Vehicle Classification Research Articles

Bio-inspired classification and evolution of multirotor Micro Aerial Vehicles (MAVs): A comprehensive review

Multirotor Micro Aerial Vehicles (MAVs) have become essential in many applications like surveillance, disaster management, and aerial inspection. The diverse demands of these applications have led to numerous design innovations, growing the MAV landscape substantially. However, such growth has made it challenging to understand the evolution and classification of MAV designs based on their functions and features. We address this challenge by introducing a novel, bio-inspired taxonomic classification framework for MAVs. Our framework spans six hierarchical ranks, each containing a diverse set of categories that classify MAVs from distinct design perspectives. It enables a proper comparison of the MAV designs in the literature, revealing their key similarities and differences. It also helps to trace the evolution of MAVs over time, identifying research trends and potential gaps. Lastly, it offers insights into future MAV design trajectories, providing a complete and clear understanding of the MAV design landscape.

Flying foxes optimization with reinforcement learning for vehicle detection in UAV imagery

Intelligent transportation systems (ITS) are globally installed in smart cities, which enable the next generation of ITS depending on the potential integration of autonomous and connected vehicles. Both technologies are being tested widely in various cities across the world. However, these two developing technologies are vital in allowing a fully automatic transportation system; it is necessary to automate other transportation and road components. Unmanned aerial vehicles (UAVs) or drones are utilized for many surveillance applications in the ITS. Detecting on-ground vehicles in drone images is significant for disaster rescue operations, traffic and parking management, and navigating uneven territories. This study presents a flying foxes optimization with deep learning-based vehicle detection and classification model on aerial images (FFODL-VDCAI) technique for ITS application. The main objective of the FFODL-VDCAI technique is to automate and accurately classify vehicles that exist in aerial images. Three primary processes are involved in the presented FFODL-VDCAI technique. Initially, the FFODL-VDCAI approach utilizes YOLO-GD (Ghost-Net and Depthwise convolution) for vehicle detection, where the YOLO-GD uses lightweight Ghost Net in place on the backbone network of YOLO-v4 and interchanges the conventional convolutional with depthwise separable convolutional and pointwise convolutional. Next, the FFO technique is used for hyperparameter tuning the Ghost Net technique. Finally, a deep Q-network (DQN) based reinforcement learning technique is used to classify detected vehicles effectively. A comprehensive simulation analysis of the FFODL-VDCAI methodology is conducted on the UAV image dataset. The performance validation of the FFODL-VDCAI methodology exhibited superior values of 96.15% and 92.03% under PSU and Stanford datasets concerning various aspects.

Hybrid deep learning with pelican optimization algorithm for M2M communication on UAV image classification

<p>Machine-to-machine (M2M) communication for unmanned aerial vehicle (UAVs) and image classification is essential to current remote sensing and data processing. UAVs and ground stations or other linked devices exchange information seamlessly using M2M communication. M2M connectivity helps UAVs with cameras and sensors communicate aerial pictures in real time or post-mission for image categorization and analysis. During flight, UAVs acquire massive volumes of picture data. Image classification, commonly using deep learning (DL) methods like convolutional neural network (CNN), automatically categorizes and annotates photos based on predetermined classes or attributes. This work uses UAV photos to produce hybrid deep learning with pelican optimization algorithm for M2M communication (HDLPOA-M2MC). HDLPOA-M2MC automates UAV picture class identification. GhostNet model is used to derive features in HDLPOA-M2MC. The HDLPOA-M2MC approach leverages pelican optimization algorithm (POA) for hyperparameter adjustment in this investigation. Finally, autoencoder-deep belief network (AE-DBN) model can classify. The HDLPOA-M2MC method’s enhanced outcomes were shown by several studies. The complete results showed that HDLPOA M2MC performed better across measures.</p>

Toward a dynamic national transportation noise map: Modeling temporal variability of spectral traffic noise emission levels.

