Tracking Algorithm Research Articles

Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization

Balancing Communication and Computation in Gradient Tracking Algorithms for Decentralized Optimization

Spatiotemporal Information, Near-Field Perception, and Service for Tourists by Distributed Camera and BeiDou Positioning System in Mountainous Scenic Areas

The collaborative use of camera near-field sensors for monitoring the number and status of tourists is a crucial aspect of smart scenic spot management. This paper proposes a near-field perception technical system that achieves dynamic and accurate detection of tourist targets in mountainous scenic areas, addressing the challenges of real-time passive perception and safety management of tourists. The technical framework involves the following steps: Firstly, real-time video stream signals are collected from multiple cameras to create a distributed perception network. Then, the YOLOX network model is enhanced with the CBAM module and ASFF method to improve the dynamic recognition of preliminary tourist targets in complex scenes. Additionally, the BYTE target dynamic tracking algorithm is employed to address the issue of target occlusion in mountainous scenic areas, thereby enhancing the accuracy of model detection. Finally, the video target monocular spatial positioning algorithm is utilized to determine the actual geographic location of tourists based on the image coordinates. The algorithm was deployed in the Tianmeng Scenic Area of Yimeng Mountain in Shandong Province, and the results demonstrate that this technical system effectively assists in accurately perceiving and spatially positioning tourists in mountainous scenic spots. The system demonstrates an overall accuracy in tourist perception of over 90%, with spatial positioning errors less than 1.0 m and a root mean square error (RMSE) of less than 1.14. This provides auxiliary technical support and effective data support for passive real-time dynamic precise perception and safety management of regional tourist targets in mountainous scenic areas with no/weak satellite navigation signals.

Railway foreign object tracking and detection with spatial positioning and feature generalization enhancement

The existing deep learning foreign object tracking and detection algorithm is easily affected by complex environments and target occlusion, resulting in problems such as missed detection and low detection accuracy. A railway foreign object tracking and detection algorithm with spatial positioning and feature generalization enhancement is proposed. First, a multi-scale cascade improved GhostNet feature network is proposed to improve the feature extraction capability of infrared targets. Secondly, the spatial positioning and feature generalization enhancement module is designed by using the spatial position positioning and generalized morphological information of foreign objects to enhance the detection accuracy of targets with position movement and tracking trajectory changesin complex scenes. Then, a pyramid prediction network is constructed to obtain the detection anchor frame, type and confidence information of infrared railway foreign objects. Finally, by improving the DeepSORT tracking algorithm with improved category and confidence display, combined with Kalman filtering and Hungarian algorithm, railway foreign object tracking and detection in infrared weak light environment is realized. Experimental results show that the proposed method has a tracking and detection accuracy of railway foreign objects 83.3%, with an average detection rate of 11.3 frames per second. Compared with the comparison method, the proposed method has higher detection accuracy and has better performance in railway foreign object tracking and detection in infrared weak light scenes.

Adaptive probe position correction for automated complex weld inspection based on structural signal monitoring

ABSTRACT To ensure comprehensive coverage of welds, multi-axis motions are necessary for the probe during the automatic detection of complex welds. Guaranteeing the effectiveness of ultrasonic data during this process is crucial for ensuring detection accuracy and reliability. Taking tubular Y-joints as an example, this paper presents an adaptive probe posture correction method based on structural signal monitoring: (1) The structural and acoustic model of tubular Y-joints is established to select and predict the target structural signal. (2) Feature extraction and signal tracking algorithms are developed to achieve real-time monitoring of signals. (3) A posture correction method is proposed based on signal characteristics: time-domain characteristics correspond to position adjustments, while amplitudes correspond to orientation corrections. Building upon this, a feedback mechanism for probe posture is established. The effectiveness of the developed method is verified through underwater automatic detection experiments of tubular Y-joints. Results demonstrate that, with the assistance of the probe posture correction method, the coverage of the effective area increases to more than 95%, and embedded defects are fully detected through a single scan. In conclusion, the adaptive probe posture correction method based on structural signal monitoring presents a promising approach for the automatic ultrasonic examination of complex welds.

