An Improved Driver Drowsiness Detection using Haar Cascade Classifier

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.

The proposed system is based on the Internet of Things (IoT). We proposed a Drowsiness detection system with Deep Learning using the internet of things. The system's goal is to prevent vehicle accidents caused by drowsy drivers. Millions of people have lost their lives globally as a result of drowsy driving incidents involving fast motorized vehicles. Research by the Central Road Research Institute (CRRI) found that almost 40% of all road accidents are triggered by drivers who are asleep at the wheel. The study's goal is to create a smart warning system that can recognize and discourage driving while fatigued. There were numerous approaches to resolving this problem. Here are a few examples: Support Vector Machine and Histogram of Gradients are used to create a system that does not require a big amount of data and is very sensitive when a picture is rotated. An application is created with the help of sensors; however, these sensors are only effective in certain environments. The surroundings are also working efficiently by counting the blinks of the eyes. The web camera is also inefficient because the camera's bandwidth varies from location to location owing to intensity. Now, a solution is developed that takes into account all of the disadvantages of the Raspberry Pi camera while still being efficient and portable. The Raspberry Pi board functions as a mini-computer that can be carried around. Using the OpenCV algorithm and OpenCV function, the Raspberry Pi camera translates the driver's video stream to a frame and grayscale image. The eye pairs take into account face landmarks, and the Eye Aspect Ratio is derived using Euclidean distances between the locations of the eyes. When the driver's condition is determined to be drowsy, an alert alarm will play, causing the driver to wake up. In 2022, 1,55,622 people died in road accidents in India. According to the National Safety Council, drowsy driving causes around 100,000 accidents, 71,000 injuries, and 1,550 fatalities each year (NSC).

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.

Driver drowsiness is one of the leading causes of traffic accidents and has a substantial impact on road safety. Many traffic accidents can be avoided if sleepy drivers were given early warnings. Drowsiness detection systems monitor the driver condition and generate an alarm if drowsiness signs are detected. In this paper, a real-time visual-based driver drowsiness detection system is presented aiming to detect drowsiness by extracting an eye feature called the eye aspect ratio. In the proposed system, which is applied on videos obtained from a public drowsiness detection dataset, the face region is first localized in each frame. Then, the eye region is detected and extracted as the region of interest using facial landmarks detector. Following that, the eye aspect ratio value of each frame is calculated, analyzed, and recorded. Finally, three different classifiers, namely, linear support vector machine, random forest, and sequential neural network, are employed to improve the detection accuracy. Subsequently, the extracted data are classified to determine if the driver's eyes are closed or open. An alarm will then be triggered to alert the drowsy driver if an eye closure is recognized for a specified duration of time.

Maneuverability is been one of the key things which people look for in their automobiles. This lead to the implementation of “Four wheel Steering “in vehicles. Four wheel steering is a system that allows the rear wheels to turn, rather than just following the front wheel. It is a system with two phases, a negative phase for slow speeds and a positive phase for the high speeds. Turning the rear wheels in the opposite direction to the front is the negative phases, which enhances faster maneuvering and a much tighter turning radius. Turning the rear wheels in the same direction as those at the front is the positive phase, which enhances sudden lane changes with much greater stability At present, there are three mechanisms used for steering the rear wheel. They are mechanical (using hypocycloidal gear set up), hydraulic and electrohydraulic. The reason for the system not being implemented in the commercial vehicle was its expensive nature. To overcome the above statement, a study was made on four wheel steering using tumbler gear mechanism. The result shows the decrease in the cost of implementation of the system and turning radius compared to two wheel steering respectively.

Traffic accidents caused by driver drowsiness are a leading factor in fatal road incidents. This study introduces a computer vision-based drowsiness detection system utilizing two methods: Eye Aspect Ratio (EAR) and Iris-Sclera Pattern Analysis (ISPA). The EAR method measures the eye aspect ratio to determine whether the eyes are open or closed. This involves calculating the vertical distance between specific landmark points on the eyelids and comparing it to the horizontal distance between points on the eye. A decrease in this ratio serves as an early indicator of drowsiness. The ISPA method employs symmetry analysis between the iris and sclera. This approach relies on the visual pattern formed when the eyes are open, where the sclera appears symmetrically distributed around the iris. During this process, eye images are processed to extract iris and sclera features, which are then analyzed for symmetry to detect signs of drowsiness. The study evaluates the reliability of both methods under varying conditions, such as changes in lighting, viewing distances, head movements, and the use of eyeglasses. The results show that the EAR method achieved an accuracy of 83.33% in distance testing, indicating its effectiveness in stable lighting environments. In contrast, the ISPA method achieved an accuracy of 59.25% under low and variable lighting conditions and proved more reliable for detecting the eyes of users wearing glasses.

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.

The proposed system aims to enhance transportation safety by reducing the number of accidents caused by driver fatigue and drowsiness, which have become increasingly common. The system analyzes facial and bodily gestures such as eye tiredness and yawning to identify signs of drowsiness and fatigue. Eye aspect ratio (EAR) is used to detect drowsiness by measuring the ratio of distances between horizontal and vertical eye landmarks. Yawn detection is performed by calculating a YAWN value based on the distance between the upper and lower lips and comparing it to a threshold value. The system incorporates an eSpeak module, a text-to-speech synthesizer, to provide appropriate voice alerts when drowsiness or yawning is detected. The ultimate goal of the proposed system is to reduce the number of fatalities resulting from road accidents and contribute to technology advancements. Keywords: Drowsiness, eSpeak module, Eye aspect ratio, Yawn Detection.

