Efficient Tracking Research Articles

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.

Intelligent Bus Tracking System with Attendance based on Facial Recognition

The Intelligent Bus Tracking System is a cutting-edge solution that integrates machine learning tools and face detection technology to revolutionize transportation services within academic institutions. Leveraging the power of artificial intelligence, this system enhances the accuracy, efficiency, and security of bus tracking while introducing innovative features such as facial recognition for identification to Student Attendance.(Saad et al., 2018) The bus tracking system is a comprehensive solution designed to enhance the efficiency and safety of transportation services within academic institutions. This system leverages modern technologies, including GPS and mobile communication to provide real time tracking and monitoring of buses operating within the academic campus. The primary goal is to optimize the transportation experience for students, faculties and staff while also improving overall operational management.(Sharif et al., 2018) Keywords: GPS, Tracking system, Attendance system Face Recognition, Machine Learning,

BUSNAV: A Real Time Bus Tracking Application

This research focuses on developing an advanced Bus Tracking System, with the primary goal of creating a GPS tracking application that surpasses existing systems in terms of accuracy and efficiency, specifically in tracking buses. The motivation for this study stemmed from the noticeable time wastage individuals experience while waiting for buses on their designated routes, coupled with the absence of real-time information for those who have missed their bus. This research endeavor aims not only to enhance the precision and efficiency of bus tracking but also to address the common issue of people wasting valuable time while awaiting buses and those who miss their rides due to the lack of real-time information. By tackling these challenges, the developed Bus Tracking System strives to optimize the overall public transportation experience, offering users timely and reliable information to streamline their commutes and minimize inconvenience. Through innovative technological solutions and a user- centric approach, this research endeavors to significantly improve the efficiency and effectiveness of bus tracking systems, ultimately benefiting commuters and transit authorities alike.

Deep learning based event reconstruction for cyclotron radiation emission spectroscopy

The objective of the cyclotron radiation emission spectroscopy (CRES) technology is to build precise particle energy spectra. This is achieved by identifying the start frequencies of charged particle trajectories which, when exposed to an external magnetic field, leave semi-linear profiles (called tracks) in the time–frequency plane. Due to the need for excellent instrumental energy resolution in application, highly efficient and accurate track reconstruction methods are desired. Deep learning convolutional neural networks (CNNs) - particularly suited to deal with information-sparse data and which offer precise foreground localization—may be utilized to extract track properties from measured CRES signals (called events) with relative computational ease. In this work, we develop a novel machine learning based model which operates a CNN and a support vector machine in tandem to perform this reconstruction. A primary application of our method is shown on simulated CRES signals which mimic those of the Project 8 experiment—a novel effort to extract the unknown absolute neutrino mass value from a precise measurement of tritium β −-decay energy spectrum. When compared to a point-clustering based technique used as a baseline, we show a relative gain of 24.1% in event reconstruction efficiency and comparable performance in accuracy of track parameter reconstruction.

Wireless Power Transfer Efficiency Optimization Tracking Method Based on Full Current Mode Impedance Matching.

Wireless power transfer (WPT) technology is a contactless wireless energy transfer method with wide-ranging applications in fields such as smart homes, the Internet of Things (IoT), and electric vehicles. Achieving optimal efficiency in wireless power transfer systems has been a key research focus. In this paper, we propose a tracking method based on full current mode impedance matching for optimizing wireless power transfer efficiency. This method enables efficiency tracking in WPT systems and seamless switching between continuous conduction mode and discontinuous mode, expanding the detection capabilities of the wireless power transfer system. MATLAB was used to simulate the proposed method and validate its feasibility and effectiveness. Based on the simulation results, the proposed method ensures optimal efficiency tracking in wireless power transfer systems while extending detection capabilities, offering practical value and potential for widespread applications.