Multi-strategy arithmetic optimization algorithm for global optimization and uncertain motion tracking

Multi-strategy arithmetic optimization algorithm for global optimization and uncertain motion tracking

An interface tracking method with triangle edge cuts

This paper introduces a volume-conserving interface tracking algorithm on unstructured triangle meshes. We propose to discretize the interface via triangle edge cuts which represent the intersections between the interface and the triangle mesh edges using a compact 6 numbers per triangle. This enables an efficient implicit representation of the sub-triangle polygonal material regions without explicitly storing connectivity information. Moreover, we propose an efficient advection algorithm for this interface representation that is based on geometric queries and does not require an optimization process. This advection algorithm is extended via an area correction step that enforces volume-conservation of the materials. We demonstrate the efficacy of our method on a variety of advection problems on a triangle mesh and compare its performance to existing interface tracking methods including VOF and MOF.

Research on Cattle Behavior Recognition and Multi-Object Tracking Algorithm Based on YOLO-BoT.

In smart ranch management, cattle behavior recognition and tracking play a crucial role in evaluating animal welfare. To address the issues of missed and false detections caused by inter-cow occlusions and infrastructure obstructions in the barn environment, this paper proposes a multi-object tracking method called YOLO-BoT. Built upon YOLOv8, the method first integrates dynamic convolution (DyConv) to enable adaptive weight adjustments, enhancing detection accuracy in complex environments. The C2f-iRMB structure is then employed to improve feature extraction efficiency, ensuring the capture of essential features even under occlusions or lighting variations. Additionally, the Adown downsampling module is incorporated to strengthen multi-scale information fusion, and a dynamic head (DyHead) is used to improve the robustness of detection boxes, ensuring precise identification of rapidly changing target positions. To further enhance tracking performance, DIoU distance calculation, confidence-based bounding box reclassification, and a virtual trajectory update mechanism are introduced, ensuring accurate matching under occlusion and minimizing identity switches. Experimental results demonstrate that YOLO-BoT achieves a mean average precision (mAP) of 91.7% in cattle detection, with precision and recall increased by 4.4% and 1%, respectively. Moreover, the proposed method improves higher order tracking accuracy (HOTA), multi-object tracking accuracy (MOTA), multi-object tracking precision (MOTP), and IDF1 by 4.4%, 7%, 1.7%, and 4.3%, respectively, while reducing the identity switch rate (IDS) by 30.9%. The tracker operates in real-time at an average speed of 31.2 fps, significantly enhancing multi-object tracking performance in complex scenarios and providing strong support for long-term behavior analysis and contactless automated monitoring.

An automatic tracking method to measure the mandibula movement during real time MRI

Mandibular movement is complex and individual due to variations in the temporomandibular joint (TMJ). Consequently, patient-centered dentistry should incorporate patients’ specific anatomy and condylar function in treatment planning. Real-time magnetic resonance imaging (rt-MRI) visualizes relevant structures and tracks mandibular movement. However, current assessments rely on qualitative observations or time-consuming manual tracking, lacking reliability. This study developed an automatic tracking algorithm for mandibular movement in rt-MRI using least mean square registration (LMS) and compared it to manual tracking (MT) during mouth opening. Ten participants with skeletal class I underwent rt-MRI (10 frames/s). The same operator tracked the condylar pathway for the two methods, setting 2000 landmarks (2 landmarks x100 frames x10 participants) for MT and 210 landmarks (3 landmarks x7 frames x10 participants) for LMS. Time required, superimposition error, and the distance between tracked condylar pathways were compared between methods. LMS tracking was 76% faster and showed significantly better superimposition (0.0289 ± 0.0058) than MT (0.059 ± 0.0145) (p = 0.002). During one-third of the movement, the pathways tracked by both methods were more than 1 mm and 1° apart. These findings highlight the benefits of automatic condylar movement tracking in rt-MRI, laying the groundwork for more objective and quantitative observation of TMJ function.

