Advanced Driver Assistance Systems Research Articles

Enhancing road image clarity with residual neural network dehazing model

Lane markers, or road markers, are the painted lines on a roadway that separate different lanes of traffic. Lane markers guide drivers and ensure orderly vehicle flow. They are essential for advanced driver assistance systems (ADAS), providing reference points for vehicle positioning on the road. These markers enable ADAS to give warnings, assistance, and automation features that enhance driver safety and convenience. However, unpredictable illumination, such as a foggy environment, can suppress marker visibility, impacting ADAS's performance. Deep learning-based methods are well-known for their superiority in handling various haze patterns. This paper presents a residual network (ResNet)-based deep learning model to improve road image clarity impacted by fog. The residual neural network dehaze model (RNN-D) utilises a joint loss function to produce haze-free images with improved lighting conditions and enhanced details. The model was trained, validated, and fine-tuned using hazy and corresponding non-hazy datasets to ensure that the model is quantitatively superior in the peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM). RNN-D achieved an average PSNR of 27.98 and SSIM of 0.8 on multiple open sourced datasets. The proposed algorithm's superior performance and visually appealing results make it a powerful tool for real-world image dehazing applications.

A Comprehensive Review of Autonomous Driving Algorithms: Tackling Adverse Weather Conditions, Unpredictable Traffic Violations, Blind Spot Monitoring, and Emergency Maneuvers

With the rapid development of autonomous driving technology, ensuring the safety and reliability of vehicles under various complex and adverse conditions has become increasingly important. Although autonomous driving algorithms perform well in regular driving scenarios, they still face significant challenges when dealing with adverse weather conditions, unpredictable traffic rule violations (such as jaywalking and aggressive lane changes), inadequate blind spot monitoring, and emergency handling. This review aims to comprehensively analyze these critical issues, systematically review current research progress and solutions, and propose further optimization suggestions. By deeply analyzing the logic of autonomous driving algorithms in these complex situations, we hope to provide strong support for enhancing the safety and reliability of autonomous driving technology. Additionally, we will comprehensively analyze the limitations of existing driving technologies and compare Advanced Driver Assistance Systems (ADASs) with Full Self-Driving (FSD) to gain a thorough understanding of the current state and future development directions of autonomous driving technology.

Dynamic inferences of crash risks in freeway merging zones: a spatio-temporal deep learning model

Freeway merging zones are critical for freeway operations and management due to potential crashes arising from complex vehicle merging behaviours. This paper investigates the application of a spatio-temporal deep learning model to infer crash risks in the zones. We first introduce a crash risk index based on Time-To-Collision and vehicle merging patterns. An innovation is that the developed spatio-temporal transformer model can analyze the evolving risk index. This model effectively captures dynamic risk features through a multi-head attention mechanism within its spatio-temporal learning components. Numerical experiments on nine inference tasks with varying spatial resolutions show improved performance of the model with lower resolution. Moreover, the ST-Transformer model is benchmarked against three advanced deep learning models, which consistently demonstrates its superiority in capturing spatio-temporal dependence in risk sequences. This investigation significantly contributes to a richer understanding of proactive traffic safety, providing valuable insights for advanced freeway management and driver assistance systems.

Understanding Elderly Drivers’ Perception of Advanced Driver Assistance Systems: A Systematic Review of Perceived Risks, Trust, Ease of Use, and Usefulness

Background: Elderly drivers often face safety challenges due to age-related declines in cognitive, sensory, and motor functions. Advanced Driver Assistance Systems (ADAS) offer a potential solution by enhancing safety and mobility. Objectives and method: This systematic review investigates the factors influencing the perception and usage of ADAS among elderly drivers, focusing on perceived safety, usefulness, trust, and ease of use. Results: Older adults show a preference for Level 1 ADAS, which they perceive as safer. Although they acknowledge the usefulness of ADAS in supporting their autonomy, skepticism remains regarding higher-level systems, primarily due to concerns about reliability and invasiveness. Trust and ease of use are essential factors influencing their acceptance. The review identifies common themes and barriers to the adoption of these technologies and emphasizes the need for senior-friendly interfaces and targeted training. The findings indicate that addressing these issues can significantly improve the safety and mobility of elderly drivers. The successful adoption of ADAS among older adults depends on balancing safety, control, and ease of use, with gradual and supportive integration fostering greater acceptance and trust. Conclusions: This study outlines practical implications for stakeholders, emphasizing the need for user-friendly ADAS design, public awareness campaigns, government incentives, insurance discounts, and community training to enhance adoption among older drivers.

