by deploying complex computations to the GPU. Based on the meticulous analysis of the relevant factors that need to be considered in real tracking scenarios, the proposed PDA-GA can improve the search quality and efficiency of the task assignment solution. We conduct an extensive array of contrast and ablation experiments to showcase the performance and efficiency of PDA-GA in conjunction with autonomous attitude control algorithms across five simulated tracking scenarios. Furthermore, to enable high-fidelity simulation of tracking scenarios, we introduce the Constellation Target Tracking Environment (CTTE), which is equipped with a physics engine and algorithms for multi-satellite task assignment and single-satellite attitude control. This endeavor lays a foundation for future research endeavors focused on autonomous tracking of multiple time-sensitive moving targets within large-scale constellation.

Development of Wi-Fi based Moving Target Tracking System for Precise Shooting

In modern times where analysis of foot traffic is essential for effective resources management and security, moving target systems that use Wi-Fi-based movement counter offers an innovation solution. This paper summarizes the fundamental idea, the methodology as well as the potential uses of the system. The proposed system makes use of the widespread characteristic of Wi-Fi networks to detect and track the movement of moving targets within a given area. With a thorough analysis of Wi-Fi signals generated by tablets, smartphones or any other wireless-enabled device carried by people, the proposed system is capable of accurately counting and recording the movements of individuals in real-time. The system operates passively by eliminating the requirement for sensors or manually counting. Furthermore, it captures live data, which allows rapid making of decisions regarding security, crowd management and resource allocation. Potential possibilities for applications of the wireless moving target counter are diverse. For retail environments they can help enhance the store's layout and personnel according to peak times for traffic as well as popular pathways. Moving target counters that use Wi-Fi provides a high-end yet easy option for precise and instant pedestrian analysis. The potential for it to transform the management of crowds and improve security across a variety of settings is a powerful device for today's environments.

An ultrawide field-of-view pinhole compound eye using hemispherical nanowire array for robot vision.

Garnering inspiration from biological compound eyes, artificial vision systems boasting a vivid range of diverse visual functional traits have come to the fore recently. However, most of these artificial systems rely on transformable electronics, which suffer from the complexity and constrained geometry of global deformation, as well as potential mismatches between optical and detector units. Here, we present a unique pinhole compound eye that combines a three-dimensionally printed honeycomb optical structure with a hemispherical, all-solid-state, high-density perovskite nanowire photodetector array. The lens-free pinhole structure can be designed and fabricated with an arbitrary layout to match the underlying image sensor. Optical simulations and imaging results matched well with each other and substantiated the key characteristics and capabilities of our system, which include an ultrawide field of view, accurate target positioning, and motion tracking function. We further demonstrate the potential of our unique compound eye for advanced robotic vision by successfully completing a moving target tracking mission.

Real-time and Intelligent Moving Targets Tracking based on UAV Remote Sensing Video Camera and Brain-like Computing Chips

Abstract. Moving target tracking technology based on Unmanned Aerial Vehicles (UAV) is widely used in many fields such as automatic inspection and emergency response. The existing moving target tracking methods usually have the problems of large computation and low tracking efficiency. Limited by the computing power of the UAV platform, real-time tracking and analysis of multiple targets based on the video data collected by UAV platform is a difficult task. In this paper, we proposed a novel Target Specific Filtering Tracking with Memory (TSFMTrack) method designed for UAV-based real-time tracking tasks, which involves a Tracklet Filtering Module (TFM) for capturing object appearance features and a Tracklet Matching Module (TMM) for bounding box association in each frame. By experimental comparison with other State-Of-The-Art (SOTA) methods on popular MOT and UAV tracking datasets, the TSFMTrack have shown obvious advantages in accuracy, computational efficiency and reliability. Furthermore, we deployed the TSFMTrack on the brain-inspired chip Lynchip KA200, the experimental results have shown that the TSFMTrack is effective on edge computational platform and suitable for UAV real-time tracking tasks.