A decentralized solid compound storage facility managed by a centralized electronic platform at a growing drug discovery company

Within a growing drug discovery company, scientists acquire (either through in house synthesis or purchase) then store, retrieve, and ship solid compound samples daily between multiple locations. The efficient management and tracking of this entire process to support drug discovery is a significant challenge. This article describes a decentralized and cost-effective inventory facility that simplifies the solid compound storage and retrieval process. Standardized storage cabinets from the market are utilized, providing a cost-effective physical infrastructure. The cabinets can be distributed across storage rooms at multiple sites and arranged into spaces with a variety of dimensions, allowing the system to be retrofitted into existing facilities and scaled up easily. We can provide storage close to work areas at each location, minimizing both unnecessary movement of staff and transportation of substances. We have applied a systematic barcoding method to the compound batch identifier that correlates with its compound location. This simplifies the compound registration process as well as the process of finding and returning compounds. Additionally, a centralized electronic platform has been employed to store, update and track solid compound information, such as properties, location and quantity. Compound shipment may be initiated from different sites, and a centralized electronic platform assists the information retrieval process, ensuring each location possesses up-to-date information. The electronic platform we present streamlines the management of compound registration, location tracking, weight updates and shipment information, facilitating seamless record sharing among all stakeholders. Every step of the process can be tracked in real time by the project team. The platform can be flexibly configured to adapt to an evolving set of storage locations, with all information and processes being audited.

OATracker: Object-aware anti-occlusion 3D multiobject tracking for autonomous driving

Efficient and accurate 3D multiobject tracking (MOT) is essential for autonomous driving. However, existing methods still struggle with multiobject occlusion, in which interruptions or even loss of crucial tracked objects is likely. Therefore, a more intelligent object-aware anti-occlusion 3D MOT for autonomous driving, named OATracker, is developed in this paper. First, an updated 3D cascaded detection (3DCD) is adopted as the detection backbone, with incorporation of an updatable component based on the OpenPCDet framework to increase the longevity. Second, a reliable object state-constrained affinity (OSA) metric is designed that adaptively combines 3D geometric and motion metrics to dynamically measure objects’ size and distance in both spatial and temporal dimensions. Third, an object-aware trajectory management (OTM) module is developed for trajectory management and status updating. Specifically, the object identity-aware adaptive tracking life manager (ATLM) allows the tracker to adaptively manage the trajectories of captured objects through a confidence metric for each objects, and the ghost-aware trajectory postoptimizer (GTP) associates the historical and detected motion states, further overcoming id-switch and fragmentation problems. Finally, experiments on the KITTI-Car tracking benchmark and practical autonomous driving car application platform show that the OATracker can achieve competitive and robust tracking performance even in occlusion conditions.

Thermoelectric power generation system intelligent Runge Kutta control: A performance analysis using processor in loop testing

As an emerging source of clean electrical power, Thermoelectric generation (TEG) finds its applications in heat removal and electricity generation as an efficient improvement tool for thermal devices utilizing fossil fuels. TEG exhibits low power density and its temperature distribution is usually non-uniform over thermal conductive surfaces. Due to the non-uniformity of heat flow and loose surface contact, non-uniform temperature distribution (NTD) appears on TEG surfaces and the TEG control problem becomes complex, multi-solution, nonlinear, and highly sensitive to operating conditions. The bypass diode activation of TEG systems streamlines the power flow in a string of series-connected modules, generating multiple peak points. Classical techniques fail to address these issues of multiple maxima and lose efficiency. To solve this problem, a novel SI-based optimization algorithm, Runge Kutta Method (RUN), is applied as MPPT control. To gauge the performance of the proposed controller several distinct case studies are used, including varying temperatures gradient, NTD, 24-hour thermal profile stochastic temperature, and experimental verification. Additionally, MPPT rating analysis, economic assessment, and statistical studies are done for comparison with other state-of-the-art control techniques. The minimum tracking and settling times have been improved by RUN to 180 ms. For the additional hardware implementation, the maximum levelized cost of energy (LCOE) is about 0.16 $kWh1.07¥kWh. The power tracking efficiency of RUN can be above 99 % with energy harvest improvements of 6.3 %.