The National Transportation Noise Map predicts time-averaged road traffic noise across the continental United States (CONUS) based on annual average daily traffic counts. However, traffic noise can vary greatly with time. This paper outlines a method for predicting nationwide hourly varying source traffic sound emissions called the Vehicular Reduced-Order Observation-based Model (VROOM). The method incorporates three models that predict temporal variability of traffic volume, predict temporal variability of different traffic classes, and use Traffic Noise Model (TNM) 3.0 equations to give traffic noise emission levels based on vehicle numbers and class mix. Location-specific features are used to predict average class mix across CONUS. VROOM then incorporates dynamic traffic class mix data to obtain dynamic traffic class mix. TNM 3.0 equations then give estimated equivalent sound level emission spectra near roads with up to hourly resolution. Important temporal traffic noise characteristics are modeled, including diurnal traffic patterns, rush hours in urban locations, and weekly and yearly variation. Examples of the temporal variability are depicted and possible types of uncertainties are identified. Altogether, VROOM can be used to map national transportation noise with temporal and spectral variability.

Comparison and evaluation of YOLO models for vehicle detection on bicycle paths

<p>Non-permitted vehicles have taken over bicycle lanes in various Latin American cities as an alternative escape from traffic. Still, they do not foresee the risk to which they expose users of smaller vehicles, such as cyclists. Technological advancement has made researchers use deep learning (DL) to solve various problems in a city's traffic. However, no research has been found focusing on any issue of vehicles allowed or prohibited to travel on a bicycle lane. Therefore, in this article, the you only look once (YOLO) algorithm was used, taking the lightest models from the YOLOv4 to the most recent version, YOLOv8, to detect 05 classes of vehicles that transit or interfere in a bicycle lane, such as bicycles (Bi), motorcycles (Mo), electric motorcycles (ME), electric scooters (SE) and motorcycle cabs (Mt). When testing with the test images, the YOLOv8m model in 50 epochs, using a batch size of 32 and SGD optimizer, was the most optimal, obtaining F1 results with 88.00%, mAP@0:50 of 94.80% and mAP@0.50:0.95 of 76.60%, also had a training time of 1:28h using a Nvidia T4 GPU from Google Colab.</p>

Air Vehicle Classification System and Speed Alert for the Prevention of Accidents on Flat and Curved Roads

Air Vehicle Classification System and Speed Alert for the Prevention of Accidents on Flat and Curved Roads

Electric light-duty vehicles have decarbonization potential but may not reduce other environmental problems

Electric vehicles are promoted as ‘clean’ technologies and offer promising reductions in transportation emissions. Nevertheless, their environmental benefits critically depend on the local electricity grid mix and the type of emission being considered. Here, we conduct a comparative life cycle assessment of the four dominant light-duty vehicle categories at both the global scale and in three representative countries: Norway, the US, and China. By analyzing different environmental indicators, particularly global warming potential and respiratory effects, and quantifying related parametric uncertainties, we reveal that the advantages of electric vehicles vary across these regions and across environmental impact types. While electric vehicles offer considerable decarbonization potential as the grid mix becomes cleaner, they might not mitigate other environmental impacts, such as increased respiratory effects on rural, low-income communities. Our results support stakeholders in identifying environmentally friendly vehicle and policy options while considering multiple factors, and emphasize the importance of tailored approaches over one-size-fits-all solutions in sustainable transportation.

Energy harvesting potential for 3 EVs equipped with PV for the area of Graz in Austria

Vehicle-integrated photovoltaics present a plausible solution to address electric vehicle barriers of limited charging access and driving ranges. This work demonstrates a simulation tool that encompasses influencing factors on a vehicle's PV yield by comparing geographical areas, vehicle classes, vehicle surfaces, weather conditions, driving/parking cycles, shading scenarios, and electric configurations. The results quantify the increase in battery energy and vehicle mileage. Extensive simulations show the roof is the primary zone for PV integration, whereas the doors contribute greatly in winter. Using high-efficiency PV modules on the roof can supply over 20 % of monthly mileage from March to September. On average, 25 % of 1000 km monthly mileage can be covered with full-vehicle PV coverage. This drops to 16 % when excluding PV doors. This technology's success centers on lightweight vehicles with large surfaces and high-efficiency modules exceeding 20 %. Simulations show that a 10 % increase in efficiency reduces charging energy needs by 12–16 %.

Classification of Unmanned Aerial Vehicles Based on Acoustic Signals Obtained in External Environmental Conditions.

