Vehicle Segmentation Research Articles

Technological progress: Interconnectedness, innovation systems, and technology delivery systems the case of Indian electric vehicles

The electric vehicle (EV) technological supply chain progresses when demand (pull) aligns with supply (push) to perform as a technology delivery system. Actors, institutions, and networks interconnect the technological supply chain with innovation as responses to external pressures to produce and deliver technology products/services. The literature separately examined the progress from a delivery perspective (linking the demand and supply network) and a systems perspective that examines technological change as a socio-technical system. Technological progress requires changes aligning push and pull or one feeding into the other. The ‘motors of innovation’ that shape the innovation system are used in systems dynamics modeling linking technological changes and progress. This study uses ‘motors of innovation’ to combine the two perspectives and uses interconnectedness to examine the alignment of push and pull and the resulting delivery phenomena. The phenomena require studying it in its settings with diverse heuristic and analytic views. Therefore, this study uses case study methodology and selects multiple Indian EV cases comprising all vehicle segments in a government direct market scenario. It makes two contributions to technological progress: one defines the combined delivery and systems perspective and includes interconnectedness. The other is moving knowledge to a broad scope and expertise and striving for interconnectedness with other systems. Further insights are possible with cases that display better technological progress, as findings noted poor interconnectedness with limited technological capability and infrastructure.

Lightweighting cost impacts on market adoption and GHG emissions in U.S. light-duty vehicle fleet

Abstract Vehicle lightweighting is a promising strategy that can reduce energy consumption and GHG emissions without compromising vehicle’s performance or size. The cost of lightweighting plays a critical role in determining the adoption of lightweighting technologies by consumers and manufacturers among advanced vehicle technologies. This analysis estimates the cost of lightweighting needed to achieve significant light-duty vehicle adoption to provide reductions in GHG emissions. Three different costs of lightweighting scenarios in the U.S. market including a baseline scenario, advanced technology scenario, and widespread scenario are evaluated employing Automotive Deployment Options Projection Tool (ADOPT). ADOPT leverages a database of over 700 existing vehicle models and options, enabling it to provide a high degree of realism and capture the unique characteristics of popular vehicles and the endogenously evolvement of the vehicle options. For baseline scenario, the lightweighting fraction reached by about 15% and GHG emissions are reduced by more than 50% in 2046 compared to 2015. The widespread scenario further reduces the GHG emissions by about 4% from the additional 10% glider mass reduction compared to the baseline scenario. The benefit came largely from lightweighting being implemented in the large market segment of lower-price vehicles, due to the relatively low lightweighting cost ($5/kg).

Trajectory optimization for the diving segment of air-breathing supersonic vehicle with multi-objective

Abstract Aiming at the trajectory optimization problem of the dive section of the supersonic vehicle under the comprehensive action of different objective functions, a trajectory optimization design method for multi-optimization objectives of air-breathing supersonic vehicles is proposed. The hp adaptive pseudo-spectrum method is used to optimize the dive trajectory of an air-breathing supersonic vehicle with the maximum flight range and maximum landing velocity under the conditions of process constraints such as overload and dynamic pressure by the weighted summation method. It is proved that this method can solve the comprehensive optimization problem of multiple optimization objectives effectively and provides a new thought for the optimization of related fields.

The Impact of the Bursting New Energy Vehicle Market on the Traditional Fuel Vehicle Industry - The Case of Audi

The automotive industry is facing an era of change against the backdrop of escalating environmental concerns and a global shift towards sustainable transportation. This thesis focuses on the impact of the emerging New Energy Vehicle (NEV) market on Audi, a stalwart of the traditional fuel vehicle segment. The purpose of this study is to assess how Audi is responding to this transition, with particular emphasis on its strategy of embracing electrification in the face of increased competition and changing consumer preferences. Through a comprehensive literature review, analysis of Audi's financial reports and sales data, this study provides insights into Audi's investment in electrification, the pace of model launches, and sales of hybrid and all-electric vehicles. The data for this study was obtained from official Audi publications, industry reports, and relevant academic articles. The findings show that Audi has made significant progress in adapting to the new energy vehicle market, as evidenced by significant investment in electric vehicles, an expanding portfolio of electric models, and sales growth in key markets.