MFACNet: A Multi-Frame Feature Aggregating and Inter-Feature Correlation Framework for Multi-Object Tracking in Satellite Videos

Efficient multi-object tracking (MOT) in satellite videos is crucial for numerous applications, ranging from surveillance to environmental monitoring. Existing methods often struggle with effectively exploring the correlation and contextual cues inherent in the consecutive features of video sequences, resulting in redundant feature inference and unreliable motion estimation for tracking. To address these challenges, we propose the MFACNet, a novel multi-frame features aggregating and inter-feature correlation framework for enhancing MOT in satellite videos with the idea of utilizing the features of consecutive frames. The MFACNet integrates multi-frame feature aggregation techniques with inter-feature correlation mechanisms to improve tracking accuracy and robustness. Specifically, our framework leverages temporal information across the features of consecutive frames to capture contextual cues and refine object representations over time. Moreover, we introduce a mechanism to explicitly model the correlations between adjacent features in video sequences, facilitating a more accurate motion estimation and trajectory associations. We evaluated the MFACNet using benchmark datasets for satellite-based video MOT tasks and demonstrated its superiority in terms of tracking accuracy and robustness over state-of-the-art performance by 2.0% in MOTA and 1.6% in IDF1. Our experimental results highlight the potential of precisely utilizing deep features from video sequences.

Facial Recognition Attendance System Using AI

bstract: This paper presents a concise overview of a facial attendance system implemented using Python. Leveraging deep learning techniques and popular libraries such as OpenCV and Tensor Flow, the system offers accurate and efficient attendance tracking based on facial recognition. The paper discusses the system architecture, dataset used for training, performance evaluation, and potential implications for real-world deployment. Overall, this research contributes to the advancement of attendance management systems through the integration of facial recognition technology. Index Terms- Facial Recognition,Attendance Management Systems, Python Programming, Deep Learning, Convolutional Neural Networks (CNNs),Learning, Convolutional Processing, Privacy Concerns, Ethical Considerations

Review of Cloud-Based Smart Energy Meters

Abstract: Smart meters represent a pivotal advancement inenergy management, offering numerous benefits to consumers and utility providers. This report provides an overview of smart meters, their functionalities, advantages, challenges, and broader implications for the energy industry. A smart meter is an advanced device that accurately measures electricity consumption. It's better than traditional meters, providing efficient tracking and insights into energy usage habits. Upgrade to a smart meter to make informed decisions and save money on electricity bills. These devices are a vital component of smart grid technology, which aims to enhance energy distribution and consumption efficiency, reliability, and sustainability. Modern technologies, such as the Internet of Things (IoT), have many applications in the energy sector. IoT can help to improve energy efficiency, increase the utilization of renewable energy sources, and reduce the environmental impact of energy use. It can achieve these goals in energy supply, transmission, distribution, and demand. This paper reviews the literature on IoT in energy metering systems and its essential components, functionality, and advantages over conventional metering systems.

Manipulating Camera Gimbal Positioning by Deep Deterministic Policy Gradient Reinforcement Learning for Drone Object Detection

The object recognition technology of unmanned aerial vehicles (UAVs) equipped with “You Only Look Once” (YOLO) has been validated in actual flights. However, here, the challenge lies in efficiently utilizing camera gimbal control technology to swiftly capture images of YOLO-identified target objects in aerial search missions. Enhancing the UAV’s energy efficiency and search effectiveness is imperative. This study aims to establish a simulation environment by employing the Unity simulation software for target tracking by controlling the gimbal. This approach involves the development of deep deterministic policy-gradient (DDPG) reinforcement-learning techniques to train the gimbal in executing effective tracking actions. The outcomes of the simulations indicate that when actions are appropriately rewarded or penalized in the form of scores, the reward value can be consistently converged within the range of 19–35. This convergence implies that a successful strategy leads to consistently high rewards. Consequently, a refined set of training procedures is devised, enabling the gimbal to accurately track the target. Moreover, this strategy minimizes unnecessary tracking actions, thus enhancing tracking efficiency. Numerous benefits arise from training in a simulated environment. For instance, the training in this simulated environment is facilitated through a dataset composed of actual flight photographs. Furthermore, offline operations can be conducted at any given time without any constraint of time and space. Thus, this approach effectively enables the training and enhancement of the gimbal’s action strategies. The findings of this study demonstrate that a coherent set of action strategies can be proficiently cultivated by employing DDPG reinforcement learning. Furthermore, these strategies empower the UAV’s gimbal to rapidly and precisely track designated targets. Therefore, this approach provides both convenience and opportunities to gather more flight-scenario training data in the future. This gathering of data will lead to immediate training opportunities and help improve the system’s energy consumption.

