Realtime Driver Drowsiness Detection Using Machine Learning

Driver fatigue is a leading cause of road accidents, particularly during long-distance driving, and necessitates reliable, real-time detection methods to prevent safety compromises. This study presents a drowsiness detection system designed to provide early warnings by analyzing eye-blinking patterns through real-time facial recognition and eye tracking using an in-vehicle camera. The system leverages MediaPipe to extract facial landmarks and compute the Eye Aspect Ratio (EAR), a geometric measure that quantifies eye openness. By employing a threshold-based decision mechanism, the system triggers audible alerts when EAR values indicate signs of drowsiness, such as prolonged or frequent eye closures. Evaluated on a dataset of 667 driver images, the system achieved an accuracy of 85% in drowsiness detection, with an optimal EAR threshold of 0.289 identified for maximizing performance. The approach demonstrates robustness against common real-world challenges, including variations in lighting conditions and camera positioning, offering a non-intrusive, adaptive, and highly reliable solution. By focusing on eye-based biometric features derived from facial landmarks, this system contributes an original and practical advancement in driver monitoring technology, with significant potential to reduce fatigue-related accidents and enhance overall road safety.

Road safety concerns have spurred the development of innovative technologies aimed at reducing accidents, particularly those caused by driver fatigue. The main scope of the driver drowsiness detection system is to minimize road accidents caused by fatigue or sleepiness of drivers. This system leverages deep learning and computer vision, employing a Raspberry Pi camera to monitor facial expressions, including yawning, to assess the driver's alertness. Upon detecting signs of drowsiness, such as prolonged eye closure or altered facial expressions, the system triggers a buzzer alert by analyzing the Eye Aspect Ratio (EAR) and Mouth Aspect Ratio (MAR) ratios. Integrated within an embedded system, it utilizes frontal face detection algorithms and Haar cascade classifiers to localize key facial features in real-time, facilitating efficient monitoring for signs of fatigue or distraction. Additionally, it issues vibration alerts if the seat belt is not fastened. The seat belt remainder will be helpful to ensure the safety of the driver, reduces accidents and monitors the driver's heart rate, triggering a PANIC message if irregularities are detected. At traffic signals, the system automatically reduces vehicle speed using a vibration motor. In the unfortunate event of an accident, the system initiates speed reduction and promptly notifies registered contacts through the Blynk application, thereby significantly reducing accidents caused by drowsy driving.

Fatigue driving is an invisible killer in car accidents and one of the main causes of traffic accidents. In order to reduce traffic accidents caused by driving fatigue, this research has developed a safety assist device to prevent such traffic accidents. In this research, a non-contact driver drowsiness detection and alert system is established in the vehicle cabin. The real-time facial image of the driver is obtained through the camera installed in front of the driver, and then the image is input to the NVIDIA Jetson TX2 embedded module. YOLO (You Only Look Once) object detection algorithm is used to detect the opening and closing of the driver's eyes, and by processing the eye area, to determine whether the driver is currently awake or fatigued while driving. The driver drowsiness detection and alert system established in this research can be applied to the vehicle interior environment to monitor the driving status. When the driver is fatigued, the system will simultaneously emit sound and light signals to promptly warn such dangerous driving behaviors. It can prevent the driver from continuing to drive when fatigued, and ensure driving safety.

Recent developments in computing technology and advancements in artificial intelligence have led to major improvements in driver monitoring systems. These enhancements are crucial given the substantial risk posed by fatigue or drowsiness on roads, leading to numerous accidents and impacting overall road safety. Timely detection and alert mechanisms for fatigued drivers can prevent many such accidents. Various methods have been formulated to monitor driver drowsiness during operation and alert drivers when their attention wanes. These methods utilize facial expressions like yawning, eye closures and head movements to gauge the level of drowsiness, in addition to analyzing biological markers of fatigue in the driver's body and monitoring vehicle behavior. This study delves into an in-depth analysis of existing driver drowsiness detection methods, focusing on widely used classification techniques. The paper classifies these methods into three primary categories: behavioral, vehicular and physiological based techniques. This study thoroughly investigates advanced methods for detecting driver fatigue, utilizing multiple machine learning and deep learning capabilities and a comparative study of these methods is presented. The research includes a detailed analysis of approaches to detect driver fatigue through facial landmark detection, employing established algorithms rooted in artificial neural networks and computer vision principles. Furthermore, the paper discusses potential advancements in driver fatigue detection technologies, providing valuable guidance for professionals and researchers striving to improve road safety through effective fatigue detection systems.

