Search Results (244)

Car accidents remain a leading cause of death worldwide, with drowsiness and distraction accounting for roughly 25% of fatal crashes in Ecuador. This study presents a real-time driver monitoring system that uses computer vision and deep learning to detect fatigue, distraction, and emotions from facial expressions. It combines a MobileNetV2-based CNN trained on RAF-DB for emotion recognition and MediaPipe’s 468 facial landmarks to compute the EAR (Eye Aspect Ratio), the MAR (Mouth Aspect Ratio), the gaze, and the head pose. Tests with 27 participants in both real and simulated driving environments showed strong results. There was a 100% accuracy in detecting distraction, 85.19% for yawning, and 88.89% for eye closure. The system also effectively recognized happiness (100%) and anger/disgust (96.3%). However, it struggled with sadness and failed to detect fear, likely due to the subtlety of real-world expressions and limitations in the training dataset. Despite these challenges, the results highlight the importance of integrating emotional awareness into driver monitoring systems, which helps reduce false alarms and improve response accuracy. This work supports the development of lightweight, non-invasive technologies that enhance driving safety through intelligent behavior analysis. Full article

Ensuring sustained driver attention is critical for intelligent transportation safety systems; however, the performance of data-driven driver distraction detection models is often limited by the high cost of large-scale manual annotation. To address this challenge, this paper proposes an adaptive semi-supervised driver distraction detection framework based on teacher–student learning and deformable pyramid feature fusion. The framework leverages a limited amount of labeled data together with abundant unlabeled samples to achieve robust and scalable distraction detection. An adaptive pseudo-label optimization strategy is introduced, incorporating category-aware pseudo-label thresholding, delayed pseudo-label scheduling, and a confidence-weighted pseudo-label loss to dynamically balance pseudo-label quality and training stability. To enhance fine-grained perception of subtle driver behaviors, a Deformable Pyramid Sparse Transformer (DPST) module is integrated into a lightweight YOLOv11 detector, enabling precise multi-scale feature alignment and efficient cross-scale semantic fusion. Furthermore, a teacher-guided feature consistency distillation mechanism is employed to promote semantic alignment between teacher and student models at the feature level, mitigating the adverse effects of noisy pseudo-labels. Extensive experiments conducted on the Roboflow Distracted Driving Dataset demonstrate that the proposed method outperforms representative fully supervised baselines in terms of mAP@0.5 and mAP@0.5:0.95 while maintaining a balanced trade-off between precision and recall. These results indicate that the proposed framework provides an effective and practical solution for real-world driver monitoring systems under limited annotation conditions. Full article

Driving safety under low-visibility or distracted conditions remains a critical challenge for intelligent transportation systems. This paper presents Edge-VisionGuard, a lightweight framework that integrates signal processing and edge artificial intelligence to enhance real-time driver monitoring and hazard detection. The system fuses multi-modal sensor data—including visual, inertial, and illumination cues—to jointly estimate driver attention and environmental visibility. A hybrid temporal–spatial feature extractor (TS-FE) is introduced, combining convolutional and B-spline reconstruction filters to improve robustness against illumination changes and sensor noise. To enable deployment on resource-constrained automotive hardware, a structured pruning and quantization pipeline is proposed. Experiments on synthetic VR-based driving scenes demonstrate that the full-precision model achieves 89.6% driver-state accuracy (F1 = 0.893) and 100% visibility accuracy, with an average inference latency of 16.5 ms. After 60% parameter reduction and short fine-tuning, the pruned model preserves 87.1% accuracy (F1 = 0.866) and <3 ms latency overhead. These results confirm that Edge-VisionGuard maintains near-baseline performance under strict computational constraints, advancing the integration of computer vision and Edge AI for next-generation safe and reliable driving assistance systems. Full article

Driver distraction, particularly mobile phone use while driving, remains one of the leading causes of road traffic incidents worldwide. In response to this issue and leveraging recent technological advances and increased access to intelligent systems, this research presents the development of an application running on an intelligent embedded architecture for the automatic detection of mobile phone use by drivers, integrating computer vision, inertial sensing, and edge computing. The system, based on the YOLOv8n model deployed on a Jetson Xavier NX 16Gb—Nvidia, combines real-time inference with an inertial activation mechanism and cloud storage via Firebase Firestore, enabling event capture and traceability through a lightweight web-based HMI interface. The proposed solution achieved an overall accuracy of 81%, an inference rate of 12.8 FPS, and an average power consumption of 8.4 W, demonstrating a balanced trade-off between performance, energy efficiency, and thermal stability. Experimental tests under diverse driving scenarios validated the effectiveness of the system, with its best performance recorded during daytime driving—83.3% correct detections—attributed to stable illumination and enhanced edge discriminability. These results confirm the feasibility of embedded artificial intelligence systems as effective tools for preventing driver distraction and advancing intelligent road safety. Full article