Detection of unmanned aerial vehicles (UAVs) and their classification on the basis of acoustic signals recorded in the presence of UAVs is a very important source of information. Such information can be the basis of certain decisions. It can support the autonomy of drones and their decision-making system, enabling them to cooperate in a swarm. The aim of this study was to classify acoustic signals recorded in the presence of 17 drones while they hovered individually at a height of 8 m above the recording equipment. The signals were obtained for the drones one at a time in external environmental conditions. Mel-frequency cepstral coefficients (MFCCs) were evaluated from the recorded signals. A discriminant analysis was performed based on 12 MFCCs. The grouping factor was the drone model. The result of the classification is a score of 98.8%. This means that on the basis of acoustic signals recorded in the presence of a drone, it is possible not only to detect the object but also to classify its model.

Immersion and Invariance-Based Linear Tracking and Regulation Controller for Depth Position of an AUV

This paper addresses the tracking control challenge in the diving motion system of a specific class of autonomous underwater vehicles (AUVs) characterized by a torpedo-like shape. A decoupled and reduced-order three degrees-of-freedom linearized diving motion model is employed for depth position control. A control law is synthesized using the immersion and invariance (I&I) technique to achieve the control objectives. The primary aim is to attain tracking by immersing a stable, lower-order target (second-order) dynamic system into a three-dimensional manifold, upon which the closed-loop system evolves. We address the regulation problem as a specialized instance of the tracking problem, with the reference input set as a predetermined known depth that requires regulation. The efficacy of the proposed control law is evaluated through simulation studies involving various scenarios. Robustness tests are conducted to assess the control law’s performance under modeling uncertainties and underwater disturbances. The computer simulation employs an AUV named MAYA, utilizing experimentally validated diving motion parameters. A comparative analysis is performed between the proposed control law and other benchmark controllers to gauge its performance. Additionally, the effectiveness of the proposed control law is confirmed by validating its application to the nonlinear model of the diving motion system.

Impact assessment of future fleet compositions in vehicle emissions in urban areas: A methodological framework and a case study

This study explores the impact of emerging vehicle technologies on direct urban traffic emissions. It investigates emission reduction potential from shifts in fleet compositions and modal choices, especially considering climate change. To achieve this, three key research areas are explored for historical, current, and future scenarios (up to 2050): mode choice, emission factors for different vehicle categories, and diverse vehicle propulsion technologies. The estimation of the modal split is pivotal, developing a methodology utilizing Stated Preference survey data, discrete choice modeling, Monte Carlo simulations, and macroscopic traffic simulations. Future scenarios derive from the reference year’s modal split, and emission factors and fleet compositions are predetermined via an extensive literature review, aiding the assessment of their respective emissions. A subsequent sensitivity analysis identifies the impact of specific parameters on emissions, guiding future research focus. Study results underscore differences in greenhouse gas emissions and primary air pollutants between base and future scenarios.

Regulatory challenges in modernizing toll road transaction systems in Indonesia

The Government of Indonesia has modernized the toll road transaction system by implementing the multi-lane free-flow (MLFF) project, set to operate commercially by the end of 2024. This project leverages Global Navigation Satellite System (GNSS) technology to identify vehicles using toll roads and establish a transaction mechanism that allows the MLFF Project Company to charge road users according to distance, vehicle category, and tariff levels. The project has result in a complex business arrangement between the Indonesia National Toll Road Authority (INTRA), Toll Road Companies (TRCs), and the MLFF Project Company. The aim of this paper is to review the regulatory and institutional framework of the MLFF project and analyze its challenges. The methodology employed is a qualitative framework for legal research, utilizing international literature reviews and current regulatory frameworks. The study assesses the proposed transaction architecture of the project and identifies commercial, political, and other risks associated with its implementation. Based on the analysis, the research identifies opportunities for regulatory improvements and better contracting arrangements. This research provides valuable insights into the regulatory landscape and offers policy recommendations for the Government to mitigate the identified risks. This contribution is significant to the academic field as it enhances understanding regulatory and institutional challenges in implementing advanced toll road systems.

