Search Results (129)

Mind wandering (MW) is a significant safety risk in driving, yet research on its scope, underlying mechanisms, and mitigation strategies remains fragmented across disciplines. In this review guided by the PRISMA framework, we analyze findings from 64 empirical studies to address these factors. The presented study quantifies the prevalence of MW in naturalistic and simulated driving environments and shows its impact on driving behaviors. We document its negative effects on braking reaction times and lane-keeping consistency, and we assess recent advancements in objective detection methods, including EEG signatures, eye-tracking metrics, and physiological markers. We also identify key cognitive and contextual risk factors, including high perceived risk, route familiarity, and driver fatigue, which increase MW episodes. Also, we survey emergent countermeasures, such as haptic steering wheel alerts and adaptive cruise control perturbations, designed to sustain driver engagement. Despite these advancements, the MW research shows persistent challenges, including methodological heterogeneity that limits cross-study comparisons, a lack of real-world validation of detection algorithms, and a scarcity of long-term field trials of interventions. Our integrated synthesis, therefore, outlines a research agenda prioritizing harmonized measurement protocols, on-road algorithm deployment, and rigorous evaluation of countermeasures under naturalistic driving conditions. Full article

Accurately identifying driver fatigue in complex driving environments plays a crucial role in road traffic safety. To address the challenge of reduced fatigue detection accuracy in complex cabin environments caused by lighting variations, we propose YOLO-FDCL, a novel algorithm specifically designed for driver fatigue detection under complex lighting conditions. This algorithm introduces MobileNetV4 into the backbone network to enhance the model’s ability to extract fatigue-related features in complex driving environments while reducing the model’s parameter size. Additionally, by incorporating the concept of structural re-parameterization, RepFPN is introduced into the neck section of the algorithm to strengthen the network’s multi-scale feature fusion capabilities, further improving the model’s detection performance. Experimental results show that on the YAWDD dataset, compared to the baseline YOLOv8-S, precision increased from 97.4% to 98.8%, recall improved from 96.3% to 97.5%, mAP@0.5 increased from 98.0% to 98.8%, and mAP@0.5:0.95 increased from 92.4% to 94.2%. This algorithm has made significant progress in the task of fatigue detection under complex lighting conditions. At the same time, this model shows outstanding performance on our self-developed Complex Lighting Driving Fatigue Dataset (CLDFD), with precision and recall improving by 2.8% and 2.2%, respectively, and improvements of 3.1% and 3.6% in mAP@0.5 and mAP@0.5:0.95 compared to the baseline model, respectively. Full article

Pupil detection is a key technology in fields such as human–computer interaction, fatigue driving detection, and medical diagnosis. Existing pupil detection algorithms still face challenges in maintaining robustness under variable lighting conditions and occlusion scenarios. In this paper, we propose a novel pupil detection algorithm, ViMSA, based on the ViM model. This algorithm introduces weighted feature fusion, aiming to enable the model to adaptively learn the contribution of different feature patches to the pupil detection results; combines ViM with the MSA (multi-head self-attention) mechanism), aiming to integrate global features and improve the accuracy and robustness of pupil detection; and uses FFT (Fast Fourier Transform) to convert the time-domain vector outer product in MSA into a frequency–domain dot product, in order to reduce the computational complexity of the model and improve the detection efficiency of the model. ViMSA was trained and tested on nearly 135,000 pupil images from 30 different datasets, demonstrating exceptional generalization capability. The experimental results demonstrate that the proposed ViMSA achieves 99.6% detection accuracy at five pixels with an RMSE of 1.67 pixels and a processing speed exceeding 100 FPS, meeting real-time monitoring requirements for various applications including operation under variable and uneven lighting conditions, assistive technology (enabling communication with neuro-motor disorder patients through pupil recognition), computer gaming, and automotive industry applications (enhancing traffic safety by monitoring drivers’ cognitive states). Full article