Combining dual attention mechanism and efficient feature aggregation for road and vehicle segmentation from UAV imagery

Unmanned aerial vehicles (UAVs) have gained significant popularity in recent years due to their ability to capture high-resolution aerial imagery for various applications, including traffic monitoring, urban planning, and disaster management. Accurate road and vehicle segmentation from UAV imagery plays a crucial role in these applications. In this paper, we propose a novel approach combining dual attention mechanisms and efficient multi-layer feature aggregation to enhance the performance of road and vehicle segmentation from UAV imagery. Our approach integrates a spatial attention mechanism and a channel-wise attention mechanism to enable the model to selectively focus on relevant features for segmentation tasks. In conjunction with these attention mechanisms, we introduce an efficient multi-layer feature aggregation method that synthesizes and integrates multi-scale features at different levels of the network, resulting in a more robust and informative feature representation. Our proposed method is evaluated on the UAVid semantic segmentation dataset, showcasing its exceptional performance in comparison to renowned approaches such as U-Net, DeepLabv3+, and SegNet. The experimental results affirm that our approach surpasses these state-of-the-art methods in terms of segmentation accuracy.

Projecting future critical material demand and recycling from China's electric passenger vehicles considering vehicle segment heterogeneity

Critical factors like electric vehicle market penetration, battery chemistry, and battery capacity determine future critical material demand and recycling potential from electric vehicles. However, current studies largely ignored the heterogeneity among vehicle segments. This study introduces a vehicle-model-based big-data driven approach to unveil electric vehicle characteristics at fleet-wide and vehicle-segment levels. Further, a bottom-up model was built to project the battery material flow dynamics in 8 scenarios, identifying middle and large vehicle segments as primary contributors. In the Business-As-Usual (BAU) scenario, demand for lithium, nickel, cobalt, and manganese by 2050 will reach 182, 447, 61, and 44 kt, respectively, with recycled materials meeting 59 %, 58 %, 60 %, and 57 % of demand. The demand and recycling of critical materials have significant inherent uncertainty, with demand potentially fluctuating from one-quarter to twice the BAU level. Policies can greatly reduce primary resources for critical materials by guiding battery usage preferences and promoting recycling.

Smart traffic management of vehicles using faster R-CNN based deep learning method

With constant growth of civilization and modernization of cities all across the world since past few centuries smart traffic management of vehicles is one of the most sorted after problem by research community. Smart traffic management basically involves segmentation of vehicles, estimation of traffic density and tracking of vehicles. The vehicle segmentation from videos helps realization of niche applications such as monitoring of speed and estimation of traffic. When occlusions, background with clutters and traffic with density variations, this problem becomes more intractable in nature. Keeping this motivation in this research work, we investigate Faster R-CNN based deep learning method towards segmentation of vehicles. This problem is addressed in four steps viz minimization with adaptive background model, Faster R-CNN based subnet operation, Faster R-CNN initial refinement and result optimization with extended topological active nets. The computational framework uses adaptive background modeling. It also addresses shadow and illumination issues. Higher segmentation accuracy is achieved through topological active net deformable models. The topological and extended topological active nets help to achieve stated deformations. Mesh deformation is achieved with minimization of energy. The segmentation accuracy is improved with modified version of extended topological active net. The experimental results demonstrate superiority of this framework with respect to other methods.