E-Mobility Revolution: Examining the Types, Evolution, Government Policies and Future Perspective of Electric Vehicles

: Electrification is a suitable method for establishing a transportation system that is both clean and energy-efficient, addressing environmental concerns. The transportation industry widely recognizes electric vehicles as a highly promising green technology that can reduce carbon emissions and energy consumption. Besides, electric vehicles are defined as vehicles that can be externally charged and propelled by an electric motor powered by a battery. Moreover, an electric vehicle consists of two distinct types: firstly, an all-electric vehicle, which relies exclusively on battery power to move an electric motor, and secondly, plug-in hybrid electric vehicles. This study aims to provide a comprehensive understanding of electric vehicles by covering four key aspects: types of electric vehicles, the history of electric vehicles, government policies related to electric vehicles, and future prospects of electric vehicles. This paper first discusses the basic types of electric vehicles. Through a comprehensive analysis of several categories of electric vehicles, their distinct characteristics, and their advantages, research enables individuals to make well-informed decisions when contemplating sustainable transportation alternatives. After that, a brief history of electric vehicles is discussed. Documenting the historical evolution of electric vehicles provides context for understanding the technological advancements, challenges, and milestones achieved in the development of electric vehicles over time. After that, Indian government policies related to electric vehicle promotion are discussed. Consequently, this encompasses various incentives, subsidies, initiatives for infrastructure development, and other policy measures with the objective of fostering the use of electric vehicles. Lastly, future prospects of electric vehicles are discussed.

Mechanistic Fatigue Performance Evaluation of Stone Mastic Asphalt Mixtures: Effect of Asphalt Performance Grade and Elastic Recovery.

This study evaluates the crack performance of stone mastic asphalt (SMA) mixtures according to the performance of a modified asphalt binder, evaluated based on the asphalt performance grade (PG) and the elastic recovery of multiple stress creep and recovery (MSCR) according to AASHTO M 320 and T 350. The cracking performance of the mixture was evaluated using the asphalt mixture performance tester (AMPT) according to AASHTO T 378 and T 400 through dynamic modulus and direct tension cyclic fatigue tests. Furthermore, the recently developed viscoelastic continuum damage (VECD) theory was utilized to evaluate the cyclic fatigue index parameter (apparent damage capacity, Sapp) and the permissible heavy vehicle class. For performance evaluation, six modified asphalt mixtures were prepared and tested using SMA aggregate gradation with a nominal maximum aggregate size (NMAS) of 10 mm. The MSCR test results revealed that, of the six asphalt mixtures, the rubber-based PG76-28 exhibited the least initial strain and the highest elastic recovery. The dynamic modulus test results demonstrated that using a rubber-based modifier increased the elastic modulus at high temperatures and decreased it at low temperatures, thereby enhancing resistance to plastic deformation in the summer and reducing low-temperature cracking in the winter. Finally, the correlation between the Sapp performance index and the elastic recovery of modified asphalt and the number of direct tension cyclic loads until failure of the mixture was evaluated as 0.87 and 0.76, respectively.

Radar Powered Perception: Multiple Approaches for Vehicle Classification

The proliferation of Advanced Driver-Assistance Systems (ADAS) and autonomous vehicles demands robust and reliable techniques for vehicle detection and classification. This paper investigates the potential of automotive radar systems for this critical task, focusing on classifying vehicles into three distinct categories (bus/truck, car/sedan/SUV, bike/bicycle). We explore multiple approaches that leverages rich set of features extracted from radar measurements. These features include target size, point density, and other signature characteristics derived from the radar return signal. By analyzing these features, we explain multiple approach aims to achieve vehicle classification. The effectiveness of the proposed method is evaluated using real-world data, with a particular focus on demonstrating its suitability for real-time applications in ADAS. The paper delves into the critical trade-offs that exist between classification accuracy, computational complexity, and inherent limitations of automotive radar sensors. We discuss the impact of sparse data, such as low point cloud data on classification accuracy. Additionally, we discuss on potential mitigation strategies to ensure reliability in challenging scenarios. Finally, the paper concludes by outlining potential future directions for enhancing vehicle classification using automotive radar systems. These advancements will pave the way for the development of more robust and reliable ADAS and autonomous vehicles, ultimately contributing to improved safety on our roads.

Real-Time Vehicle Classification Using LSTM Optimized by Oppositional-Based Wild Horse Optimization

Real-Time Vehicle Classification Using LSTM Optimized by Oppositional-Based Wild Horse Optimization

Comfort in Automated Driving: A Literature Survey and a High-Level Integrative Framework