Driver drowsiness is a major contributor to road accidents, often resulting from delayed reaction times and impaired cognitive performance. This study introduces EffRes-DrowsyNet, a hybrid deep learning model that integrates the architectural efficiencies of EfficientNetB0 with the deep representational capabilities of ResNet50. The model is designed to detect early signs of driver fatigue through advanced video-based analytics by leveraging both computational scalability and deep feature learning. Extensive experiments were conducted on three benchmark datasets—SUST-DDD, YawDD, and NTHU-DDD—to validate the model’s performance across a range of environmental and demographic variations. EffRes-DrowsyNet achieved 97.71% accuracy, 98.07% precision, and 97.33% recall on the SUST-DDD dataset. On the YawDD dataset, it sustained a high accuracy of 92.73%, while on the NTHU-DDD dataset, it reached 95.14% accuracy, 94.09% precision, and 95.39% recall. These results affirm the model’s superior generalization and classification performance in both controlled and real-world-like settings. The findings underscore the effectiveness of hybrid deep learning models in real-time, safety-critical applications, particularly for automotive driver monitoring systems. Furthermore, EffRes-DrowsyNet’s architecture provides a scalable and adaptable solution that could extend to other attention-critical domains such as industrial machinery operation, aviation, and public safety systems. Full article

The incorporation of Driver Monitoring Systems (DMSs) in vehicles is fundamental to enhancing road safety by continuously assessing driver behavior and identifying signs of fatigue or distraction. However, as these technologies evolve, they also present considerable cybersecurity challenges. This research undertakes an extensive Threat Analysis and Risk Assessment (TARA) of DMSs, adhering to the ISO/SAE 21434 standard, to methodically detect and assess potential security threats. A total of 115 threats were recognized and classified into 95 low-risk, 16 medium-risk, and 4 high-risk scenarios, underscoring key vulnerabilities in data transmission, sensor reliability, and communication frameworks. To mitigate these risks, we suggest a range of countermeasures, including enhanced encryption techniques, stringent authentication protocols, and reinforced access control mechanisms, designed to strengthen the security posture of DMSs in practical applications. This study introduces a structured framework for evaluating and addressing cybersecurity threats in alignment with industry regulations, facilitating the dependable and safeguarded implementation of DMSs in future vehicle architectures while contributing to ongoing progress in automotive cybersecurity. Full article

With the rapid advancement of autonomous driving (AD) technology, its application in road traffic has garnered increasing attention. This study analyzes 534 AD and 82,030 human driver traffic accidents and employs SMOTE to balance the sample sizes between the two groups. Using association rule mining, this study identifies key risk factors and behavioral patterns. The results indicate that while both AD and human driver accidents exhibit seasonal trends, their risk characteristics and distributions differ markedly. AD accidents are more frequent in summer (July–August) on clear days and tend to occur at intersections and on streets, with a higher proportion of non-injury collisions observed at night. Collisions involving non-motorized road users are more prevalent in human driver accidents. AD systems show certain advantages in detecting non-motorized vehicles and performing low-speed evasive maneuvers, particularly at night; however, limitations remain in perception and decision-making under complex conditions. Human driver accidents are more susceptible to driver-related factors such as fatigue, distraction, and risk-prone behaviors. Although AD accidents generally result in lower injury severity, further technological refinement and scenario adaptability are required. This study provides insights and recommendations to enhance the safety performance of both AD and human-driven systems, offering valuable guidance for policymakers and developers. Full article

Driver fatigue is a key factor in road accidents worldwide, requiring effective real-time detection mechanisms. Traditional deep neural network (DNN)-based solutions have shown promising results in detecting drowsiness; however, they are often less suitable for real-time applications due to their high computational complexity, risk of overfitting, and reliance on large datasets. Hence, this paper introduces an innovative approach that integrates fast neighbourhood component analysis (FNCA) with a deep neural network (DNN) to enhance the detection of driver drowsiness using electroencephalogram (EEG) data. FNCA is employed to optimize feature representation, effectively highlighting critical features for drowsiness detection, which are then analysed using a DNN to achieve high accuracy in recognizing signs of driver fatigue. Our model has been evaluated on the SEED-VIG dataset and achieves state-of-the-art accuracy: 94.29% when trained on 12 subjects and 90.386% with 21 subjects, surpassing existing methods such as TSception, ConvNeXt LMDA-Net, and CNN + LSTM. Full article

