Experiments on the State Farm Distracted Driver Detection dataset show that MobileNetV3-Large provides the best trade-off among the evaluated lightweight models, demonstrating a practical balance between unseen-driver generalization, interpretability, and real-time embedded inference.
Abstract
Driver distraction is a major road-safety concern that requires reliable and efficient in-vehicle monitoring systems. The main contribution of this work is a reproducible driver-disjoint and deployment-oriented evaluation framework that jointly examines unseen-driver generalization, lightweight model benchmarking, explainability, calibration, and embedded inference. Experiments on the State Farm Distracted Driver Detection dataset show that MobileNetV3-Large provides the best trade-off among the evaluated lightweight models, achieving 88.92% test accuracy, 89.02% balanced accuracy, 88.07% macro-F1, and 97.88% Top-3 accuracy on unseen drivers. Explainable AI analysis indicates that the model mainly focuses on behavior-relevant regions, including the hands, face, phone area, steering wheel, and upper-body posture. For embedded deployment, TensorRT optimization on the Jetson Orin Nano Super achieved 212.94 FPS with 4.67 ms end-to-end latency in FP16 mode. These results demonstrate a practical balance between unseen-driver generalization, interpretability, and real-time embedded inference.
IYOLO, an enhanced YOLOv8-based framework for simultaneous detection and classification of vehicles, drivers, and passengers on highways, aiming to distinguish drivers from passengers and establish one-to-one vehicle-driver associations is proposed.
Yang Zhang, Peihua Lv, Hongjin Ren et al.· International Conference on...· 0 citations
This research establishes a statistically robust and deployable foundation for next-generation intelligent transportation systems by coupling Bayesian learning theory with edge computing design.
S. M. Hosseini, V. Kiani, Hadi Sadoghi-Yazdi· Computing· 0 citations
Introduction Driver drowsiness is a leading cause of road traffic fatalities worldwide, and the convergence of computer vision and deep learning has transformed driver-state monitoring by enabling non-invasive detection within Advanced Driver Assistance Systems (ADAS). Methods This systematic literature review, conducted using the PRISMA 2020 methodology and the Kitchenham protocol, synthesizes findings from 33 peer-reviewed studies published between January 2021 and October 2025 to examine the architectures, biomarkers, performance benchmarks, and deployment barriers of deep-learning-based drowsiness detection. Results The literature is dominated by convolutional single–pass designs; no reviewed model combines an accuracy above 99% with a latency below 100 ms, and none were evaluated on embedded or automotive–grade hardware. Discussion This distribution highlights a persistent accuracy-latency trade-off and emphasizes the need for embedded hardware and cross–dataset evaluation. By synthesizing the available evidence, this review characterizes the current state of the art and proposes a prioritized framework for selecting deep learning architectures for embedded ADAS applications.
Christian Wilbert Salas Yupanqui, Cristhian Edy Llanque Tipo, Frank Diego Choquehuanca Huayhua et al.· Frontiers in Artificial Inte...· 0 citations
Driver behavior is a critical factor in road safety, contributing to the majority of traffic crashes. The i-DREAMS project introduced the concept of a Safety Tolerance Zone (STZ) to enhance driving safety through real-time and post-trip interventions. This study develops and evaluates three hybrid machine learning models—(i) Deep Neural Network–Random Forest (DNN-RF), (ii) Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM), and (iii) Recurrent Neural Network–AdaBoost (RNN-AdaBoost)—to classify risky driving behavior into three safety levels using naturalistic driving data from Belgium and the UK. The dataset includes 69 drivers, 15,389 trips, and 265,512 min of driving data. Among the models tested, the DNN-RF model demonstrated the highest accuracy, reaching 98% in Belgium and 97% in the United Kingdom, outperforming other approaches. Feature importance analysis identified harsh acceleration and braking as the most critical factors in Belgium, while total trip distance and harsh acceleration were predominant in the UK. To enhance model transparency, we applied the Local Interpretable Model-agnostic Explanations (LIME) algorithm, providing valuable insights into model predictions. The findings support the potential of hybrid deep learning models in improving road safety by accurately detecting risky driving behaviors. These insights can inform targeted interventions and driver assistance technologies to mitigate crash risks and promote safer driving practices.
E. Theodoraki, Thodoris Garefalakis, Eva Michelaraki et al.· Infrastructures· 0 citations
Sri Lanka’s public bus network carries millions of daily commuters yet operates with negligible real-time visibility into driver safety, road compliance, or service quality [1], [2]. Drivers go unmonitored, violations go unrecorded, and passengers lack reliable arrival or occupancy information [1]. This paper presents an integrated, low-cost IoT platform addressing these deficiencies within a single system. A cab-mounted camera continuously monitors the driver, detecting drowsiness, phone use, and seat belt non-compliance with a mean average precision (mAP50) of 98.5%. A forward-facing module fuses object detection, lane segmentation, and monocular depth estimation to identify traffic violations at 10–25 FPS (Raspberry Pi 5; Table III). Calibrated load cells feed a LightGBM regressor generating load-aware speed recommendations (R2 = 0.887, MAE = 1.94 km/h). An LSTM trained on SLTB ticketing data predicts arrival times to within 103 s MAE; a BiLSTM multi-task model estimates boarding and alighting counts with MAEs of 2.29 and 2.18 passengers, respectively. The complete hardware bill-of-materials is under USD 100 per bus, comprising a Raspberry Pi 4/5, ESP32, load cells, and off-the-shelf sensors. Together these modules form a proof-of-concept that meaningfully advances transit safety and passenger intelligence without infrastructure-level investment.
A lightweight multi-task learning framework for safety-critical autonomous driving perception that strikes a balance between accuracy and real-time performance in multi-task perception, thereby supporting safety-critical perception by reducing perception latency and improving perception reliability.
Xin Dong, Jun Shen, Chiyuan Li et al.· Journal of Real-Time Image P...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