The advancement of automated vehicle technology and the resulting shift from active driver control to a more passive role introduce previously unexplored factors that influence drivers' comfort. Examples include the vehicle's level of automation and the driver's preferred driving style, trust in the vehicle, and situation awareness. To structure these as a resource that can support future research, we conducted a comprehensive literature review, identifying 51 works that directly or peripherally address comfort in an automated driving context. Most of these works focus on the physical component of comfort, rooted in vehicle dynamics, while only a few consider a broader concept of comfort necessary to encompass a more expansive set of factors. Based on this review, we propose an integrative framework of 27 comfort influencing factors and their interrelationships. We categorize factors into six groups, encompassing the driving environment, vehicle physical features and automation system, and the user's activity, individual characteristics, and understanding of the automated system. These six groups are organized into the three larger categories of environment, vehicle, and user-related considerations. Patterns that emerge from the framework include that: a) some factors primarily influence physical well-being (such as motion forces), b) some contribute to discomfort (automation failures) while others contribute to comfort (secondary activities), c) some are stable and known before the trip (individual characteristics) while others change over time (environment), and d) comfort or discomfort can lead users to change either the relevant factors (level of automation) or their own behavior (secondary activities).

Proposed Index for Assigning an Environmental Label to Passenger Cars

At present, the classification of vehicles by means of the environmental label aims to positively distinguish the most environmentally friendly vehicles and to be an effective instrument at the service of municipal policies, both to restrict traffic during high pollution periods and to promote new technologies through tax benefits and other incentives related to mobility and the environment. However, there is a great deal of controversy about the awarding of this environmental label, since it is basically based only on the year of manufacture of the vehicle and the type of fuel it uses, without taking into account many other factors that influence the environmental characterization of a vehicle. This paper presents a proposal for an index to characterize passenger cars from an environmental point of view, considering other additional factors, such as tire wear and particulate emissions during braking. The proposed index is applied to a series of passenger cars representative of the segments currently present in the Spanish market. The index considers seven vehicle parameters. Up to three cases with different parameter weights are analyzed. This index provides greater discrimination of the environmental performance of vehicles than the current eco-labeling system, in each of the three cases studied.

Classification, military applications, and opportunities of unmanned aerial vehicles

Unmanned aerial vehicles (UAVs) are cutting-edge technologies used for military purposes world-wide at tactical, operational, and strategic levels. This study provides an overview of the history and current state of military drones, considering a global and Ecuadorian background. Then, a classification of the UAVs developed and built in Ecuador is conducted based on their endurance, altitude, and wing span to understand the national context and progress. The research also delves into the applications of UAVs in several military operations and missions, aiming to create a framework that aligns UAV capabilities with specific operational needs; this permits the identification of the challenges and opportunities the country faces. Unmanned aerial systems have changed the battlefield, and the government needs to adapt to a national strategy that incorporates this technology; this research analyzes and provides insights to improve military capabilities such as exploring modern UAV military applications, technical updates in communication, navigation, and data acquisition systems; and the integration of emerging technologies like smart materials, artificial intelligence, and electric propulsion systems. This study provides valuable insights into the Ecuadorian UAVs that enhance the country’s military operations and offer some applications and uses of this technology for national security.

LiVeR: Lightweight Vehicle Detection and Classification in Real-Time

Detection of vehicles and their classification is a significant component of wide-area monitoring and surveillance, as well as intelligent- transportation . Existing solutions tend to employ heavy-weight infrastructure and costly equipment, as well as largely depend on constant support from the cloud through round-the-clock internet connectivity and uninterrupted power supply. Moreover, existing works mainly concentrate on localized measurement and do not discuss their efficient integration to address the problem over a wide area. For practical use in an outdoor environment, apart from being technically sound and accurate, a solution also needs to be cost-effective , lightweight , easy to install , flexible , low overhead , and easily maintainable , as well as self-sufficient as much as possible. However, fulfilling all these goals together is a challenging task. In this work, we propose an IoT-assisted strategy, LiVeR , to accomplish it. For self-sufficient on-the-fly classification in resource-constrained low-power IoT devices, LiVeR minimizes not only the computational requirements but also the energy consumption, which enables sustained operation in a hostile outdoor environment for a considerably long time solely based on battery power. Through extensive studies based on outdoor measurement and trace-based simulation on empirical data, we demonstrate that LiVeR classifies vehicles of small, medium, and large size with an accuracy of 91.3% up to 98.8%, 92.3% up to 98.5%, and 93.8% up to 98.8%, respectively, for single-lane traffic. We also demonstrate that LiVeR spends only about one-third of the number of RF packets to achieve vehicle detection and classification compared to the state-of-the-art RF-based solution, considerably extending the lifetime of the system.