Micro-mechanical behavior of stone-blowing in ballast maintenance using DEM-CFD coupling method

Stone-blowing restores the track geometry by blowing small crushed stones into the bottom of the sleeper, extending the maintenance period. In this study, ballast and filling stones were modelled using discrete element method (DEM), while the air blowing was simulated using computational fluid dynamics (CFD). The DEM-CFD coupled model has been used to simulate the stone-blowing process and investigate the optimal operation parameters from a micro view.The disturbance of ballast bed during stone-blowing process was analyzed. Meanwhile, the effect of air velocity and tube layouts on the stone-blowing, as well as the sleeper settlement after stone-blowing were discussed. The results show that the maximum disturbance occurs in the inserting area between sleepers, and the disturbance increased with faster insertion speed. It was suggested that the inserting speed of the tube is 0.4 m/s. When the air velocity of stone-blowing was not less than 20 m/s, the blowing quality meets the requirement. Furthermore, the four-tubed stone-blowing approach distributed filling stones more evenly under the sleeper, and reduced the risk of tube blockage. After stone-blowing, the contact number between the bottom of the sleeper and the ballast is greatly increased, reaching 217.9 % after double cross tubes, and 245 % after four tubes stone-blowing. The crushed stone blown in greatly improves the stress distribution of the ballast bed and makes the load transfer more uniform. Overall, this study provides valuable insights into the stone-blowing process and can help optimize the stone-blowing parameters for efficient and effective track maintenance.

Improving the efficiency of photovoltaic-thermoelectric generator system using novel flying squirrel search optimization algorithm: Hybrid renewable and thermal energy system (RTES) for electricity generation

The world is moving towards cleaner energy to cater to the effects of global warming, the existing renewable energy resources need to be hybridized with other resources for better output using the same input. Photovoltaic-thermoelectric generator (PV-TEG) energy system is one example of a hybrid renewable and thermal energy system (RTES) for electricity generation, the waste heat which if accumulated on the PV Panel causes an efficiency dip, the heat can be converted into useful energy using a TEG module resulting in PV Panel cooling as well as added energy at the output. For the PV-TEG energy system the controllability aspect is crucial as the main problem lies in the optimization and harvesting of energy from these two sources, the non-linear energy generation nature of the PV and TEG energy systems due to changing conditions i.e., partial shading (PS) and dynamic temperature spread (DTS), makes it hard to attain the full potential of PV and TEG systems using classical/analog techniques. To solve this problem, a novel implementation of Flying Squirrel Search Optimization (FSSO) is used for the Maximum Power Point Tracking (MPPT) for the PV-TEG energy system. The proposed FSSO MPPT algorithm is proven effective through a comparison with Particle Swarm Optimization (PSO), Fruit Fly Optimization (FFO), Perturb and Observe (P&O), and Incremental Conductance (InC) algorithms, demonstrating its superiority. The FSSO-based MPPT algorithm exhibits rapid and accurate Global Maxima (GM) tracking in real-time, minimizing power oscillations with a tracking efficiency of 99.56% and a tracking time of under 0.3 s.