Predictive Analytics in ADAS Development: Leveraging CRM Data for Customer-Centric Innovations in Car Manufacturing

The rapid evolution of Advanced Driver Assistance Systems (ADAS) has transformed the automotive landscape, necessitating a shift towards more customer-centric development strategies. This paper explores the integration of predictive analytics with Customer Relationship Management (CRM) data to foster innovations in ADAS development. By harnessing insights from customer interactions, preferences, and feedback, manufacturers can anticipate market demands and tailor ADAS features to enhance user experience. Through a comprehensive analysis of case studies and industry practices, we demonstrate how predictive analytics can improve decision-making processes, facilitate the identification of emerging trends, and optimize resource allocation. The findings underscore the potential of leveraging CRM data to drive customer- focused innovations, ultimately resulting in enhanced vehicle safety, satisfaction, and competitive advantage in the automotive sector.

Informer-FDR: A short-term vehicle speed prediction model in car-following scenario based on traffic environment

Drivers’ car-following behaviors on urban roads are influenced by various factors, including pedestrians, cyclists, adjacent vehicles, and roadside parking. However, few models consider these factors’ influence on drivers’ speed selections during car-following, limiting the human-like driving capability of advanced driver assistance systems (ADAS). This paper proposes a vehicle speed prediction model in car-following scenario that considers the influences of the traffic environment. The vehicle speed is predicted using Informer-FDR (Informer with fusion features, dilated causal convolution, and residual connection), which adopts an improved encoder-decoder structure based on the Informer model. Fusing features of traffic environment characteristics and vehicle dynamics parameters enables the dynamic interaction characteristics between drivers and the traffic environment and potential traffic conflicts to be effectively reflected, which enhances the model’s understanding of the complex driving environment. Moreover, the high computational complexity is reduced by using the ProbSparse self-attention mechanism, which will help to address the difficulty of applying Transformer class models to on-board platforms. Totally 3,980 car-following cases were extracted from naturalistic driving data (NDD), vehicle dynamics parameters and traffic environment characteristics in the car-following scenarios were obtained through target detection and ranging algorithm. The optimal feature set was mined using the combined feature selection method. The dilated causal convolution and average pooling layer are introduced to expand the receptive field of the model, enhance global feature extraction, and ensure the causality of temporal predictions. Furthermore, the residual connection was added to the encoder, realizing the direct deep transfer of cross-layer information. Verifications on the test set show that Informer-FDR has the lowest MAE (0.583), MSE (2.942), RMSE (1.715), and the highest speed prediction accuracy (97.76%), spacing gap accuracy (94.27%), acceleration accuracy (95.35%), which outperforms other baseline models in terms of prediction performance. The ablation study confirms the importance of the improved distilling layer module, residual connection module, and fusion features for predictive performance improvement. Additionally, the road-type experiment reveals performance differences of the model on different road types, emphasizing the importance of incorporating traffic environment on urban road.

Traffic Light Detection using Ensemble Learning by Boosting with Color-Based Data Augmentation

Recent advancements in deep neural networks have significantly improved the detection and recognition of traffic lights for advanced driver assistance systems (ADAS). Traditional methods often rely on identifying traffic light boxes and then recognizing individual signal lights, which can be problematic due to variations in bulb arrangements across different regions. To address this limitation, we propose a novel traffic light detection method that directly recognizes individual signal lights. Our two-stage approach combines data augmentation and ensemble learning to achieve high detection rates. By learning color characteristics from validation sets, we can effectively identify signal light candidates with a 97.26% accuracy rate. Subsequent classification results in a recognition accuracy of 98.6%, surpassing the performance of existing state-of-the-art traffic light detection algorithms. Code and dataset are available at https://github.com/981124/yolov7_traffic_light_detect.

New insights into factors affecting the severity of autonomous vehicle crashes from two sources of AV incident records