An Attitude Adaptive Integral Sliding Mode Control Algorithm with Disturbance Observer for Microsatellites to Track High-Speed Moving Targets

Gaze tracking of high-speed moving targets is a novel application mode for low Earth orbit microsatellites. In this mode, small satellites are equipped with high-resolution, narrow-field-of-view video cameras for stable gaze-tracking imaging of high-speed moving targets. This paper proposes a high-precision attitude adaptive integral sliding mode control method with a feedforward compensation disturbance observer to enhance the capability of a microsatellite attitude control system for gaze tracking of high-speed moving targets. Specifically, first, we present the attitude control system model for microsatellites and the calculation method for the desired attitude of target tracking based on image feedback. Then, an adaptive integral sliding mode attitude control algorithm with a feedforward compensation disturbance observer, which meets the requirements of high-precision tracking control, is designed. The developed algorithm utilizes the disturbance observer to observe the friction torque of the flywheel and compensates for it through feedforward control. It also employs the adaptive integral sliding mode control algorithm to reduce the impact of uncertain disturbances, decrease the steady-state error of the system, and enhance attitude control precision. Simulation experiments demonstrated that the designed disturbance observer can successfully observe the frictional disturbance torque of the flywheel. The attitude Euler angle control precision for high-speed moving target tracking reached 0.03°, and the angular velocity control precision reached 0.005°/s, validating the effectiveness of the proposed approach.

Concrete structure assembly technology based on 3D intelligent image analysis

AbstractAt present, there is no standard practice for temporary connection of component installation. How to make temporary connections to components more efficient and accurate is the key to the construction of cast‐in‐place connection parts in concrete prefabricated buildings. In order to improve the assembly technology of concrete structures, this paper combines three‐dimensional intelligent image analysis technology for simulation, analyzes and compares several common electronic image stabilization algorithms, discusses the video image stabilization technology based on gray projection method in detail, and gives experimental results. Moreover, this paper analyzes and compares common moving target tracking algorithms, such as feature‐based tracking, region matching‐based tracking, dynamic contour‐based tracking, and 3D model‐based tracking. In addition, this paper studies the target tracking algorithm based on the Camshift algorithm, and constructs the assembly model of the intelligent concrete structure with the support of the algorithm. Through experimental verification, it is known that the performance distribution of the concrete structure assembly model based on 3D intelligent image analysis in experimental evaluation is between [81, 89], the experimental study shows that the concrete structure assembly model based on 3D intelligent image analysis can effectively improve the assembly effect of concrete structure.

Efficient 2-D MUSIC algorithm for super-resolution moving target tracking based on an FMCW radar

Frequency modulated continuous wave (FMCW) radar is an advantageous sensor scheme for target estimation and environmental perception. However, existing algorithms based on discrete Fourier transform (DFT), multiple signal classification (MUSIC) and compressed sensing, etc., cannot achieve both low complexity and high resolution simultaneously. This paper proposes an efficient 2-D MUSIC algorithm for super-resolution target estimation/tracking based on FMCW radar. Firstly, we enhance the efficiency of 2-D MUSIC azimuth-range spectrum estimation by incorporating 2-D DFT and multi-level resolution searching strategy. Secondly, we apply the gradient descent method to tightly integrate the spatial continuity of object motion into spectrum estimation when processing multi-epoch radar data, which improves the efficiency of continuous target tracking. These two approaches have improved the algorithm efficiency by nearly 2–4 orders of magnitude without losing accuracy and resolution. Simulation experiments are conducted to validate the effectiveness of the algorithm in both single-epoch estimation and multi-epoch tracking scenarios.

Adaptive Image-Based Moving-Target Tracking Control of Wheeled Mobile Robots With Visibility Maintenance and Obstacle Avoidance

Adaptive Image-Based Moving-Target Tracking Control of Wheeled Mobile Robots With Visibility Maintenance and Obstacle Avoidance

Target tracking using video surveillance for enabling machine vision services at the edge of marine transportation systems based on microwave remote sensing

AbstractAutomatic target tracking in emerging remote sensing video-generating tools based on microwave imaging technology and radars has been investigated in this paper. A moving target tracking system is proposed to be low complexity and fast for implementation through edge nodes in a mini-satellite or drone network enabling machine intelligence into large-scale vision systems, in particular, for marine transportation systems. The system uses a group of image processing tools for video pre-processing, and Kalman filtering to do the main task. For testing the system performance, two measures of accuracy and false alarms probability are computed for real vision data. Two types of scenes are analyzed including the scene with single target, and the scene with multiple targets that is more complicated for automatic target detection and tracking systems. The proposed system has achieved a high performance in our tests.

Artificial Potential Field Based Trajectory Tracking for Quadcopter UAV Moving Targets.