Visual tracking algorithm based on template updating and dual feature enhancement

Aiming at the problem of tracking failure due to target deformation, flipping and occlusion in visual tracking, a template updating algorithm based on image structural similarity is proposed by dynamically updating the template to adapt to the changes of the target during tracking, specifically, a queue is used to save the recent N -frame tracking results, and a decision is made on whether to update the template or not based on the structural similarity score between the current tracking results and the template image, and if updated, the template is matched from the historical N -frame tracking results as the new template. If updated, the optimal target image is matched from the historical N -frame tracking results as a new template for subsequent tracking. The tracking feature enhancement module and segmentation feature enhancement module are also designed based on SiamMask network. The tracking feature enhancement module consists of non-local operations and convolutional downsampling, which is used to establish contextual correlation, enhance the target features, suppress the background interference, improve the tracking robustness, and solve the feature attenuation problem due to the occlusion of the target. The segmentation feature enhancement module introduces the convolutional block attention module and deformable convolution to improve the network's ability to capture channel and spatial features, adaptively learn the shape and contour information of the target, and enhance the network's segmentation accuracy of the tracked target. , which in turn improves the tracking accuracy. Experiments show that the proposed algorithm performs well and stably in solving the above problems, improving the expected average overlap rate by 5.2%, 5.3%, and 2.5%, and the robustness by 6%, 7.9%, and 15.6%on the VOT2016, VOT2018, and VOT2019 datasets , respectively, and achieving a real-time speed of 91 frames per second, when compared to the baseline SiamMask.

Adaptive content-aware spatial regularized correlation filter tracking algorithm

In order to solve the annoying boundary effects in correlation filter (CF) trackers induced by cyclic shift when sampling training patches, and improve the tracking performance, an adaptive content aware spatially regularized correlation filter (ACSRCF) is proposed. Firstly, real negative samples are generated from the background area around the target object, so as to alleviate the filter degradation by the fake negative samples induced from the circularly shifted object patches. Secondly, the locality sensitive histogram (LSH) based foreground feature is extracted and incorporated with the spatial regularization weight which is updated adaptively according to the varied object-oriented appearances. Thereafter, the CF model is optimized using the alternative direction method of multipliers (ADMM) in which the model is decomposed into two sub-problems and the LSH-based features are used in iteration for obtaining the optimal solutions. Finally, the proposed method is evaluated on 5 public benchmarks. The experimental results show that the accuracy and success rate scores of our method on OTB 50 dataset are 90.3%and 66.1%, respectively, exceeding the other CF trackers .The data on the OTB100 dataset is 92.2%and 69.2%, and the accuracy first ranks among all the trackers, while the success rate is ahead of other CF trackers.

Real-Time Tracking Target System Based on Kernelized Correlation Filter in Complicated Areas.

The achievement of rapid and reliable image object tracking has long been crucial and challenging for the advancement of image-guided technology. This study investigates real-time object tracking by offering an image target based on nuclear correlation tracking and detection methods to address the challenge of real-time target tracking in complicated environments. In the tracking process, the nuclear-related tracking algorithm can effectively balance the tracking performance and running speed. However, the target tracking process also faces challenges such as model drift, the inability to handle target scale transformation, and target length. In order to propose a solution, this work is organized around the following main points: this study dedicates its first part to the research on kernelized correlation filters (KCFs), encompassing model training, object identification, and a dense sampling strategy based on a circulant matrix. This work developed a scale pyramid searching approach to address the shortcoming that a KCF cannot forecast the target scale. The tracker was expanded in two stages: the first stage output the target's two-dimensional coordinate location, and the second stage created the scale pyramid to identify the optimal target scale. Experiments show that this approach is capable of resolving the target size variation problem. The second part improved the KCF in two ways to meet the demands of a long-term object tracking task. This article introduces the initial object model, which effectively suppresses model drift. Secondly, an object detection module is implemented, and if the tracking module fails, the algorithm is redirected to the object detection module. The target detection module utilizes two detectors, a variance classifier and a KCF. Finally, this work includes trials on object tracking experiments and subsequent analysis of the results. Initially, this research provides a tracking algorithm assessment system, including an assessment methodology and the collection of test videos, which helped us to determine that the suggested technique outperforms the KCF tracking method. Additionally, the implementation of an evaluation system allows for an objective comparison of the proposed algorithm with other prominent tracking methods. We found that the suggested method outperforms others in terms of its accuracy and resilience.