To overcome the issues of excessive computation and resource usage in distracted driving detection systems, this study introduces a compact detection framework named YOLOv8s-FPNE, built upon the YOLOv8 architecture. The proposed model incorporates FasterNet, Partial Convolution (PConv) layers, a Normalized Attention Mechanism (NAM), and the Focal-EIoU loss to achieve an optimal trade-off between accuracy and efficiency. FasterNet together with PConv enhances feature extraction while reducing redundancy, NAM strengthens the model’s sensitivity to key spatial and channel information, and Focal-EIoU refines bounding-box regression, particularly for hard-to-detect samples. Experimental evaluations on a public distracted driving dataset show that YOLOv8s-FPNE reduces the number of parameters by 21.7% and computational cost (FLOPS) by 23.6% relative to the original YOLOv8s, attaining an mAP@0.5 of 81.6%, which surpasses existing lightweight detection methods. Ablation analyses verify the contribution of each component, and comparative studies further confirm the advantages of NAM and Focal-EIoU. The results demonstrate that the proposed method provides a practical and efficient solution for real-time distracted driving detection on embedded and resource-limited platforms. Full article

Texting while driving (TWD) is a leading cause of distracted driving-related crashes, especially among college students. This study applied the Multi-Theory Model (MTM) of health behavior change to predict initiation and sustenance of refraining from TWD among university students. A cross-sectional survey was conducted among 164 students from a Southwestern U.S. public university using a 49-item validated MTM-based questionnaire. Structural equation modeling and hierarchical multiple regression analyses were employed to assess reliability, construct validity, and predictors of behavioral initiation and sustenance. Cronbach’s alpha coefficients ranged from 0.71 to 0.93, indicating strong reliability. The MTM demonstrated good fit (CFI = 0.950, RMSEA = 0.057 for initiation; CFI = 0.992, RMSEA = 0.039 for sustenance). Behavioral confidence (β = 0.30, p < 0.001) significantly predicted initiation, explaining 51.5% of the variance, while emotional transformation (β = 0.41, p < 0.001) and practice for change (β = 0.27, p = 0.0105) predicted sustenance, accounting for 61.5% of the variance. The MTM effectively explained both initiation and sustenance of refraining from TWD among college students. Interventions aimed specifically at reducing texting while driving should prioritize strengthening behavioral confidence for initiating change and supporting emotional transformation and practice-for-change strategies to sustain long-term abstinence from TWD. MTM-based approaches hold strong potential for designing theory-driven, culturally relevant distracted driving prevention programs. Full article

With the ongoing integration of advanced technologies into modern vehicle systems, understanding user interaction becomes a critical factor for safe and intuitive operation—especially in the transition towards autonomous driving. This article uncovers user-reported challenges of UX and in-vehicle UIs. The analysis is based on quantitative and qualitative evaluations of user-generated content (UGC) from automotive-focused online forums. The quantitative analysis is conducted by Natural Language Processing (NLP), while qualitative evaluation is performed through Mayring, applying a deductive–inductive category formation approach. The study investigates challenges related to interface complexity, driver distraction, and missing user diversity in the context of increasing digitalization. Based on the analysis, a set of practical design implications is presented, emphasizing context-sensitive function reduction, multimodal interface concepts, and UX strategies for reducing complexity. It has become evident that UX concepts in the automotive context can only succeed if they are adaptive, safety-oriented, and tailored to the needs of heterogeneous user groups. This leads to the development of an interaction strategy model, serving as a transitional framework for guiding the shift from manual to fully automated driving scenarios. The paper concludes with an outlook on further research to validate and refine the implications and UX framework. Full article