The trajectory or moving-target tracking feature is desirable, because it can be used in various applications where the usefulness of UAVs is already proven. Tracking moving targets can also be applied in scenarios of cooperation between mobile ground-based and flying robots, where mobile ground-based robots could play the role of mobile landing pads. This article presents a novel proposition of an approach to position-tracking problems utilizing artificial potential fields (APF) for quadcopter UAVs, which, in contrast to well-known APF-based path planning methods, is a dynamic problem and must be carried out online while keeping the tracking error as low as possible. Also, a new flight control is proposed, which uses roll, pitch, and yaw angle control based on the velocity vector. This method not only allows the UAV to track a point where the potential function reaches its minimum but also enables the alignment of the course and velocity to the direction and speed given by the velocity vector from the APF. Simulation results present the possibilities of applying the APF method to holonomic UAVs such as quadcopters and show that such UAVs controlled on the basis of an APF behave as non-holonomic UAVs during 90° turns. This allows them and the onboard camera to be oriented toward the tracked target. In simulations, the AR Drone 2.0 model of the Parrot quadcopter is used, which will make it possible to easily verify the method in real flights in future research.

Robust Cubature Kalman Filter for Moving-Target Tracking with Missing Measurements.

Handling the challenge of missing measurements in nonlinear systems is a difficult problem in various scientific and engineering fields. Missing measurements, which can arise from technical faults during observation, diffusion channel shrinking, or the loss of specific metrics, can bring many challenges when estimating the state of nonlinear systems. To tackle this issue, this paper proposes a technique that utilizes a robust cubature Kalman filter (RCKF) by integrating Huber's M-estimation theory with the standard conventional cubature Kalman filter (CKF). Although a CKF is often used for solving nonlinear filtering problems, its effectiveness might be limited due to a lack of knowledge regarding the nonlinear model of the state and noise-related statistical information. In contrast, the RCKF demonstrates an ability to mitigate performance degradation and discretization issues related to track curves by leveraging covariance matrix predictions for state estimation and output control amidst dynamic disruption errors-even when noise statistics deviate from prior assumptions. The performance of extended Kalman filters (EKFs), unscented Kalman filters (UKFs), CKFs, and RCKFs was compared and evaluated using two numerical examples involving the Univariate Non-stationary Growth Model (UNGM) and bearing-only tracking (BOT). The numerical experiments demonstrated that the RCKF outperformed the EKF, EnKF, and CKF in effectively handling anomaly errors. Specifically, in the UNGM example, the RCKF achieved a significantly lower ARMSE (4.83) and ANCI (3.27)-similar outcomes were observed in the BOT example.

Distributed Dynamic Task Allocation for Moving Target Tracking of Networked Mobile Robots Using k -WTA Network.

Tasks allocation plays a pivotal role in cooperative robotics. This study proposes a novel fully distributed task allocation method for target tracking, by which mobile robots only need to share state information with communication neighbors. The proposed method adopts a distributed k winners-take-all ( k -WTA) network to select the k mobile robots closest to the moving target to perform the target tracking task. In addition, an innovative robot control law is designed, incorporating speed feedback and nonlinear activation functions to achieve finite-time error convergence. Unlike previous approaches, our distributed task allocation method yields finite-time error convergence, does not rely on consensus filters, and eliminates the need for a central computing unit to get the k -WTA result during the control process. We demonstrate the effectiveness of the proposed method through theoretical analysis and simulations. Compared to traditional methods, our method leads to smaller total moving distances and speed norms, which underscores the significance of our method in enhancing the efficiency and performance of mobile robots in dynamic task allocation.

Domain-knowledge-aided airborne ground moving targets tracking

This paper investigates the problem of traffic surveillance using an unmanned aerial vehicle (UAV) and proposes a domain-knowledge-aided airborne ground moving target tracking algorithm. To improve the accuracy of multiple target tracking, the proposed algorithm incorporates domain knowledge into the joint probabilistic data association (JPDA) filter as state constraints. The domain knowledge considered in this paper includes both road information extracted from a given map and local traffic regulations. Conventional track update method is modified to enhance the capability of recognition of temporarily track loss. A variable structure multiple model (VS-MM) method is developed to assign the road segment to a given target. The main contribution of this paper is that we establish a comprehensive framework for target tracking with the aid of domain knowledge and analyze the effect of diverse constraints on target tracking performance, while the limitations involve only 2-D target behaviors are considered, and the sophisticated interactions between targets are neglected. The effectiveness of proposed algorithm is demonstrated through extensive numerical simulations.