Adaptive interacting multiple model particle filter based on a dual-pattern bat algorithm for maneuvering target tracking

The interacting multiple model particle filter (IMM-PF) is a filtering method commonly used for nonlinear non-Gaussian radar systems. Its transfer probabilities are usually fixed and dependent on prior information. When tracking maneuvering targets, the IMM-PF may cause excessive tracking errors due to the model switching lag. In addition, the particle impoverishment caused by the resampling of the particle filter seriously affects the filtering accuracy. Therefore, the IMM-PF has difficulty meeting the accuracy and speed requirements of modern high-performance radar target tracking systems. To address these problems, an adaptive interacting multiple model particle filter based on the dual-pattern bat algorithm (ADIMM-DPBA-PF) is proposed for tracking maneuvering targets under nonlinear and non-Gaussian conditions. First, the adaptive model switching mechanism is established to adjust the transition probabilities using the model probability posterior information at consecutive times, improving the model switching efficiency. Second, a particle filter based on the dual-pattern bat algorithm (DPBA-PF) is proposed. The filter exploits global search and local search strategies to optimize the particles and intelligently move the particles to the high likelihood region. Finally, a particle filter based on the dual-pattern bat algorithm is used to form the adaptive interacting multiple model method. The experimental results show that the proposed algorithm has better comprehensive performance than the IMM-PF.

Primary atomization of shear-thinning liquid jets: a direct numerical simulation study

Using direct numerical simulation, the primary atomization of shear-thinning liquid jets into stagnant gas is investigated. Starting from a Newtonian configuration with material properties approximately corresponding to a Diesel injection, two hypothetical shear-thinning cases using the power-law and the Carreau-Yasuda models for the calculation of the apparent viscosity are investigated. A recently developed tracking algorithm is used to identify droplets newly formed from the core jet, as well as all other droplets in the computational domain, and a number of relevant droplet characteristics, such as droplet volume, surface area and center of mass, is recorded at each time step. This allows a comparison of droplet characteristics on the basis of probability density functions. It is observed that the shear-thinning behavior of the liquid phase, which is particularly relevant at the interface, influences the droplet volumes and shapes. While the mean viscosity differs significantly for the different cases, the first- and second-order velocity and volume fraction statistics remain nearly unchanged.

An adaptive acceleration scheme for phase-field fatigue computations

Abstract Phase-field models of fatigue are capable of reproducing the main phenomenology of fatigue behavior. However, phase-field computations in the high-cycle fatigue regime are prohibitively expensive due to the need to resolve spatially the small length scale inherent to phase-field models and temporally the loading history for several millions of cycles. As a remedy, we propose a fully adaptive acceleration scheme based on the cycle jump technique, where the cycle-by-cycle resolution of an appropriately determined number of cycles is skipped while predicting the local system evolution during the jump. The novelty of our approach is a cycle-jump criterion to determine the appropriate cycle-jump size based on a target increment of a global variable which monitors the advancement of fatigue. We propose the definition and meaning of this variable for three general stages of the fatigue life. In comparison to existing acceleration techniques, our approach needs no parameters and bounds for the cycle-jump size, and it works independently of the material, specimen or loading conditions. Since one of the monitoring variables is the fatigue crack length, we introduce an accurate, flexible and efficient method for its computation, which overcomes the issues of conventional crack tip tracking algorithms and enables the consideration of several cracks evolving at the same time. The performance of the proposed acceleration scheme is demonstrated with representative numerical examples, which show a speedup reaching up to four orders of magnitude in the high-cycle fatigue regime with consistently high accuracy. Graphical abstract