Drowsiness or fatigue is a major cause of road accidents and has significant implications for road safety. Several deadly accidents can be prevented if the drowsy drivers are warned in time. A variety of drowsiness detection methods exist that monitor the drivers' drowsiness state while driving and alarm the drivers if they are not concentrating on driving. The relevant features can be extracted from facial expressions such as yawning, eye closure, and head movements for inferring the level of drowsiness. The biological condition of the drivers' body, as well as vehicle behavior, is analyzed for driver drowsiness detection. This paper presents a comprehensive analysis of the existing methods of driver drowsiness detection and presents a detailed analysis of widely used classification techniques in this regard. First, in this paper, we classify the existing techniques into three categories: behavioral, vehicular, and physiological parameters-based techniques. Second, top supervised learning techniques used for drowsiness detection are reviewed. Third, the pros and cons and comparative study of the diverse method are discussed. In addition, the research frameworks are elaborated in diagrams for better understanding. In the end, overall research findings based on the extensive survey are concluded which will help young researchers for finding potential future work in the relevant field.

Driver drowsiness detection is a system that uses various sensors and algorithms to detect when a driver is becoming fatigued or drowsy. When a driver is drowsy, they are not operating in full alert mode rather, they are only somewhat tired. The majority of traffic accidents throughout the world are caused by fatigued and sleepy drivers. This can be done through monitoring eye movements, facial expressions, and head position, as well as analyzing driving patterns such as sudden lane changes or prolonged periods of inactivity on the steering wheel. The system can then alert the driver to take a break or pull over to rest, potentially preventing accidents caused by drowsy driving. It can also be used in commercial vehicles for safety of drivers and other people on the road. Accidents in the present day are increasingly being caused by this consisting of ocular fatigue. These characteristics show that the driver's condition is not right. For the purpose of detecting sleepiness, the ratio of distances between the horizontal and vertical eye landmarks is calculated using the EAR (Eye Aspect Ratio). The proposed method calculates the landmark since the landmarks are identified precisely enough to do so. This study determines the eye aspect ratio (EAR), a single scalar quantity that characterizes the opening of the eyes in each frame, and extracts it. Finally, an SVM classifier developed by Haar Cascade recognizes eye blinks as a pattern of EAR values. However, both driver fatigue and distraction may result in slower response times, reduced driving efficiency, and a higher risk of being involved in an accident. The output is delivered to the detection system, and the alert will be activated, if the driver's degree of fatigue and the estimated amount of sleepiness are determined. The true number of accidents brought on by driver fatigue is difficult to ascertain because it is frequently under reported. The driver typically doesn't notice the small change from being tired to nodding off. This explains why it is critical to continue research in this area with the goal of reducing the frequency of driver drowsy accidents and motivating for a driver sleepiness detection system.

Nowadays, drowsiness is a serious cause of traffic accidents, a problem of major concern to society. Driver fatigue or sleepiness decreases the driver’s reaction time, reduces attention, and affects the quality of decision making which impairs the driving experience. Therefore, in this paper, a drowsiness detection system is designed based on computer vision, using a cascade of classifiers based on Haar-like features. The system is able to detect the face and eyes of the driver and determine the eyes closure or opening, which concludes the drowsiness of the driver. The paper presents the five primary steps involves which are: video acquirement, frame separation, face detection, eyes detection and drowsiness detection.