Despite advances in autonomous driving technology, current systems still require drivers to remain alert at all times. These systems issue warnings regardless of whether the driver is actually gazing at the road, which can lead to driver fatigue and reduced responsiveness over time, ultimately compromising safety. This paper proposes a sustainable real-time driver gaze monitoring method to enhance the safety and reliability of autonomous vehicles. The method uses a YOLOX-based face detector to detect the driver’s face and facial features, analyzing their size, position, shape, and orientation to determine whether the driver is gazing forward. By accurately assessing the driver’s gaze direction, the method adjusts the intensity and frequency of alerts, helping to reduce unnecessary warnings and improve overall driving safety. Experimental results demonstrate that the proposed method achieves a gaze classification accuracy of 97.3% and operates robustly in real-time under diverse environmental conditions, including both day and night. These results suggest that the proposed method can be effectively integrated into Level 3 and higher autonomous driving systems, where monitoring driver attention remains critical for safe operation. Full article

The latest developments in Advanced Driver Assistance Systems (ADAS) have greatly enhanced the comfort and safety of drivers. These technologies can identify driver abnormalities like fatigue, inattention, and impairment, which are essential for averting collisions. One of the important aspects of this technology is automated traffic accident detection and prediction, which may help in saving precious human lives. This study aims to explore critical features related to traffic accident detection and prevention. A public US traffic accident dataset was used for the aforementioned task, where various machine learning (ML) models were applied to predict traffic accidents. These ML models included Random Forest, AdaBoost, KNN, and SVM. The models were compared for their accuracies, where Random Forest was found to be the best-performing model, providing the most accurate and reliable classification of accident-related data. Owing to the black box nature of ML models, this best-fit ML model was executed with explainable AI (XAI) methods such as LIME and permutation importance to understand its decision-making for the given classification task. The unique aspect of this study is the introduction of explainable artificial intelligence which enables us to have human-interpretable awareness of how ML models operate. It provides information about the inner workings of the model and directs the improvement of feature engineering for traffic accident detection, which is more accurate and dependable. The analysis identified critical features, including sources, descriptions of weather conditions, time of day (weather timestamp, start time, end time), distance, crossing, and traffic signals, as significant predictors of the probability of an accident occurring. Future ADAS technology development is anticipated to be greatly impacted by the study’s conclusions. A model can be adjusted for different driving scenarios by identifying the most important features and comprehending their dynamics to make sure that ADAS systems are precise, reliable, and suitable for real-world circumstances. Full article

In-vehicle physiological sensing is emerging as a vital approach to enhancing driver monitoring and overall automotive safety. This pilot study explores the feasibility of a pressure-based system, repurposing commonplace occupant classification electronics to capture respiration signals during real-world driving. Data were collected from a driver-seat-embedded, fluid-filled pressure bladder sensor during normal on-road driving. The sensor output was processed using simple filtering techniques to isolate low-amplitude respiratory signals from substantial background noise and motion artifacts. The experimental results indicate that the system reliably detects the respiration rate despite the dynamic environment, achieving a mean absolute error of 1.5 breaths per minute with a standard deviation of 1.87 breaths per minute (9.2% of the mean true respiration rate), thereby bridging the gap between controlled laboratory tests and real-world automotive deployment. These findings support the potential integration of unobtrusive physiological monitoring into driver state monitoring systems, which can aid in the early detection of fatigue and impairment, enhance post-crash triage through timely vital sign transmission, and extend to monitoring other vehicle occupants. This study contributes to the development of robust and cost-effective in-cabin sensor systems that have the potential to improve road safety and health monitoring in automotive settings. Full article

Fatigue driving is one of the crucial factors causing traffic accidents. Most existing fatigue driving detection algorithms overlook individual driver characteristics, potentially leading to misjudgments. This article presents a novel detection algorithm that utilizes facial multi-feature fusion, thoroughly considering the driver’s individual characteristics. To improve the judging accuracy of the driver’s facial expressions, a personalized threshold is proposed based on the normalization of the driver’s eyes and mouth opening and closing instead of the traditional average threshold, as individual drivers have different eye and mouth sizes. Given the dynamic changes in fatigue level, a sliding window model is designed for further calculating blinking duration ratio (BF), yawning frequency (YF), and nodding frequency (NF), and these evaluation indexes are used in the feature fusion model. The reliability of the algorithm is verified by the actual test results, which show that the detection accuracy reaches 95.6% and shows good application potential in fatigue detection applications. In this way, facial multi-feature fusion and fully considering the driver’s individual characteristics makes fatigue driving detection more accurate. Full article