Superior safety is the main banner value of promoting autonomous vehicle (AV) technology, but it is difficult to responsibly claim it. The potential for AVs to reduce crash and injury risks would be overshadowed by technological limitations, regardless of their ability to mitigate or eliminate human error. This study aims to identify the key factors affecting crash severity by analyzing real-world AV crash data from the U.S. between 2015 and 2022. We integrated two open data sources from the California DMV and NHTSA. Mixed multinomial logit models incorporating the interaction effects were estimated using the crash severity level, addressing the observed and unobserved heterogeneities. Our results show that Advanced Driver Assistance System (ADAS) engagement is associated with a higher likelihood of slight injury crashes, whereas Automated Driving System (ADS) engagements show the opposite effect. In addition, we found that various environmental and road factors, including lighting conditions, weather, road type, and road surface conditions, significantly affect the severity of AV crashes. For instance, daylight conditions contribute to a lower likelihood of slight-injury crashes. On the other hand, driving under unfavorable weather conditions (cloudy, foggy, rainy, or snowy), on the highway, and on non-dry road surfaces are associated with an increase in the likelihood of severe injury crashes. Furthermore, several significant interaction effects were revealed. First, the mitigating effect of ADS engagement on the likelihood of slight injury crashes is reduced by the rear-end collision type. Second, the likelihood of slight injury crashes increases when AV interacts with heavy trucks on highways. Third, the likelihood of severe injuries increases when AVs collide with Vulnerable Road Users (VRUs) on urban streets. Overall, this research is expected to provide policymakers and AV manufacturers with valuable insights into AV safety, stressing that addressing the identified factors will lead to improved AV design and control algorithms.

Phase transition in heterogeneous macro continuum model integrating the jerk effect with the mixed traffic flow involving human driving and ADAS vehicles

Vehicles equipped with advanced driving assistance systems (ADAS) can acquire information about preceding and following vehicles, which will have an undeniable impact on the phase transition of traffic flow. Therefore, we establish a new heterogeneous continuum model of traffic flow considering the jerk effect mixed with human driving (HD) and ADAS vehicles. The neutral stability condition associated with the permeability of ADAS vehicle is inferred via stability analysis. According to simulation, shock wave occurs, implying that our model can emerge correct wave propagation trend. Moreover, the simulation of density evolution and flow changes also suggests that an increase in ADAS vehicle penetration and jerk effect can enhance traffic system stability and reduce energy consumption.

Trajectory representation learning with multilevel attention for driver identification

Massive trajectory data has originated from the development of positioning technology. Learning GPS trajectory representation to characterize a driver’s driving style is a challenging task with important applications in many areas, including autonomous driving, auto insurance, advanced driver assistance systems, urban computing, and the internet of things. Few studies have considered the interactions between different factors. In this study, we propose a novel trajectory representation method based on a multilevel attention mechanism (ATTraj2vec) and apply it to the task of driver identification. We use 1D CNN to summarize local features, including motion, spatial and temporal features. Then we utilize a multilevel attention mechanism to extract global features, aggregating the interactions of motion features with temporal and spatial features progressively. Additionally, we adopt multi-loss to optimize our model simultaneously, which consists of a softmax loss for driver classification and Siamese loss for making trajectories from the same driver more similar. Classification experimental results on a real-world automobile trajectory dataset demonstrate that our proposed model significantly outperforms existing baselines. Meanwhile, the proposed method provides significant gains in the trajectory clustering of unseen drivers. The code is available in the repository, https://github.com/limengyuan2021/ATTraj2vec,

Correlation Between Traffic Locus of Control and Advanced Driver Assistance System (ADAS) Use

Inappropriate use of advanced driver assistance systems (ADAS), such as adaptive cruise control (ACC) and lane keeping assistance (LKA), may cause safety issues. In a driving simulator experiment, we examined how a specific driver characteristic, locus of control in traffic (T-LOC), influences the use of ADAS. It was found that without any ADAS training, the Self dimension of T-LOC, measuring the extent to which one believes they are responsible for their driving safety, was negatively correlated with time spent on secondary tasks after environmental cues became visible indicating a possible need for takeover. Further, with a responsibility-focused training, drivers with higher Self scores tended to take control over faster when necessary. The findings highlight the role of individual differences in the formation of driver behaviors associated with ADAS use. Investigation of other driver characteristics and incorporating them to the design of training paradigms are suggested.

Predictive Models of Brake Reaction and Steering of Police Officers in Critical Driving Situations

Motor vehicle crashes involving police vehicles significantly impact law enforcement officer (LEO) safety, often occurring during high-risk maneuvers like pursuit driving and sudden lane changes. These incidents are exacerbated by LEOs’ interaction with in-vehicle technologies, including Mobile Computer Terminals. Advanced Driver-Assistance Systems (ADAS) could mitigate these risks, though existing ADAS algorithms are not tailored to the unique work demands. To address these challenges, our study develops predictive models for LEO braking and steering in critical situations, based on a driving simulator experiment with police officers. Both braking and steering models were constructed and identified as effective in predicting police officer braking response and steering. The models can be practically applied as part of ADAS systems to deliver warnings at appropriate times, adapting to police officer demands in critical driving situations. Study implications contribute to the wider body of knowledge on surface transportation, occupational safety, and the use of adaptive models.