Multibody dynamics modeling and simulation of a three-wheeled mobile robot using a robotic approach

PurposeThis paper focuses on the application of a robotic technique for modeling a three-wheeled mobile robot (WMR), considering it as a multibody polyarticulated system. Then the dynamic behavior of the developed model is verified using a physical model obtained by Simscape Multibody.Design/methodology/approachFirstly, a geometric model is developed using the modified Denavit–Hartenberg method. Then the dynamic model is derived using the algorithm of Newton–Euler. The developed model is performed for a three-wheeled differentially driven robot, which incorporates the slippage of wheels by including the Kiencke tire model to take into account the interaction of wheels with the ground. For the physical model, the mobile robot is designed using Solidworks. Then it is exported to Matlab using Simscape Multibody. The control of the WMR for both models is realized using Matlab/Simulink and aims to ensure efficient tracking of the desired trajectory.FindingsSimulation results show a good similarity between the two models and verify both longitudinal and lateral behaviors of the WMR. This demonstrates the effectiveness of the developed model using the robotic approach and proves that it is sufficiently precise for the design of control schemes.Originality/valueThe motivation to adopt this robotic approach compared to conventional methods is the fact that it makes it possible to obtain models with a reduced number of operations. Furthermore, it allows the facility of implementation by numerical or symbolical programming. This work serves as a reference link for extending this methodology to other types of mobile robots.

A Control-Theoretic Spatio-Temporal Model for Wildfire Smoke Propagation Using UAV-Based Air Pollutant Measurements

Wildfires have the potential to cause severe damage to vegetation, property and most importantly, human life. In order to minimize these negative impacts, it is crucial that wildfires are detected at the earliest possible stages. A potential solution for early wildfire detection is to utilize unmanned aerial vehicles (UAVs) that are capable of tracking the chemical concentration gradient of smoke emitted by wildfires. A spatiotemporal model of wildfire smoke plume dynamics can allow for efficient tracking of the chemicals by utilizing both real-time information from sensors as well as future information from the model predictions. This study investigates a spatiotemporal modeling approach based on subspace identification (SID) to develop a data-driven smoke plume dynamics model for the purposes of early wildfire detection. The model was learned using CO2 concentration data which were collected using an air quality sensor package onboard a UAV during two prescribed burn experiments. Our model was evaluated by comparing the predicted values to the measured values at random locations and showed mean errors of 6.782 ppm and 30.01 ppm from the two experiments. Additionally, our model was shown to outperform the commonly used Gaussian puff model (GPM) which showed mean errors of 25.799 ppm and 104.492 ppm, respectively.

Smart Campus: Smart Attendance Management System using Face Recognition

This Review Paper studies several research papers based on the Smart Attendance system for recording attendance based on facial recognition. Efficient and accurate attendance management is a crucial task in various educational and organizational settings. Traditional methods of manual attendance tracking are time-consuming and error-prone. The proposed system utilizes computer vision and deep learning techniques to recognize and verify the identity of individuals in a given environment. Through the deployment of facial recognition algorithms, it captures and matches facial features with existing records in a database, allowing for seamless and efficient attendance tracking.

Quick installation technology DNA profile – Rapid DNA

The investigation of criminal offenses requires modern, up-to-date, practical means. The ANDE Rapid DNA Identification System is a new technology that generates a DNA ID from forensic samples in less than two hours. In today’s conditions, its use in forensics, practical activities of law enforcement agencies on a permanent basis is very relevant. ANDE technology is specially designed and proven to be robust, mobile and suitable for use in harsh environments.
 The National Police of Ukraine is tasked with the enormous task of identifying victims of horrific crimes related to the ongoing war with russia. Over the past year, it has been proven that a significant percentage of these victims cannot be identified through forensic DNA alone, given her critical condition. The enormous amount of forensic DNA processing work required to address this situation far exceeds the capabilities of traditional DNA laboratory infrastructure. In addition, the logistical overhead associated with managing the efficient storage, movement, tracking, and provenance of large numbers of bodies or even DNA samples across wide geographic areas causes significant wastage of critical resources and long delays. ANDE technology accelerates DNA processing from months or even years to less than two hours. Forensic specialists use mobile DNA laboratories to identify dead. Today, the National Police operates 32 mobile laboratories. Rapid DNA’s secure, field-ready mobile systems provide the most accurate and efficient DNA identification results.
 Thus, the main goal of this study is to provide practical recommendations for forensic support for the use of rapid DNA profiling technology, using Rapid DNA as an example, in pre-trial investigation.
 The stated provisions and practical recommendations in the article are relevant in the context of the use of modern technologies by practical workers.