Driver distraction remains one of the leading causes of traffic accidents. Although deep learning approaches such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformers have been extensively applied for distracted driving detection, their performance is often hindered by limited real-time efficiency and high false detection rates. To address these challenges, this paper proposes an efficient dual-stream neural architecture, termed DualStream-AttnXGS, which jointly leverages visual and pose information to improve distraction recognition accuracy. In the RGB stream, an enhanced EfficientNetB0 backbone is employed, where Ghost Convolution and Coordinate Attention modules are integrated to strengthen feature representation while maintaining lightweight computation. A compound loss function combining Center Loss and Focal Loss is further introduced to promote inter-class separability and stabilize training. In parallel, the keypoint stream extracts human skeletal features using YOLOv8-Pose, which are subsequently classified through a compact ensemble model based on XGBoost v2.1.4 and Gradient Boosting. Finally, a Softmax-based probabilistic fusion strategy integrates the outputs of both streams for the final prediction. The proposed model achieved 99.59% accuracy on the SFD3 dataset while attaining 99.12% accuracy on the AUCD2 dataset, demonstrating that the proposed dual-stream architecture provides a more effective solution than single-stream models by leveraging complementary visual and pose information. Full article

According to Sigmund Freud, the unconscious is full of contradictions (wild emotional impulses, baseless fears, and repressive forces) but it is also a control mechanism. It is no wonder that digital platforms—requiring uniformity, reliable protocols, secure transmissions and proprietary algorithms as well as an enormous database about human desire and impulses—would gravitate toward a model of control, or more specifically, the ideal of automating impulsive actions and reactions. Similar to the Freudian unconscious, digital platforms and networks are infamously black-boxed, meaning their operations (inner workings) are made invisible to the average user, including information about them. Yet, the digital unconscious also seems to perfect and promote this as an automatic destructive force (a death drive fed by extraction, consumption and a will to endless profit) that is incommensurate with life on the planet. Using the recent pleas by the Tuvaluan Minister of Justice, Communication, and Foreign Affairs (Simon Kofe) to the United Nations Convention on Climate Change, this article will argue that denial has replaced repression as the key mechanism of the digital unconscious, allowing twenty-first century media to offer itself as pharmakon (both poison and a remedy or at least a distraction) to those twenty-first century crises that nineteenth-, twentieth-, and twenty-first-century media continue to advance. Full article

Accurate and efficient multi-agent trajectory prediction remains a core challenge for autonomous driving, particularly in modeling complex interactions while maintaining physical plausibility and computational efficiency. Many existing methods- especially those based on large transformer architectures- tend to overlook physical constraints, leading to unrealistic predictions and high deployment costs. In this work, we propose a lightweight trajectory prediction framework that integrates physical information to enhance interaction modeling and runtime performance. Our method introduces two physically inspired strategies: (1) a constraint-guided mechanism is used to filter irrelevant or distracting neighbors, and (2) a physics-aware attention module is applied to steer attention weights toward physically plausible interactions. The overall architecture adopts a modular and vectorized design, effectively reducing model complexity and inference latency. Experiments on the Argoverse V1 dataset, comparing against multiple existing methods, demonstrate that our approach achieves a favorable balance among accuracy, physical feasibility, and efficiency, running in real time on a commodity desktop GPU. Future work will focus on validating its performance on embedded hardware. Full article

In the dynamic and complex environment of highly automated vehicles, ensuring driver safety is the most critical task. While automation promises to reduce human error, the driver’s role is shifting to that of a teammate who must remain vigilant and ready to intervene, making it essential to monitor their attention level. However, a significant challenge in this domain is the considerable inter-individual variability in how people physiologically respond to cognitive states, such as distraction. This study addresses this by developing a methodology that first groups drivers into distinct physiology-based clusters before training a predictive model. The study was conducted in a high-fidelity driving simulator, where multimodal data streams, including heart rate variability and electrodermal activity, were collected from 30 participants during conditional-automated driving experiments. Using a time-series k-means clustering algorithm, the researchers successfully partitioned the drivers into clusters based on their physiological and behavioral patterns, which did not correlate with demographic factors. Then, a Long Short-Term Memory model was trained for each cluster, which achieved similar predictive performance compared to a single, generalized model. This finding demonstrates that a personalized, cluster-based approach is feasible for physiology-based driver monitoring, providing a robust and replicable solution for developing accurate and reliable attention estimation systems. Full article