Drivers’ facial expression recognition systems play a pivotal role in Advanced Driver Assistance Systems (ADASs) by monitoring emotional states and detecting fatigue or distractions in real time. However, deploying such systems in resource-constrained environments like vehicles requires lightweight architectures to ensure real-time performance, efficient model updates, and compatibility with embedded hardware. Smaller models significantly reduce communication overhead in distributed training. For autonomous vehicles, lightweight architectures also minimize the data transfer required for over-the-air updates. Moreover, they are crucial for their deployability on hardware with limited on-chip memory. In this work, we propose a novel Dual Attention Lightweight Deep Learning (DALDL) approach for drivers’ facial expression recognition. The proposed approach combines the SqueezeNext architecture with a Dual Attention Convolution (DAC) block. Our DAC block integrates Hybrid Channel Attention (HCA) and Coordinate Space Attention (CSA) to enhance feature extraction efficiency while maintaining minimal parameter overhead. To evaluate the effectiveness of our architecture, we compare it against two baselines: (a) Vanilla SqueezeNet and (b) AlexNet. Compared with SqueezeNet, DALDL improves accuracy by 7.96% and F1-score by 7.95% on the KMU-FED dataset. On the CK+ dataset, it achieves 8.51% higher accuracy and 8.40% higher F1-score. Against AlexNet, DALDL improves accuracy by 4.34% and F1-score by 4.17% on KMU-FED. Lastly, on CK+, it provides a 5.36% boost in accuracy and a 7.24% increase in F1-score. These results demonstrate that DALDL is a promising solution for efficient and accurate emotion recognition in real-world automotive applications. Full article

Mountainous roads are severely affected by environmental factors such as insufficient lighting and shadows from tree branches, which complicates the detection of drivers’ facial features and the determination of fatigue states. An improved method for recognizing driver fatigue states on mountainous roads using the YOLOv5 neural network is proposed. Initially, modules from Deformable Convolutional Networks (DCNs) are integrated into the feature extraction stage of the YOLOv5 framework to improve the model’s flexibility in recognizing facial characteristics and handling postural changes. Subsequently, a Triplet Attention (TA) mechanism is embedded within the YOLOv5 network to bolster image noise suppression and improve the network’s robustness in recognition. Finally, the Wing loss function is introduced into the YOLOv5 model to heighten the sensitivity to micro-features and enhance the network’s capability to capture details. Experimental results demonstrate that the modified YOLOv5 neural network achieves an average accuracy rate of 85% in recognizing driver fatigue states. Full article

The significant number of road traffic accidents caused by fatigued drivers presents substantial risks to the public’s overall safety. In recent years, there has been a notable convergence of intelligent cameras and artificial intelligence (AI), leading to significant advancements in identifying driver drowsiness. Advances in computer vision technology allow for the identification of driver drowsiness by monitoring facial expressions such as yawning, eye movements, and head movements. These physical indications, together with assessments of the driver’s physiological condition and behavior, aid in assessing fatigue and lowering the likelihood of drowsy driving-related incidents. This study presents an extensive variety of meticulously designed algorithms that were thoroughly analyzed to assess their effectiveness in detecting drowsiness. At the core of this attempt lay the essential concept of feature extraction, an efficient technique for isolating facial and ocular regions from a particular set of input images. Following this, various deep learning models, such as a traditional CNN, VGG16, and MobileNet, facilitated detecting drowsiness. Among these approaches, the MobileNet model was a valuable choice for drowsiness detection in drivers due to its real-time processing capability and suitability for deployment in resource-constrained environments, with the highest achieved accuracy of 92.75%. Full article

Driving fatigue is the cause of many traffic accidents and poses a serious threat to road safety. To address this issue, this paper aims to develop a system for the early detection of driver fatigue. The system leverages heart rate variability (HRV) features and embedded machine learning to estimate the driver’s fatigue level. The driver’s HRV is derived from electrocardiogram (ECG) signals captured by a wearable device for analysis. Time- and frequency-domain HRV features are then extracted and used as the input for a machine learning classifier. A dataset of HRV features is collected from a driving simulation experiment involving 18 participants. Four machine learning classifiers are evaluated, and a backpropagation neural network (BPNN) is selected for its superior performance, achieving up to 94.35% accuracy. The optimized classifier is successfully deployed on an embedded system, providing a cost-effective and portable solution for the early detection of driver fatigue. The results demonstrate the feasibility of using HRV-based machine learning models for the early detection of driver fatigue, contributing to enhanced road safety and a reduced accident risk. Full article