Vehicle crashes lead to huge economic and social consequences, and one non-negligible cause of accident is driver sleepiness. Driver sleepiness analysis based on the monitoring of vehicle acceleration, steering and deviation from the road or physiological and behavioral monitoring of the driver, e.g., monitoring of yawning, head pose, eye blinks and eye closures, electroencephalogram, electrooculogram, electromyogram and electrocardiogram (ECG), have been used as a part of sleepiness alert systems. Heart rate variability (HRV) is a potential method for monitoring of driver sleepiness. Despite previous positive reports from the use of HRV for sleepiness detection, results are often inconsistent between studies. In this work, we have re-evaluated the feasibility of using HRV for detecting drivers’ sleepiness during real road driving. A database consists of ECG measurements from 10 drivers, driving during morning, afternoon and night sessions on real road were used. Drivers have reported their average sleepiness level by using the Karolinska sleepiness scale once every five minutes. Statistical analysis was performed to evaluate the potential of HRV indexes to distinguish between alert, first signs of sleepiness and severe sleepiness states. The results suggest that individual subjects show different reactions to sleepiness, which produces an individual change in HRV indicators. The results motivate future work for more personalized approaches in sleepiness detection.

Driver fatigue is one of the leading causes of traffic accidents. At present, fatigue driving detection has disadvant ages such as low practical application effect and high equipment requirements. This paper proposes a multi-feature point non-invasive fatigue monitoring system based on a support vector machine with a hybrid kernel function. The system detects feature points through a gradient descent tree algorithm based on a cascaded regression and calculates the eye aspect ratio (EAR) and mouth aspect ratio (MAR). The heart rate is obtained through RGB image analysis combined with Euler’s video magnification algorithm. Classify facial features to get fatigued. This paper is based on the Logistic and Radial Basis Polynomial Kernel (RBPK) function to improve the support vector machine, which has better learning and generalization. Finally, this paper uses the Driver Drowsiness Detection Dataset and the author’s dataset to test. The classification accuracy rate for a single picture is 96.92%. In summary, the system proposed in this paper has a better recognition rate for fatigue driving detection.

Android-based driver alert system is a real-time application which is used for detecting driver drowsiness and alerts the driver to reduce the possible accidents. In this paper, the detection is based on the results of face and eye region or the pupil of the eyeball to determine whether the driver is in the drowsy condition or not. A new approach is introduced for detecting driver drowsiness by using Google API and OpenCV library. My system uses a modified implementation of the Viola-Jones algorithm for faces and eye detection of the driver. Detection is performed on the basis of the symptoms related to eye and face region of driver. In this method, face detection module, motion detection module, on road motion detection module, GPS module are used for extracting the symptoms of driver drowsiness. Android-based smart phones are equipped with several sensors that can help to assist in safety development for drivers on the road. Comparison between OpenCV library and Google API of both face and eye detection as shown in this paper using graph. The average correction detection ratio of face detection is 100% and eye detection is 85%, which shows my proposed system is feasible, cost effective, and reliable.

The proposed system aims to lessen the number of accidents that occur due to drivers' drowsiness and fatigue, which will in turn increase transportation safety.This is becoming a common reason for accidents in recent times.Several faces and body gestures are considered such as signs of drowsiness and fatigue in drivers, including tiredness in eyes and yawning.Due to extended driving durations and boredom in crowded settings, driver weariness is one of the leading causes of traffic accidents, particularly for drivers of big vehicles.Computer vision-based image processing techniques are one of them.This uses various images of the driver to detect drowsiness states using his/her eyes states and facial expressions.This technique is the focus of this survey paper.