Recover a moving rotor UAV without ground–air communications: System and control of a dual-stage tracking device

Recovering a moving rotor unmanned aerial vehicle (UAV) using a single-stage dynamic tracking device poses a significant challenge, particularly without real-time communication between the two systems. This study presents a dual-stage tracking system comprising an unmanned ground vehicle (UGV) and a Stewart platform, aimed at dynamically tracking and recovering the UAV. Firstly, an observation algorithm combining Kalman filtering (KF) and curve fitting is designed to estimate and complete the drone’s states and predict its trajectory. Subsequently, a decoupled dual-stage tracking control structure is introduced, integrating two independent controlled subsystems. Specifically, in the UGV controller, the model predictive control (MPC) is employed to enhance dynamic tracking capabilities using absolute kinematics. A motion tracking algorithm based on relative kinematics was developed for the Stewart recovery platform to compensate for UGV tracking errors and improve tracking accuracy. Dynamic recovery simulations and experiments have been conducted to validate the feasibility and effectiveness of the proposed dual-stage tracking system. The results demonstrate the system’s capability to dynamically track and recover the drone without real-time communication in complex environments characterized by detection noise and target trajectory disturbances.

UAV Hunter: A Net-Capturing UAV System with Improved Detection and Tracking Methods for Anti-UAV Defense

The abuse of UAVs poses a potential risk to social security, necessitating the investigation of anti-UAV methods to safeguard critical areas. However, the existing UAV countermeasures face challenges such as high environmental impact, restricted spatial deployment, and low cost-effectiveness. To address these limitations, we developed a novel anti-UAV system known as UAV Hunter, which adopts an airborne tether-net capture device with visual aids to counter unauthorized UAVs. This system employs an “Anti-UAV with UAV” scheme, comprising a ground control station and a net-capturing UAV. The operator utilizes the ground control station to determine the mission area and flight path and then controls the flight of the net-capturing UAV. During flight, the net-capturing UAV leverages its dual-mode sensor to continuously monitor the target area. Simultaneously, the onboard computer executes a UAV detection and tracking algorithm to search for unauthorized UAVs in real time. The results are relayed to the operator in real time, facilitating precise adjustments for the net-capturing UAV to launch the rope net accurately. The system successfully realizes the functions of dual-mode real-time detection and tracking, precise net capture, and efficient integrated control. Compared with existing methods, the developed system exhibits accurate recognition, rapid action, diverse application scenarios, and an enhanced human–machine interaction experience. Test results in the open environment further validate the feasibility and functional integrity of the system, demonstrating its capability to effectively capture low-altitude unauthorized UAVs.

Blessing or curse? The two-sided effects of algorithmic control on ego-depletion and safety performance of gig workers

The emergence of gig economy has facilitated the adoption of algorithm-based management systems, creating favorable conditions for gig workers. Nevertheless, it also brings various challenges and uncertainties, especially gig workers' safety performance, having become a prominent concern. Based on ego-depletion theory, we investigate the underlying mechanism through which platform algorithmic control influences on safety performance of gig workers. Based on two points of data from 314 gig workers in China, we found that the three dimensions of algorithmic control (viz., standardized guidance, tracking evaluation and behavioral constraint) have differential effects on safety performance. On one hand, algorithmic standardized guidance is negatively related to ego-depletion, which in turn improves safety performance. On the other hand, algorithmic tracking evaluation and behavioral constraint are positively related to ego-depletion, and consequently reducing safety performance. Furthermore, algorithmic transparency moderates the relationship between algorithmic standardized guidance, algorithmic tracking evaluation, and ego-depletion; self-efficacy moderates the relationship between algorithmic standardized guidance and ego-depletion; both trait mindfulness and leadership safety commitment moderate the relationship between ego-depletion and safety performance. This study offers valuable insights for platform enterprises to optimize the effectiveness of algorithmic control.