Fusion-driven deep feature network for enhanced object detection and tracking in video surveillance systems

Object detection and tracking (ODT) is a crucial research area in video surveillance (VS) systems and poses a significant challenge in computer vision and image processing. The primary objective is to identify objects of various classes from video sequences for detection and tracking. The object detection and tracking process involves extracting moving objects from frames and tracking them over time. With the advancement of computer intelligence, this study proposes a novel optimized deep fused learning (ODFL) model for efficient object detection and tracking in video surveillance systems. The optimized deep fused learning model focuses primarily on detecting and tracking multiple objects present in video frames. Initially, the input video undergoes pre-processing by converting it into video frames and applying Gaussian filtering to eliminate noise and enhance frame quality. Next, the feature fusion model employs the Dense Convolution Feature Fusion Network (D-ConvFFN) to extract and fuse relevant features. Subsequently, the Enhanced RefineDet-based Fire Hawk (ERFH) object detection module is utilized by the optimized deep fused learning model to efficiently recognize multiple objects in the video frames. The hyperparameters are optimized using the Fire Hawk optimizer. Once the objects are recognized, a softmax classifier categorizes them into different classes. The Hungarian-based SORT model is used for multi-object tracking. The proposed optimized deep fused learning model is implemented in Python, evaluated on the PETS S2 2009 and UA-DETRAC datasets, and assessed in terms of various evaluation measures. The optimized deep fused learning model’s performance is compared with prevailing architectures, and it achieves a maximum accuracy of 99.16% for the PETS S2 2009 dataset and 99.42% for the UA-DETRAC dataset, outperforming existing classifiers for multi-class object detection and tracking.

A simplified control algorithm for efficient and robust tracking of the maximum power point in PV systems

This article presents a novel two-stage simplified control algorithm designed to enhance the Maximum Power Point Tracking (MPPT) operation of PV systems while minimizing the complexity associated with it. A voltage-based hybrid beta-incremental conductance (hybrid-beta-INC) is developed in the first stage to determine the MPP voltage. The methodology behind this scheme is to first approach the neighborhood of the MPP through an intermediate variable β, which has a simple monotonically decreasing relationship with the PV voltage. Subsequently, the INC is employed to target the actual MPP voltage. The steady-state response of the PV system is thus maintained throughout this stage by the hybrid-beta-INC. In the second stage, a simplified parameter-less (SP) controller is proposed to regulate the underdamped dynamics of the PV. The system's stability as a whole is enhanced through the decoupling of these two phases. In contrast to currently available MPPT controllers, the proposed SP makes a significant contribution to the structural simplicity of the control framework by eliminating the need for adjustable parameters. Simplicity, enhanced control immunity and resilience to load disturbances and parametric uncertainties are the main attributes of the proposed controller. Its superior attributes over exiting controllers such as the P&O, INC, search space, and hybrid INC-integral backstepping nonlinear controllers, is affirmed on the basis of quantitative metrics such as the tracking time, ripples and efficiency. Finally, the performance of the proposed system is monitored under real-time environmental settings for three consecutive days, which confirms its resilience and dependability in tracking the MPP of the PV system under experimental conditions. The results showed that the controller is able to cope with climatic and load changes maintaining a robust response. It is unveiled that it maintains a minimum efficiency of 99.72% despite fluctuations in temperature. In the presence of continually changing irradiance conditions, the EN 50,530 test demonstrates an efficacy in excess of 99.95%.