A Hybrid Driver Fatigue and Distraction Detection Model Using AlexNet Based on Facial Features

A Real-Time Embedded System for Driver Drowsiness Detection Based on Visual Analysis of the Eyes and Mouth Using Convolutional Neural Network and Mouth Aspect Ratio

Currently, the number of vehicles in circulation continues to increase steadily, leading to a parallel increase in vehicular accidents. Among the many causes of these accidents, human factors such as driver drowsiness play a fundamental role. In this context, one solution to address the challenge of drowsiness detection is to anticipate drowsiness by alerting drivers in a timely and effective manner. Thus, this paper presents a Convolutional Neural Network (CNN)-based approach for drowsiness detection by analyzing the eye region and Mouth Aspect Ratio (MAR) for yawning detection. As part of this approach, endpoint delineation is optimized for extraction of the region of interest (ROI) around the eyes. An NVIDIA Jetson Nano-based device and near-infrared (NIR) camera are used for real-time applications. A Driver Drowsiness Artificial Intelligence (DD-AI) architecture is proposed for the eye state detection procedure. In a performance analysis, the results of the proposed approach were compared with architectures based on InceptionV3, VGG16, and ResNet50V2. Night-Time Yawning-Microsleep-Eyeblink-Driver Distraction (NITYMED) was used for training, validation, and testing of the architectures. The proposed DD-AI network achieved an accuracy of 99.88% with the NITYMED test data, proving superior to the other networks. In the hardware implementation, tests were conducted in a real environment, resulting in 96.55% and 14 fps on average for the DD-AI network, thereby confirming its superior performance.

Illumination Intelligent Adaptation and Analysis Framework: A comprehensive solution for enhancing nighttime driving fatigue monitoring

Nighttime driving presents a critical challenge to road safety due to insufficient lighting and increased risk of driver fatigue. Existing methods for monitoring driver fatigue, mainly focusing on behavioral analysis and biometric monitoring, face significant challenges under low-light conditions. Their effectiveness, especially in dynamic lighting environments, is limited by their dependency on specific environmental conditions and active driver participation, leading to reduced accuracy and practicality in real-world scenarios. This study introduces a novel 'Illumination Intelligent Adaptation and Analysis Framework (IIAAF)', aimed at addressing these limitations and enhancing the accuracy and practicality of driver fatigue monitoring under nighttime low-light conditions. The IIAAF framework employs a multidimensional technology integration, including comprehensive body posture analysis and facial fatigue feature detection, per-pixel dynamic illumination adjustment technology, and a light variation feature learning system based on Convolutional Neural Networks (CNN) and time-series analysis. Through this integrated approach, the framework is capable of accurately capturing subtle fatigue signals in nighttime driving environments and adapting in real-time to rapid changes in lighting conditions. Experimental results on two independent datasets indicate that the IIAAF framework significantly improves the accuracy of fatigue detection under nighttime low-light conditions. This breakthrough not only enhances the effectiveness of driving assistance systems but also provides reliable scientific support for reducing the risk of accidents caused by fatigued driving. These research findings have significant theoretical and practical implications for advancing intelligent driving assistance technology and improving nighttime road safety.

Electric Bus Pedal Misapplication Detection Based on Phase Space Reconstruction Method

Due to the environmental protection of electric buses, they are gradually replacing traditional fuel buses. Several previous studies have found that accidents related to electric vehicles are linked to Unintended Acceleration (UA), which is mostly caused by the driver pressing the wrong pedal. Therefore, this study proposed a Model for Detecting Pedal Misapplication in Electric Buses (MDPMEB). In this work, natural driving experiments for urban electric buses and pedal misapplication simulation experiments were carried out in a closed field; furthermore, a phase space reconstruction method was introduced, based on chaos theory, to map sequence data to a high-dimensional space in order to produce normal braking and pedal misapplication image datasets. Based on these findings, a modified Swin Transformer network was built. To prevent the model from overfitting when considering small sample data and to improve the generalization ability of the model, it was pre-trained using a publicly available dataset; moreover, the weights of the prior knowledge model were loaded into the model for training. The proposed model was also compared to machine learning and Convolutional Neural Networks (CNN) algorithms. This study showed that this model was able to detect normal braking and pedal misapplication behavior accurately and quickly, and the accuracy rate on the test dataset is 97.58%, which is 9.17% and 4.5% higher than the machine learning algorithm and CNN algorithm, respectively.

DDD TinyML: A TinyML-Based Driver Drowsiness Detection Model Using Deep Learning

Driver drowsiness is one of the main causes of traffic accidents today. In recent years, driver drowsiness detection has suffered from issues integrating deep learning (DL) with Internet-of-things (IoT) devices due to the limited resources of IoT devices, which pose a challenge to fulfilling DL models that demand large storage and computation. Thus, there are challenges to meeting the requirements of real-time driver drowsiness detection applications that need short latency and lightweight computation. To this end, we applied Tiny Machine Learning (TinyML) to a driver drowsiness detection case study. In this paper, we first present an overview of TinyML. After conducting some preliminary experiments, we proposed five lightweight DL models that can be deployed on a microcontroller. We applied three DL models: SqueezeNet, AlexNet, and CNN. In addition, we adopted two pretrained models (MobileNet-V2 and MobileNet-V3) to find the best model in terms of size and accuracy results. After that, we applied the optimization methods to DL models using quantization. Three quantization methods were applied: quantization-aware training (QAT), full-integer quantization (FIQ), and dynamic range quantization (DRQ). The obtained results in terms of the model size show that the CNN model achieved the smallest size of 0.05 MB using the DRQ method, followed by SqueezeNet, AlexNet MobileNet-V3, and MobileNet-V2, with 0.141 MB, 0.58 MB, 1.16 MB, and 1.55 MB, respectively. The result after applying the optimization method was 0.9964 accuracy using DRQ in the MobileNet-V2 model, which outperformed the other models, followed by the SqueezeNet and AlexNet models, with 0.9951 and 0.9924 accuracies, respectively, using DRQ.