<div>Driver fatigue and drowsiness portray an integral role in the frequency of road accidents. Putting in place policies intended to alert drivers is imperative for averting accidents and saving lives. This work aims to improve road safety by devising a real-time driver drowsiness detection system. To accomplish this, drowsiness is detected using YOLOv8 algorithm optimized with the whale optimization algorithm (WOA). Key facial cues such as eye closure and yawning frequency are monitored to analyze driving behavior by the suggested approach. YOLOv8 model optimized with WOA processes video streams in real time and sets off an alarm on the graphical user interface (GUI) dashboard based on the output. The proposed approach was investigated using two datasets namely UTA-RLDD and D3S. A 640 × 640 pixel image with a frame rate of 50 fps was used in the investigation. The mAP at 0.5 (mean average precision at 0.5 IoU (intersection over union) threshold) of drowsiness detection system using UTA-RLDD dataset is 85.4% and using D3S dataset is 84.3%. It was indicated by the obtained results that the WOA-optimized YOLOv8 model attains superior detection accuracy and quicker inference times in comparison to the contemporary methods. This analysis sets the stage for advancements in real-time drowsiness detection techniques for implementation in vehicle safety systems.</div>

Driver drowsiness is a major factor that contributing to road accidents. Several researches are ongoing to detect driver drowsiness, but they suffer from the complexity and cost of the models. This paper introduces a hybrid artificial intelligence (AI)-driven framework integrating deep learning (DL) and machine learning (ML) models for real-time drowsiness detection. The system utilizes a robust DL model to classify driver states based on facial images and support vector machine (SVM) model is trained to develop a cost-efficient yet robust facial landmark detector to extract key features such as eye aspect ratio (EAR) and mouth aspect ratio (MAR). We also introduce a multi-stage decision fusion mechanism that combines convolutional neural network (CNN) probability scores with EAR/MAR thresholds to enhance detection reliability and reduce false positives. Experimental results demonstrate that the proposed model achieves 98% accuracy and F1-score, significantly outperforming traditional DL approaches. Additionally, the SVM-based landmark predictor shows improved efficiency with lower mean squared error (MSE) without having higher computational requirements.

Fatigue driving has always received a lot of attention, but few studies have focused on the fact that human fatigue is a cumulative process over time, and there are no models available to reflect this phenomenon. Furthermore, the problem of incorrect detection due to facial expression is still not well addressed. In this article, a model based on BP neural network and time cumulative effect was proposed to solve these problems. Experimental data were used to carry out this work and validate the proposed method. Firstly, the Adaboost algorithm was applied to detect faces, and the Kalman filter algorithm was used to trace the face movement. Then, a cascade regression tree-based method was used to detect the 68 facial landmarks and an improved method combining key points and image processing was adopted to calculate the eye aspect ratio (EAR). After that, a BP neural network model was developed and trained by selecting three characteristics: the longest period of continuous eye closure, number of yawns, and percentage of eye closure time (PERCLOS), and then the detection results without and with facial expressions were discussed and analyzed. Finally, by introducing the Sigmoid function, a fatigue detection model considering the time accumulation effect was established, and the drivers’ fatigue state was identified segment by segment through the recorded video. Compared with the traditional BP neural network model, the detection accuracies of the proposed model without and with facial expressions increased by 3.3% and 8.4%, respectively. The number of incorrect detections in the awake state also decreased obviously. The experimental results show that the proposed model can effectively filter out incorrect detections caused by facial expressions and truly reflect that driver fatigue is a time accumulating process.

The number of automobile accidents due to driver drowsiness is increasing at an alarming rate. An automated non-contact system that can identify driver drowsiness early is the need of the hour. Motivated by this alarming need, a novel method is proposed that can detect driver drowsiness at an early stage and avoid mishaps. After the preprocessing of data using various features like Mouth Aspect Ratio, Eye Aspect Ratio, Pupil Circularity and Mouth Over Eye Ratio, the classification is done as comparative analysis of K-Nearest Neighbour, Naïve Bayes, Logistic Regression, Decision Trees, Random Forest, XGBoost, MLP and CNN on the University of Texas at Arlington Real-Life Drowsiness Dataset (UTA-RLDD) with different labels and thus we are able to detect the drowsiness. The accuracy was evaluated, and Logistic Regression provides the best accuracy in detecting drowsiness based on the dataset and was able to achieve 75.67% accuracy for 9080 samples.