In-vehicle voice assistants face usability challenges due to limitations in delivering feedback within the constraints of the driving environment. The presented study explores the potential of Rich Visual Feedback (RVF) on Head-Up Displays (HUDs) as a multimodal solution to enhance system usability. A user study with 32 participants evaluated three HUD User Interface (UI) designs: the AR Fusion UI, which integrates augmented reality elements for layered, dynamic information presentation; the Baseline UI, which displays only essential keywords; and the Flat Fusion UI, which uses conventional vertical scrolling. To explore HUD interface principles and inform future HUD design without relying on specific hardware, a simulated near-field overlay was used. Usability was measured using the System Usability Scale (SUS), and distraction was assessed with a penalty point method. Results show that RVF on the HUD significantly influences usability, with both content quantity and presentation style affecting outcomes. The minimal Baseline UI achieved the highest overall usability. However, among the two Fusion designs, the AR-based layered information mechanism outperformed the flat scrolling method. Distraction effects were not statistically significant, indicating the need for further research. These findings suggest RVF-enabled HUDs can enhance in-vehicle voice assistant usability, potentially contributing to safer, more efficient driving. Full article

Autonomous driving is anticipated to increase safety, efficiency, and accessibility of passenger transportation. Passengers are given freedom in the use of travel time through the potential to conduct non-driving related tasks (NDRTs). However, factors such as trust and motion sickness pose challenges to the widespread adoption of this technology. Human–machine interfaces (HMIs) have shown potential in mitigating motion sickness and fostering trust calibration in autonomous vehicles (AVs), e.g., by visualizing upcoming or current maneuvers of the vehicle. The majority of research on such HMIs relies on the passengers’ attention, preventing uninterrupted NDRT execution and thus impeding the automation’s usefulness. In this paper, we present a visual HMI, providing AV passengers with information about current driving maneuvers through their peripheral fields of view. This method of information transmission is compared to conventional in-vehicle displays and LED strips regarding perceptibility and distraction. In a controlled laboratory setting, N = 34 participants experienced each HMI condition, indicating their perception of the maneuver visualizations using joystick input while either focusing on a fixation cross to measure perceptibility or solving math tasks to measure distraction. The peripheral HMIs caused better maneuver perception (${{\eta }_{\mathrm{p}}}^2=0.12$) and lower distraction (${{\eta }_{\mathrm{g}}}^2=0.16$) from a visual NDRT than the conventional displays. These results yield implications for the design of HMIs for motion sickness mitigation and trust calibration in AVs. Full article

Distracted driving continues to be a major contributor to road accidents, highlighting the growing research interest in advanced driver monitoring systems for enhanced safety. This paper seeks to improve the overall performance and effectiveness of such systems by highlighting the importance of recognizing the driver’s activity. This paper introduces a novel methodology for assessing driver attention by using multi-perspective information using videos that capture the full driver body, hands, and face and focusing on three driver tasks: distracted actions, gaze direction, and hands-on-wheel monitoring. The experimental evaluation was conducted in two phases: first, assessing driver distracted activities, gaze direction, and hands-on-wheel using a CNN-based model and videos from three cameras that were placed inside the vehicle, and second, evaluating the multi-task fusion algorithm, considering the aggregated danger score, which was introduced in this paper, as a representation of the driver’s attentiveness based on the multi-task data fusion algorithm. The proposed methodology was built and evaluated using a DMD dataset; additionally, model robustness was tested on the AUC_V2 and SAMDD driver distraction datasets. The proposed algorithm effectively combines multi-task information from different perspectives and evaluates the attention level of the driver. Full article

Global road safety reports identify human factors as the leading causes of traffic accidents, particularly behaviors such as speeding, drunk driving, and driver distraction, emphasizing the need for autonomous driving technologies to enhance transport safety. This research aims to provide a practical model for the development of autonomous driving systems as part of an autonomous transportation system for inter-building passenger mobility, intended to enable safe and efficient short-distance transport between buildings in semi-open environments such as university campuses. This work presents a fully integrated autonomous platform combining LiDAR, cameras, and IMU sensors for mapping, perception, localization, and control within a drive-by-wire framework, achieving superior coordination in driving, braking, and obstacle avoidance and validated under real campus conditions. The electric golf cart prototype achieved centimeter-level mapping accuracy (0.32 m), precise localization (0.08 m), and 2D object detection with an mAP value exceeding 70%, demonstrating accurate perception and positioning under real-world conditions. These results confirm its reliable performance and suitability for practical autonomous operation. Field tests showed that the vehicle maintained appropriate speeds and path curvature while performing effective obstacle avoidance. The findings highlight the system’s potential to improve safety and reliability in short-distance autonomous mobility while supporting scalable smart mobility development. Full article