Photovoltaic Maximum Power Point Tracking Technology Based on Improved Perturbation Observation Method and Backstepping Algorithm

Photovoltaic power generation systems mainly use the maximum power tracking (MPPT) controller to adjust the voltage and current of the solar cells in the photovoltaic array, so that the photovoltaic array runs at the maximum power point (MPP) to achieve the purpose of maximum power output. At present, photovoltaic power stations mainly adopt the traditional method to track the maximum power point, but this fixed step method easily causes output power oscillation of the photovoltaic array when tracking the maximum power point, and it easily falls into the local extreme point under partial shadow conditions. In order to solve these problems, this paper proposes an improved perturbation observation method and backstepping method (IP&O-backstepping) to replace the traditional method applied to the MPPT controller to optimize the operating state of the solar cell, thereby improving the output power point of the photovoltaic array and increasing the output power of the photovoltaic array. The algorithm first uses the improved perturbation and observation (IP&O) method to search the maximum power point of the photovoltaic array and output the reference voltage. Secondly, the reference voltage is input into the backstepping algorithm for voltage tracking. Finally, the algorithm tracks the reference voltage and makes the photovoltaic array operate at the maximum power point. The simulation is carried out by using MATLAB/Simulink. The IP&O-backstepping algorithm is compared with the intelligent algorithm and the traditional method, and the results show that compared to the above algorithm, the IP&O-backstepping algorithm can not only track the maximum power point of the photovoltaic array, but also has a faster tracking speed, and the output power has almost no oscillation when the photovoltaic array runs at the maximum power point.

A Radar-Based Methodology for Aerosol Plume Identification and Characterisation on the South African Highveld

Biomass burning on the South African Highveld annually injects substantial amounts of aerosols and trace gases into the atmosphere, impacting the global radiative balance, cloud microphysics, and regional air quality. These aerosols are transported as plumes over long distances, posing challenges to existing in situ and satellite-based monitoring techniques because of their limited spatial and temporal resolution, particularly in environments with low-level sources. This study aims to develop and validate a novel radar-based methodology to detect, track, and characterise aerosol plumes, addressing the limitations of existing in situ and satellite monitoring techniques. Using high-resolution volumetric reflectivity data from an S-band radar in Pretoria, South Africa, a traditional storm tracking algorithm is adapted to improve plume identification. Case studies of plume events in June and August 2013 demonstrate the radar’s effectiveness in distinguishing lower vertical profiles and reduced reflectivity of plumes compared with storm echoes. The adapted algorithm successfully tracked the spatial and temporal evolution of the plumes, revealing their short-lived nature. Results indicate that radar-derived geospatial characteristics have the potential to contribute significantly to understanding the impacts of plumes on local air quality. These findings underscore the critical need for high spatio-temporal resolution data to support effective air quality management and inform policy development in regions affected by biomass burning.

Design, and dynamic evaluation of a novel photovoltaic pumping system emulation with DS1104 hardware setup: Towards innovative in green energy systems.

Diesel engines (DEs) commonly power pumps used in agricultural and grassland irrigation. However, relying on unpredictable and costly fuel sources for DEs pose's challenges related to availability, reliability, maintenance, and lifespan. Addressing these environmental concerns, this study introduces an emulation approach for photovoltaic (PV) water pumping (WP) systems. Emulation offers a promising alternative due to financial constraints, spatial limitations, and climate dependency in full-scale systems. The proposed setup includes three key elements: a PV system emulator employing back converter control to replicate PV panel characteristics, a boost converter with an MPPT algorithm for efficient power tracking across diverse conditions, and a motor pump (MP) emulator integrating an induction motor connected to a DC generator to simulate water pump behaviors. Precise induction motor control is achieved through a controlled inverter. This work innovatively combines PV and WP emulation while optimizing system dynamics, aiming to develop a comprehensive emulator and evaluate an enhanced control algorithm. An optimized scalar control strategy regulates the water MP, demonstrated through MATLAB/Simulink simulations that highlight superior performance and responsiveness to solar irradiation variations compared to conventional MPPT techniques. Experimental validation using the dSPACE control desk DS1104 confirms the emulator's ability to faithfully reproduce genuine solar panel characteristics.