Distributed time-varying optimization control protocol for multi-agent systems via finite-time consensus approach

This paper addresses a distributed time-varying optimization problem with inequality constraints based on multi-agent systems over switching communication graphs. To reduce the influence of time-varying inequality constraints, an exact penalty method and smoothing technique are employed. Then, a Hessian-based distributed control protocol is presented to seek the time-varying optimal solution of the distributed time-varying optimization problem by virtue of only local information and interaction. It is shown that all agents not only achieve finite-time consensus but also track the time-varying global optimal target eventually. Compared with the existing distributed optimization protocols, the proposed control protocol is suitable for more general distributed time-varying optimization problems and enjoys high-efficiency convergence. Finally, numerical examples and experiment on moving target tracking of Unmanned Aircraft Vehicle (UAV) are performed to illustrate the effectiveness of the proposed control protocol.

Moving Target Tracking Method Based on Improved Camshift

<p>Aiming at the problem that target occlusion and other disturbances in complex background will reduce the tracking accuracy of moving target, and even lead to tracking failure, this paper proposes a moving target tracking algorithm based on the improved Camshift algorithm. Firstly, Gaussian background is used to model the foreground image to improve the backprojection image, and then the interference of backprojection is removed to improve the tracking effect in complex background conditions. Secondly, Kalman filtering is utilized to predict the trajectory, which further improves the tracking accuracy of Camshift algorithm in occlusion condition. A lot of experiments are processed, and the results show that the proposed algorithm could effectively improve the tracking accuracy and meet the real-time requirements.</p> <p> </p>

Volumetric MRI with sparse sampling for MR-guided 3D motion tracking via sparse prior-augmented implicit neural representation learning.

Volumetric reconstruction of magnetic resonance imaging (MRI) from sparse samples is desirable for 3D motion tracking and promises to improve magnetic resonance (MR)-guided radiation treatment precision. Data-driven sparse MRI reconstruction, however, requires large-scale training datasets for prior learning, which is time-consuming and challenging to acquire in clinical settings. To investigate volumetric reconstruction of MRI from sparse samples of two orthogonal slices aided by sparse priors of two static 3D MRI through implicit neural representation (NeRP) learning, in support of 3D motion tracking during MR-guided radiotherapy. A multi-layer perceptron network was trained to parameterize the NeRP model of a patient-specific MRI dataset, where the network takes 4D data coordinates of voxel locations and motion states as inputs and outputs corresponding voxel intensities. By first training the network to learn the NeRP of two static 3D MRI with different breathing motion states, prior information of patient breathing motion was embedded into network weights through optimization. The prior information was then augmented from two motion states to 31 motion states by querying the optimized network at interpolated and extrapolated motion state coordinates. Starting from the prior-augmented NeRP model as an initialization point, we further trained the network to fit sparse samples of two orthogonal MRI slices and the final volumetric reconstruction was obtained by querying the trained network at 3D spatial locations. We evaluated the proposed method using 5-min volumetric MRI time series with 340ms temporal resolution for seven abdominal patients with hepatocellular carcinoma, acquired using golden-angle radial MRI sequence and reconstructed through retrospective sorting. Two volumetric MRI with inhale and exhale states respectively were selected from the first 30s of the time series for prior embedding and augmentation. The remaining 4.5-min time series was used for volumetric reconstruction evaluation, where we retrospectively subsampled each MRI to two orthogonal slices and compared model-reconstructed images to ground truth images in terms of image quality and the capability of supporting 3D target motion tracking. Across the seven patients evaluated, the peak signal-to-noise-ratio between model-reconstructed and ground truth MR images was 38.02±2.60dB and the structure similarity index measure was 0.98±0.01. Throughout the 4.5-min time period, gross tumor volume (GTV) motion estimated by deforming a reference state MRI to model-reconstructed and ground truth MRI showed good consistency. The 95-percentile Hausdorff distance between GTV contours was 2.41±0.77mm, which is less than the voxel dimension. The mean GTV centroid position difference between ground truth and model estimation was less than 1mm in all three orthogonal directions. A prior-augmented NeRP model has been developed to reconstruct volumetric MRI from sparse samples of orthogonal cine slices. Only one exhale and one inhale 3D MRI were needed to train the model to learn prior information of patient breathing motion for sparse image reconstruction. The proposed model has the potential of supporting 3D motion tracking during MR-guided radiotherapy for improved treatment precision and promises a major simplification of the workflow by eliminating the need for large-scale training datasets.