Securing the vetaverse: Web 3.0 for decentralized Digital Twin-enhanced vehicle–road safety

The rapid evolution of vehicular communication technologies in recent times necessitates robust security measures and enhanced road safety protocols. Integrity of data shared between vehicles, their Digital Twins (DT) and road side units is at stake. Intrusion in these data can potentially lead to misinformation in Advanced Driving Assistance Systems (ADAS) causing serious consequences upon road safety. These include improper detection of drunk driving behaviors. In this domain, Web 3.0 emerges as the overarching approach that can transform security of vehicles and ensure road safety. This paper explores the potential of Web 3.0 and its key enabling technologies to establish a VEhicular meTAVERSE (Vetaverse) utilizing edge-based DTs of the vehicles to process their dynamics shared in real-time, and based on its deep learning models, predict whether the driving behavior is drunk or sober. This Deep Neural Network (DNN) performs these predictions with 96% accuracy. It secures all Vehicle-to-Digital Twin (V2DT) communications via Multichain - a horizontally scaled parallel blockchains platform that tamper proofs each bit of sensor data, and optimizes transaction validation time to leverage vetaverse security. Results reveal that this framework is accurate and computationally lightweight in comparison to existing state-of-the-art, and brings Web 3.0 to the crucial road safety use-case.

Organizing planning knowledge for automated vehicles and intelligent transportation systems

AbstractIntelligent Transportation Systems (ITS) are crucial for developing fully automated vehicles. While significant progress has been made with advanced driver assistance systems and automation technology, challenges remain, such as improving traffic information, enhancing planning and control systems, and developing better decision‐making capabilities. Despite these hurdles, the potential benefits of ITS are so many that its challenges have attracted substantial industrial investment and research groups interested in the automated driving field. In this work, a methodology based on state space search for planning knowledge integration is proposed. The main goal of the proposal is to provide a planning system with the necessary information to perform properly any task related to lateral and longitudinal control, path following, trajectory generation, arbitration and behavior execution by localizing the vehicle with respect to a high‐level road plan. To this end, this research compares cutting‐edge methods for rapidly finding the K nearest neighbor in relatively high dimensional road plans constructed from the traffic information stored in a high definition map. During the experimentation phase, promising real‐time results have been obtained for fast KNN algorithms, leading to a robust tree index‐based methodology for decision making in self‐driving vehicles combining path planning, trajectory tracking, trajectory creation, knowledge aggregation and precise vehicle control.

SMALL OBJECT DETECTION APPROACH BASED ON ENHANCED SINGLE-SHOT DETECTOR FOR DETECTION AND RECOGNITION OF INDONESIAN TRAFFIC SIGNS

The detection and recognition of traffic signs are crucial components of advanced driving assistance systems (ADAS) that enhance road safety. Current traffic sign detection and recognition model technology is proficient in identifying and interpreting traffic signs. However, for accurate detection and recognition, the traffic sign in the image must be of a certain minimum pixel size or distance from the driver's sight line for proper detection. The ADAS system should be capable of detecting and recognizing road traffic signs from a considerable distance as they come into the driver's line of vision. The higher the vehicle speed, the greater the distance required for the sign to be detected and recognized, allowing the driver sufficient time to react according to the sign's meaning. Addressing these challenges, this research proposes an enhanced version of the single shot detector (SSD) algorithm, commonly used in object detection, to improve the algorithm's ability to detect small objects. The proposed method involves adding an auxiliary layer module to the original SSD architecture to increase the feature map resolution and expand the conventional layer's receptive space. With the Enhanced SSD algorithm, the detection capability of the SSD can be significantly enhanced in terms of accuracy. The limitations of this study are related to the influence of occlusion and clutter, which might affect the performance of object detection, especially for small objects, which are more susceptible to being influenced by various factors. The research results demonstrate that Enhanced SSD improves object detection accuracy compared to the original SSD, with a mean average precision (mAP) of 97.87 compared to 95.35 for detecting 21 traffic signs in Indonesia.

Safety Trends in the Automobile Industry in India

The automobile industry in India has experienced significant advancements in recent years, driven by rapid technological innovations and evolving consumer expectations. Safety has emerged as a critical focus area, with stakeholders ranging from government bodies to manufacturers and consumers increasingly emphasizing the need for stringent safety measures. This paper explores the key safety trends shaping the Indian automotive sector, including the adoption of advanced driver-assistance systems (ADAS), the implementation of new crash test standards, and the increased integration of passive and active safety features in vehicles. Additionally, it highlights the regulatory changes brought forth by the Indian government, such as the Bharat New Vehicle Safety Assessment Program (BNVSAP) and mandatory safety norms like airbags and anti-lock braking systems (ABS). The study also examines the role of technological innovations, including connected vehicle technologies and the potential of autonomous driving in enhancing road safety. By analyzing these trends, the paper aims to provide insights into how safety measures in the Indian automobile industry are evolving to meet global standards and reduce the rising number of road accidents in the country.