Design Optimization of LCV CAB for Frontal Pendulum Test: Enhancing Survival Space Improvement Through Frugal Load Path Transfer Techniques

In the fiercely competitive landscape of the automotive industry, Original Equipment Manufacturers (OEMs) encounter substantial challenges in the realm of Research and Development (R&D), particularly in the pursuit of lightweight design without compromising safety. As a result, the automotive sector continuously seeks innovative tools and methodologies to substantially optimize the structural composition of Light Commercial Vehicle (LCV) segments. The design of lightweight cabins, while simultaneously ensuring crashworthiness, not only plays a pivotal role in determining the market success of a new LCV but also holds significant legal implications. One well-established and indispensable evaluation tool to ascertain compliance with critical homologation requirements is the frontal pendulum test. This test serves as a litmus test for the appropriate design of Body in White (BIW) architecture, crucial for safeguarding occupant safety in unforeseen emergency scenarios.Within the context of adhering to styling themes and the design intent governing the three-dimensional (3D) geometry, a notable deviation emerged in the form of a 33 mm extension of the front panel in the newly stylized cabin. This deviation presented CAB engineers with a formidable challenge, as it disrupted the conventional load path of the frontal pendulum, rerouting it to the CAB itself instead of the intended transfer to the frame via the bull bar. The primary objective of this work is to restore the load path to the frame, all the while adhering to the original styling intent and refraining from introducing any additional modifications to major adjacent components such as the bumper and bumper reinforcement. Furthermore, this undertaking extends to encompass an exploration of cost reduction opportunities within the ambit of the newly styled CAB.
 Keywords: LCV CAB, Frontal Pendulum, Frugal Load, Occupant safety regulation, Styling impact, Pendulum impact, CAE simulation

Evaluating the Impact of Price Fluctuations on Consumer Buying Decisions and Adaptation Strategies in the Automotive Market

This research paper delves into the intricate dynamics of the U.S. automotive market from 2012 to 2022, with a specific focus on understanding how price fluctuations influence consumer buying decisions and the corresponding adaptation strategies deployed by manufacturers. Through a mixed-methods approach, combining quantitative analysis of sales data, price trends, and economic indicators with qualitative insights from interviews with industry experts and consumers, the study reveals a pronounced shift towards fuel-efficient and electric vehicles (EVs). This shift is primarily driven by consumer sensitivity to price changes and a burgeoning emphasis on environmental sustainability. The findings highlight significant demographic variations in price sensitivity, particularly among younger and middle-income consumers, and delineate the impact of broader economic indicators on purchasing behaviors, especially in the luxury vehicle segment. Manufacturers’ adaptation strategies, including product diversification, investment in sustainable technologies, and flexible pricing models, are also examined. The study’s insights underscore the complex interplay between economic theories of consumer behavior, market adaptation strategies, and the evolving landscape of automotive technology. It offers valuable implications for manufacturers, policymakers, and consumers, aiming to navigate the challenges of market volatility and the transition towards sustainability. The research concludes with recommendations for future studies to explore emerging trends and assess long-term impacts, contributing to a deeper understanding of the automotive market’s adaptive mechanisms in response to economic fluctuations.

Factors Shaping the Future of Leasing in Poland. The Role of External Shocks, Regulations, and Emerging Technologies

Abstract This study aims to identify and evaluate the key trends in the leasing sector in Poland from the perspective of both the present situation and the coming years. The literature review and the conducted In-Depth Interviews among senior executives of leasing businesses in Poland and among representatives of the Polish Leasing Association enabled us to determine the following list of contemporary trends that are relevant to the leasing sector: the circular economy, the sharing economy and product-as-a-service, incidental and shock-related changes, digitalization, automation and robotization, as well as the development of the electric vehicle segment. Furthermore, many of these phenomena fit into the broader concept of so-called sustainable finance. All of the indicated trends were deemed as relevant by the experts. The leasing sector has not yet reached the maximum of its potential for market expansion in Poland.