Real Time Volumetric MRI for MR-Guided 3D Motion Tracking via Sparse Prior-Augmented Neural Representation Learning

To reconstruct volumetric MRI from orthogonal cine acquisition aided by sparse priors of 2 static 3D MRI through implicit neural representation (NeRP) learning, with the goal of eliminating large-scale training datasets for data-driven sparse MRI reconstruction and supporting clinical workflow of real time 3D motion tracking during MR-guided radiotherapy. A multi-layer perceptron network was trained to learn the NeRP of a patient-specific MRI dataset, where the network takes 4D data coordinates of voxel locations and motion states as inputs and outputs corresponding voxel intensities. By first learning the NeRP of 2 static 3D MRI with different breathing motion states, prior knowledge of patient breathing motion was embedded into network weights through optimization. The prior knowledge was then augmented from 2 to 31 motion states by querying the optimized network at interpolated/extrapolated motion state coordinates. Starting from the prior-augmented network as an initialization point, the network was further trained using sparse samples of 2 orthogonal cine slices. The final volumetric reconstruction was obtained by querying the trained network at desired 3D spatial locations. We evaluated the proposed method using 5-minute volumetric MRI time series with 340 ms temporal resolution collected from 7 liver carcinoma patients. The time series was acquired using golden-angle radial MRI sequence and reconstructed through retrospective sorting. Two MRI with inhale and exhale states respectively were selected from the first 30 sec of the time series for prior embedding and augmentation. The remaining 4.5-min time series was used for volumetric reconstruction evaluation, where we retrospectively subsampled each MRI to 2 orthogonal slices and compared network-reconstructed images to ground truth images in terms of image quality and the capability of supporting 3D target motion tracking. Across the 7 patients evaluated, the peak signal to noise ratio between model reconstruction and ground truth was 54.66 ± 6.16 dB and the structural similarity index measure was 0.99 ± 0.01. Gross tumor volume (GTV) contours estimated by deforming a reference state MRI to model-reconstructed and ground truth MRI showed good consistency. The 95-percentile Hausdorff distance between GTV contours was 1.89 ± 1.13 mm, which is less than the voxel dimension. The mean GTV centroid position difference between ground truth and model estimation was less than 1 mm in all 3 orthogonal directions. Volumetric MRI from orthogonal cine acquisition with sparse priors is feasible by modeling prior knowledge through implicit neural representation learning. The model-reconstructed images showed sufficient accuracy in supporting 3D motion tracking of abdominal targets. By eliminating the need for large scale training datasets, the method promises to enable clinical implementation of 3D motion tracking for precision radiation therapy.

Extracting lung contour deformation features with deep learning for internal target motion tracking: a preliminary study

Objective. To propose lung contour deformation features (LCDFs) as a surrogate to estimate the thoracic internal target motion, and to report their performance by correlating with the changing body using a cascade ensemble model (CEM). LCDFs, correlated to the respiration driver, are employed without patient-specific motion data sampling and additional training before treatment. Approach. LCDFs are extracted by matching lung contours via an encoder–decoder deep learning model. CEM estimates LCDFs from the currently captured body, and then uses the estimated LCDFs to track internal target motion. The accuracy of the proposed LCDFs and CEM were evaluated using 48 targets’ motion data, and compared with other published methods. Main results. LCDFs estimated the internal targets with a localization error of 2.6 ± 1.0 mm (average ± standard deviation). CEM reached a localization error of 4.7 ± 0.9 mm and a real-time performance of 256.9 ± 6.0 ms. With no internal anatomy knowledge, they achieved a small accuracy difference (of 0.34∼1.10 mm for LCDFs and of 0.43∼1.75 mm for CEM at the 95% confidence level) with a patient-specific lung biomechanical model and the deformable image registration models. Significance. The results demonstrated the effectiveness of LCDFs and CEM on tracking target motion. LCDFs and CEM are non-invasive, and require no patient-specific training before treatment. They show potential for broad applications.