Depth Video-Based Secondary Action Recognition in Vehicles via Convolutional Neural Network and Bidirectional Long Short-Term Memory with Spatial Enhanced Attention Mechanism

Secondary actions in vehicles are activities that drivers engage in while driving that are not directly related to the primary task of operating the vehicle. Secondary Action Recognition (SAR) in drivers is vital for enhancing road safety and minimizing accidents related to distracted driving. It also plays an important part in modern car driving systems such as Advanced Driving Assistance Systems (ADASs), as it helps identify distractions and predict the driver’s intent. Traditional methods of action recognition in vehicles mostly rely on RGB videos, which can be significantly impacted by external conditions such as low light levels. In this research, we introduce a novel method for SAR. Our approach utilizes depth-video data obtained from a depth sensor located in a vehicle. Our methodology leverages the Convolutional Neural Network (CNN), which is enhanced by the Spatial Enhanced Attention Mechanism (SEAM) and combined with Bidirectional Long Short-Term Memory (Bi-LSTM) networks. This method significantly enhances action recognition ability in depth videos by improving both the spatial and temporal aspects. We conduct experiments using K-fold cross validation, and the experimental results show that on the public benchmark dataset Drive&Act, our proposed method shows significant improvement in SAR compared to the state-of-the-art methods, reaching an accuracy of about 84% in SAR in depth videos.

Simulation of Advanced Driving Assistance Systems for a Dynamic Vehicle Model

Simulation of Advanced Driving Assistance Systems for a Dynamic Vehicle Model

Road target recognition based on radar range-Doppler spectrum with GS – ResNet

ABSTRACT Road target recognition ability of automotive millimetre-wave (mmWave) radar is crucial in areas such as autonomous driving, advanced driver assistance systems (ADAS), and automated emergency braking systems (AEBS). Current mmWave radar systems are primarily utilized for speed, distance, and angle measurements, with limited capability or unsatisfactory performance in target classification. In response to this limitation, this paper proposes a novel method for road target recognition, using radar range-Doppler spectrum as input data and introducing a global attention mechanism and SCConv module. First, the range-Doppler spectrum is processed by the clutter removal algorithm block to remove background clutter and vibration interference. Second, considering the small features and susceptibility to noise interference in the range-Doppler spectrum, we have devised a deep residual network based on a global attention mechanism, significantly enhancing the model’s accuracy in range-Doppler spectrum classification. Finally, we introduce the SCConv module and improve the downsampling module in ResNet to enhance the model’s classification accuracy. Experimental results demonstrate that the model achieves an average accuracy of 99.79% in classifying six types of road targets, significantly outperforming other methods. This research is of significant importance in advancing the understanding of road traffic conditions by autonomous driving systems and enhancing system safety.

Enhancing Autonomous Driving Safety: A Robust Stacking Ensemble Model for Traffic Sign Detection and Recognition

Accurate detection and classification of traffic signs play a vital role in ensuring driver safety and supporting advancements in autonomous driving technology. This paper introduces a novel approach for traffic sign detection and recognition by integrating the Faster RCNN and YOLOX-Tiny models using a stacking ensemble technique. The innovative ensemble methodology creatively merges the strengths of both models, surpassing the limitations of individual algorithms and achieving superior performance in challenging real-world scenarios. The proposed model was evaluated on the CCTSDB dataset and the MTSD dataset, demonstrating competitive performance compared to traditional algorithms. All experiments were conducted using Python 3.8 on the same system equipped with an NVIDIA GTX 3060 12G graphics card. Our results show improved accuracy and efficiency in recognizing traffic signs in various real-world scenarios, including distant, close, complex, moderate, and simple settings, achieving a 4.78% increase in mean Average Precision (mAP) compared to Faster RCNN and improving Frames Per Second (FPS) by 8.1% and mAP by 6.18% compared to YOLOX-Tiny. Moreover, the proposed model exhibited notable precision in challenging scenarios such as ultra-long-distance detections, shadow occlusions, motion blur, and complex environments with diverse sign categories. These findings not only showcase the model’s robustness but also serve as a cornerstone in propelling the evolution of autonomous driving technology and sustainable development of future transportation. The results presented in this paper could potentially be integrated into advanced driver-assistance systems and autonomous vehicles, offering a significant step forward in enhancing road safety and traffic management.