Robust 3D Semantic Segmentation Method Based on Multi-Modal Collaborative Learning

Since camera and LiDAR sensors provide complementary information for the 3D semantic segmentation of intelligent vehicles, extensive efforts have been invested to fuse information from multi-modal data. Despite considerable advantages, fusion-based methods still have inevitable limitations: field-of-view disparity between two modal inputs, demanding precise paired data as inputs in both the training and inferring stages, and consuming more resources. These limitations pose significant obstacles to the practical application of fusion-based methods in real-world scenarios. Therefore, we propose a robust 3D semantic segmentation method based on multi-modal collaborative learning, aiming to enhance feature extraction and segmentation performance for point clouds. In practice, an attention based cross-modal knowledge distillation module is proposed to effectively acquire comprehensive information from multi-modal data and guide the pure point cloud network; then, a confidence-map-driven late fusion strategy is proposed to dynamically fuse the results of two modalities at the pixel-level to complement their advantages and further optimize segmentation results. The proposed method is evaluated on two public datasets (urban dataset SemanticKITTI and off-road dataset RELLIS-3D) and our unstructured test set. The experimental results demonstrate the competitiveness of state-of-the-art methods in diverse scenarios and a robustness to sensor faults.

Automatic Outer Contour Detection and Quantification of Vehicles Using Monocular Vision

Oversized vehicles have the potential to collide with walls or ceilings when passing through tunnels and bridges, posing a serious threat to the health of transportation infrastructure and public safety. Hence, it is crucial to accurately and immediately detect vehicle dimensions, including length, width, and height, to avoid such accidents. Using computer vision and view geometry, this study presents a framework for automatically detecting and quantifying the outer contours of vehicles through monocular vision. First, traffic scene images are captured which are then used to create a transformation matrix of the ground surface. Second, a modified Mask region-based convolutional neural network (Mask R-CNN) is constructed to detect and segment the vehicle instances from the video frames. Finally, a view geometry-based algorithm was developed to detect the outer contours of passing vehicles and quantify their dimensions. In the field test, the accuracy of the vehicle segmentation and the identified vehicle dimensions was validated. In addition, the proposed method’s superiority was confirmed by comparing it with two other existing approaches. The comparison results show that the proposed method has better accuracy and is more convenient to use since it does not require a premeasured reference. In addition, the developed method can accurately identify not only the dimensions of vehicles parallel to the road but also vehicles that are changing lanes or making a U-turn.

A Comprehensive Review of Electric Vehicle Efficiency Enhancement Through Drive Cycle Optimization: Evaluating its Influence on Electric Range and Longevity

The best driving range for electric cars (EVs) is a major difficulty because this parameter is mostly determined by the amount of energy in the battery pack. However, it is crucial to understand that user behavior and particular driving habits have a significant impact on this range. The necessity for a reevaluation of typical drive cycles, which have grown increasingly out of step with changing customer needs, has been highlighted by recent controversy around the stated range statistics by EV manufacturers. Drive cycles must be modified in accordance with the major variances in driving behaviors across various vehicle segments. In addition, the driving cycle and patterns change across different demographic areas in varied countries like India, creating a special difficulty in the development of a new standard driving cycle that can accommodate a wide range of users. Real-world driving patterns must be taken into account in order to effectively anticipate an EV’s range and evaluate the durability and warranty of its battery pack. The careful selection of a very-specific driving-based realistic profile is therefore crucial for the environment surrounding electric vehicles. We explore the complex process of creating driving profiles particularly designed for electric vehicles in this in-depth review article. We examine the subtleties and traits of these profiles to offer light on their importance in the context of EVs. This assessment provides insightful information on how electric car technology is developing as well as the crucial part that driving styles will play in the development of sustainable transportation in the future.