In recent studies, drowsiness of drivers while driving is seen as one of the most important causes of deaths due to traffic accidents. Therefore, in this study, an algorithm that determines driver fatigue by examining the driver's eye conditions in real-time is proposed. Python versions of OpenCV (Open Source Computer Vision Library) and machine learning libraries were used to create this proposed algorithm. In the study, the face and eyes were detected with the Cascade classifier using Haar features. Detected eyes were classified as “open” “closed” or “half open” with the model trained by the SVM (Support Vector Machine) method according to the HOG (Histogram of Oriented Gradient) feature descriptor. Driver fatigue was decided according to the PERCLOS (Percentage of Eyelid Closure) method, which examines the percentage of eyelid closure over time. In the proposed system, fatigue was detected according to the time the driver's eyes were in the “half-open” or “closed” state, and a related user interface was designed and audio and visual warnings were given to the driver.

A computer vision-based system called the Drowsiness Sensing Device using OpenCV was designed to identify driver drowsiness. The technology uses video frames from a camera positioned inside a car to identify different sleepiness indicators, including the length of eye closure and head position. The Eye Aspect Ratio (EAR), which aids in trying to assess drowsiness, is determined using the OpenCV library, which is also used to extract feature points and detect eye blinks. The system also has an alarm mechanism that sounds when a certain level of drowsiness is attained, alerting the driver to take the appropriate action. The proposed approach can be possibly employed to reduce the number of accidents occurred due to driver drowsiness. The suggested system is a real-time drowsiness sensing system that makes use of OpenCV to gauge a person's level of drowsiness. The technology employs a camera to take pictures of the driver's face, assessing the features like the mouth and eyes to determine how sleepy they are. The system can identify drowsiness by noticing changes in the eyes, such as drooping eyelids, and mouth movements, such as yawning. When the amount of drowsiness surpasses a predetermined threshold, the system informs the driver by assessing the photos using machine learning techniques. By prompting the driver to take a break, the proposed technology may help prevent accidents brought on by drowsy driving.

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.

Autonomous Vehicles (AVs) are being promoted as an emerging technology with the potential to improve traffic efficiency and safety. However, the scarcity of publicly available AV crash data contributes to a limited understanding of safety issues for deploying AVs. To gain a deeper understanding of the factors contributing to AV crashes, this study created a unique dataset by combining 445 intersection AV crashes from the California Department of Motor Vehicles with detailed roadway geometric and traffic characteristic data. To address the issue of imbalanced data, the Borderline synthetic minority oversampling technique (BL-SMOTE) was utilized in this study. A framework for analyzing AV crash types at intersections was also developed using the Categorical gradient boosting (Catboost) and Bayesian networks (BNs) models. The results show that inappropriate vehicle maneuvers, such as sudden lane changes or speed control, can increase the likelihood of an AV being involved in a sideswipe crash. Additionally, in scenarios where the AADT of the major road is lower, AVs are more prone to rear-end crashes when proceeding. These findings can provide valuable insights for creating safety management strategies in different situations and improve the development of innovative car warning technologies, such as rear-end collision warnings.

Road traffic accidents are a major global challenge, causing significant public health and economic burdens. In Saudi Arabia, the rapid increase in motorization and urbanization has led to one of the world's highest traffic fatality rates. This study examines the effectiveness of the SAHER traffic enforcement system in the Dammam Metropolitan Area (DMA) using insights from 23 road safety experts through structured questionnaires and interviews. The analysis highlights that SAHER has improved compliance with traffic laws and enhanced road safety perceptions but remains limited in its scope and coverage. Key findings identify driver distractions, speeding, and sudden lane changes as the leading causes of accidents, with younger drivers disproportionately involved. Experts emphasize the need for enhancements to SAHER, including increasing the number and strategic rotation of cameras, addressing additional violations such as aggressive driving, and improving coverage near schools and high-pedestrian areas. Recommendations include integrating SAHER into future urban planning, combining automated enforcement with public education campaigns, and improving traffic infrastructure, such as signage and signal operations. This study provides valuable insights into the role of automated enforcement in improving road safety and offers actionable strategies for policymakers to address traffic-related challenges and promote sustainable urban mobility in Saudi Arabia.

Reinforcement learning (RL) offers a powerful paradigm for adaptive motion planning in complex driving environments. However, applying RL to autonomous driving remains challenging due to uncertainty from partial observability and the stochastic, multimodal behaviors of traffic participants. This paper presents a novel risk-aware RL framework for non-conservative motion planning under uncertainty. By integrating Partially Observable Markov Decision Processes (POMDP) with a deep RL-based policy optimization scheme, the proposed approach explicitly models aleatoric uncertainty via a Gaussian Mixture Bayesian Belief Updater and a time-varying risk field. Additionally, an Adaptive Context-aware Attention (ACA) module is employed to prioritize critical targets for enhanced interaction modeling dynamically. Extensive experiments on the CARLA simulator show that the framework generalizes well across diverse traffic conditions, improving average reward by 65.74% and 64.02% in low-speed dense and high-speed sparse scenarios. It remains robust in challenging situations such as overtaking and sudden lane changes in the PeMS dataset. Furthermore, distributed deployment tests confirm a real-time performance of 10 Hz on a hardware-in-the-loop platform, demonstrating the feasibility of practical deployment.