How to raise consumer awareness of the environmental impact of vehicle attributes? A big data analysis

The introduction of the Euro 7 emission standard is expected to significantly change the typology of the European passenger car. This study analyzes the environmental impact resulting from future trends in fleet composition and proposes an innovative vehicle classification system focused on raising consumer awareness of the importance of their choices with regard to key attributes such as body type, engine power and vehicle weight. A sensitivity analysis of the fleet's greenhouse gas emissions to deviations in their composition is carried out, considering the preferences expressed by the consumers in 2022 and the vehicle's specifications reported by the automotive industry on European digital platforms embodying Industry 4.0 principles. The findings show that internal combustion fleet emissions are expected to rise 0.30% per 1% increase in engine power and 0.44% to 0.69% per 1% increase in weight, according to the Worldwide Harmonised Light Vehicle Test Procedure (WLTP). The plug-in electric vehicle (PHEV) segment is the fastest growing in terms of market share. This trend will continue in the future, as this is the segment best suited to comply with the emissions targets imposed on manufacturers. Another relevant conclusion is that the environmental impact of PHEV vehicles is potentially very negative if the drivers' charging habits do not reflect the manufacturer's design intention. Thus, the development of consumer environmental awareness tools is urgent. This is the study's main motivation: to develop a tool in the scope of the Industry 4.0 while promoting the emergent concept of Industry 5.0, sustainability based and human-centered.

Temporal assessment of emission inventory model for Indian heavy commercial vehicle segment – A top-down approach

Heavy commercial vehicles (HCVs) are pivotal to India's economy but are also significant sources of air pollution. To address this issue, the Indian government implemented Bharat Stage VI (BS-VI) emission standards in 2020. Research gap regarding realistic inputs for annual vehicle kilometres and survival rate of heavy commercial vehicles has been identified. The HCV sector is categorized into long-haul vehicles (32 tonnes and above, with higher annual vehicle usage and survival rates) and pick-up and delivery HCV trucks (16–32 tonnes, with relatively lower annual vehicle usage and survival rates). Based on the primary research by taking into account the inputs from various stakeholders regarding annual vehicle kilometres and survival rates subject to vehicle type and emission standards, an HCV emission inventory for India has been developed for regulated pollutants (NOx, PM2.5, and CO) till 2035. We assume no additional external technological or policy interventions, except the anticipated shift to Bharat Stage VII (BS-VII) standards by 2027. Key findings reveal that the on-road HCV population is projected to marginally increase (6.5%) by 2035 compared to 2020. However, there is a notable 97% surge in goods transport tonnage by 2035, indicating more efficient commercial vehicle usage, especially in the heavier category (32 tonnes and above). Crucially, annual emissions of NOx, PM2.5, and CO from the HCV segment are expected to peak in 2020 and decline significantly by 2035. Emissions are projected to decrease by 91.5% (NOx), 96.6% (PM2.5), and 97.6% (CO) compared to 2020 levels due to the introduction of BS-VI standards in 2020 and the anticipated adoption of BS-VII standards in 2027. This study is instrumental in defining base emission inventory till 2035 for any further policy evaluation for heavy commercial vehicle segment for reducing air pollution and enhancing environmental sustainability.

Towards Safer Highway Work Zones: Insights from Deep Learning Analysis of Thermal Footage

Thermal imaging, when coupled with deep-learning-based analysis, can significantly improve highway work zone management and safety, though data scarcity in this field has been a historical challenge. We collected over 440 hours of thermal footage from highway sites in Massachusetts and New Hampshire and created a vehicle segmentation dataset featuring over 14,000 vehicle instances. We implement effective training strategies for deep learning models and develop algorithms to analyze vehicle trajectories and merging behaviors. Various visualization techniques are illustrated to better understand the extensive analytics data generated for each site, which can lead to development of data-driven strategies to improve Traffic management and safety. GitHub repository: https://github.com/z00bean/SmartWorkZoneControl.

Development of the electric vehicle market in Russia and China

The scientific problem of the energy transition and building a “green” economy remains one of the most pressing both abroad and in Russia. The main directions are the development of environmentally friendly production, achieving carbon neutrality, developing the car market using new energy sources, etc. In this regard, the object of this paper is to conduct a more in-depth study and analysis of the regulation of electric vehicles sales globally, in China and Russia. This article presents a proactive transportation strategy and forecast that prioritizes the expansion of the electric vehicle segment and the technologies used in production in Russia and China. The legal and economic basis for regulating the use of electric vehicles is characterized, and a comparative characterization of production and development of the transport market is made. As the main recommendation, the need to improve Russian transportation legislation with further changes and adjustments to the regulatory framework can be outlined. It seems appropriate to develop a number of additional incentive measures for both manufacturers of electric vehicles and their consumers, providing the emerging market with the necessary service and electric charging infrastructure, which confirms the proposed research hypothesis. The results of the work may be useful to experts and specialists in the field of green energy and transport, government authorities, as well as researchers studying scientific problems of developing environmentally friendly and intelligent electric vehicles.

Role of car segment and fuel type in the choice of alternative fuel vehicles: A cross-nested logit model for the English market

In this article, we study the role of car segment and fuel type in the choice of alternative fuel vehicles and in the prediction of its market. For this purpose, we propose a joint choice cross-nested logit model to understand the demand for alternative fuel vehicles (AFV) and to study substitutional patterns between fuel types and vehicle segments with a full revealed preference approach, using only publicly available real data at disaggregate (household) level in England. Our results show that, as hypothesised, fuel type choice is not independent from car segment choice. The correlation patterns in the chosen specification reveal that individual car alternatives belonging to the same car segment are strongly correlated, while a weaker correlation exists between alternatives from different segments which share the same fuel type. The results suggest that creating awareness for cleaner fuel alternatives might be more effective if a targeted approach that considers these substitutional patterns is used. From a policy standpoint, while purchase prices play an important role and government policies have been concentrated in reducing the gap between ICE vehicles and AFVs in this dimension, our models stress the relevance of the operating cost variable, suggesting that its effect might also be crucial in the purchase decision.

Artificial intelligent systems for vehicle classification: A survey

Digitalization is revolutionizing our way of life and catalyzing the transformation into smart city. Intelligent Transportation System (ITS) being an indispensable component of smart city leverages massive amount of collected information to improve traffic efficiency, thereby creating a safer and comfortable commuting environment for the users. One of the most important tasks in ITS is vehicle classification which aims to find out the vehicle identity, including vehicle segment, automobile maker, model, etc. In this article, we first present the vehicle classification taxonomy branched based on the nature of input data. We subsequently investigate diverse area of sensor-based vehicle classification followed by image-based vehicle classification which cover both the conventional and emerging techniques in a comprehensive manner. The methodologies together with the corresponding strengths and potential weaknesses are elucidated so that it serves as an invaluable reference for vehicle classification related applications in the future. More importantly, we express our views on future research direction with the intention to accelerate the development of vehicle classification field.In contrast to previous works, we aim to cover wide spectrum of vehicle classification methodologies in this review to provide more clarity when it comes to selecting a solution that suits individual need. They include both sensor-based and image-based vehicle classification for VTR, VLR and VMMR. We employ exhaustive coverage approach for the former to identify the extant solutions that are built upon various kinds of sensing technologies and they are further collated according to the installation methods. For image-based methods, we screen for the works that have been central to both pre- and post-deep learning era. The featured works either address the shortcoming of previous works in image domain or present novel concept to advance the classification performance.

Exploring user satisfaction and improvement priorities in electric vehicle segments

This study is the first to explore satisfaction and asymmetry in full- and mini-sized electric vehicles (Mini EVs). An integrated framework, SI Gap-ML-IG (Satisfaction Importance Gap-Machine Learning-Importance Grid), is proposed to identify factor attributes, asymmetric effects, and improvement priorities. The SI Gap reveals a large difference between user perception and expectation. Five machine learning algorithms and a traditional linear regression are then compared, and numerical results show that Random Forest is the most suitable method for predicting overall satisfaction and extracting derived importance. Improvements in noise isolation and actual range are shown to be urgently needed for both EV segments. For Mini EVs, three additional factors—safety, comfort, and purchase subsidy—need improving. For full-size EVs, improvements are needed in delivery time, charging queue time, and purchase price. These findings provide new insights and policy implications for the EV industry and government policymakers.