Driver Drowsiness Detection Research Articles

Fatigue Driving Detection Method Based on IPPG Technology

Physiological signal index can accurately reflect the degree of fatigue, but the contact detection method will greatly affect the driver's driving. This paper presents a non-contact method for detecting tired driving. It uses cameras and other devices to collect information about the driver's face. By recording facial changes over a period and processing the captured video, pulse waves are extracted. Then the frequency domain index and nonlinear index of heart rate variability were extracted by pulse wave characteristics. Finally, the experiment proves that the method can clearly judge whether the driver is tired. In this study, the Imaging Photoplethysmography (IPPG) technology was used to realise non-contact driver fatigue detection. Compared with the non-contact detection method through identifying drivers' blinking and yawning, the physiological signal adopted in this paper is more convincing. Compared with other methods that detect physiological signals to judge driver fatigue, the method in this paper has the advantages of being non-contact, fast, convenient and available for the cockpit environment.

Efficient and Robust Driver Fatigue Detection Framework Based on the Visual Analysis of Eye States

Fatigue detection based on vision is widely employed in vehicles due to its real-time and reliable detection results. With the coronavirus disease (COVID-19) outbreak, many proposed detection systems based on facial characteristics would be unreliable due to the face covering with the mask. In this paper, we propose a robust visual-based fatigue detection system for monitoring drivers, which is robust regarding the coverings of masks, changing illumination and head movement of drivers. Our system has three main modules: face key point alignment, fatigue feature extraction and fatigue measurement based on fused features. The innovative core techniques are described as follows: (1) a robust key point alignment algorithm by fusing global face information and regional eye information, (2) dynamic threshold methods to extract fatigue characteristics and (3) a stable fatigue measurement based on fusing percentage of eyelid closure (PERCLOS) and proportion of long closure duration blink (PLCDB). The excellent performance of our proposed algorithm and methods are verified in experiments. The experimental results show that our key point alignment algorithm is robust to different scenes, and the performance of our proposed fatigue measurement is more reliable due to the fusion of PERCLOS and PLCDB.

Fatigue Detection Through Car Driver’s Face Using Boosting Local Binary Patterns

The general population is concerned with traffic accidents. Driver fatigue is one of the leading causes of car accidents. Several factors, including nighttime driving, sleep deprivation, alcohol consumption, driving on monotonous roads, and drowsy and fatigue-inducing drugs, can contribute to fatigue. This study proposes a facial appearance-based driver fatigue detection system. This is based on the assumption that facial features can be used to identify driver fatigue. We categorize driver conditions into three groups: normal, talking, and yawning. In this study, we used Adaboost to propose Boosting Local Binary Patterns (LBP) to improve the image features of fatigue drivers in the Support Vector Machine (SVM) model. The experimental results indicate that the system's optimal performance achieves an accuracy value of 93.68%, a recall value of 94%, and a precision value of 94%.
 

Exploring contributing factors to improper driving actions in single-vehicle work zone crashes: A mixed logit analysis considering heterogeneity in means and variances, and temporal instability

A work-zone introduces unexpected conditions for road users and may cause severe safety issues. This study aims to understand drivers’ pre-crash improper actions, which are the major contributing factor to the crash occurrence and outcomes severity in single-vehicle (SV) work-zone crashes. A mixed logit model with heterogeneity in mean and variance was developed using Florida’s seven-year work-zone crash data. The estimated models investigated five pre-crash improper actions (no contributing action, careless driving, speeding, swerving lanes, and other pre-crash actions) in SV work-zone crashes. Year-paired likelihood ratio tests identified temporal instability existing in the dataset over the study period and suggested yearly model estimation to capture the temporal instability. The model results identified a wide range of variables that impact drivers’ pre-crash improper actions, such as driver and weather conditions, work-zone type, and temporal and lighting characteristics. The findings of this study imply that driving psychology plays a critical role in safety-related driving behaviors in work-zone areas. Engineering or education countermeasures that could increase driver alertness of potential hazards are suggested to reduce improper actions by drivers and improve work-zone safety.

Facial feature fusion convolutional neural network for driver fatigue detection

Driver fatigue detection is critical for preventing traffic accidents. However, in real driving scenarios, low-quality input situations often occur due to occlusion, large-turn head deformation, and inconsistent eye states, which introduce noise and degrade the performance of single-stream networks. To address this, we propose a multi-stream facial feature fusion convolution neural network (FFF–CNN) that enhances performance on low-quality inputs. The FFF-CNN includes a global face stream and two local eye streams, with feature fusion used for eye state classification. To facilitate feature fusion, we implemented two preprocessing modules, the feature attention module (FAM) and the stream interaction module (SIM). FAM emphasizes important features in the global face stream, while SIM corrects information from the two local eye streams. The proposed FFF-CNN achieved good performance on both our dataset and the public Closed Eyes in the Wild (CEW) dataset. Compared to single-stream networks, the FFF-CNN improved performance by 4.95% and 4.27% on our dataset and the CEW dataset, respectively. Furthermore, it achieved state-of-the-art performance on the CEW dataset with an accuracy of 98.35%. The effectiveness of the proposed FAM and SIM has been verified by experiments. Notably, our experimental results show that the proposed FFF-CNN effectively improved fatigue detection performance on low-quality input, approaching the performance on normal situations.

Detecting slow eye movements using multi-scale one-dimensional convolutional neural network for driver sleepiness detection

Background:Slow eye movements (SEMs), which occurs during eye-closed periods with high time coverage rate during simulated driving process, indicate drivers’ sleep onset. New Method:For the multi-scale characteristics of slow eye movement waveforms, we propose a multi-scale one-dimensional convolutional neural network (MS-1D-CNN) for classification. The MS-1D-CNN performs multiple down-sampling processing branches on the original signal and uses the local convolutional layer to extract the features for each branch. Results:We evaluate the classification performance of this model on ten subjects’ standard train–test datasets and continuous test datasets by means of subject-subject evaluation and leave-one-subject-out cross validation, respectively. For the standard train–test datasets, the overall average classification accuracies are about 99.1% and 98.6%, in subject-subject evaluation and leave-one-subject-out cross validation, respectively. For the continuous test datasets, the overall average values of accuracy, precision, recall and F1-score are 99.3%, 98.9%, 99.5% and 99.1% in subject-subject evaluation, are 99.2%, 98.8%, 99.3% and 99.0% in leave-one-subject-out cross validation. Comparison with existing method:Results of the standard train–test datasets show that the overall average classification accuracy of the MS-1D-CNN is quite higher than the baseline method based on hand-designed features by 3.5% and 3.5%, in subject-subject evaluation and leave-one-subject-out cross validation, respectively. Conclusions:These results suggest that multi-scale transformation in the MS-1D-CNN model can enhance the representation ability of features, thereby improving classification accuracy. Experimental results verify the good performance of the MS-1D-CNN model, even in leave-one-subject-out cross validation, thus promoting the application of SEMs detection technology for driver sleepiness detection.

Fatigue in transportation operations: A contextual factors survey among Iranian suburban drivers.

Fatigue, as a persistent and serious occupational hazard, plays an important role in traffic accidents by reducing the driver's ability to maneuver with the vehicle and increasing the likelihood of falling asleep at the wheel. The purpose of this study was to identify the individual contextual factors, sleep condition, lifestyle, job characteristics, environmental, and economic conditions that affect the fatigue and alertness of Iranian suburban bus drivers. A questionnaire-based cross-sectional survey was used for this study. Non-probability sampling was used to study 401 suburban bus drivers from Tehran province, Iran, ranging in age from 24 to 67 years. The SPSS22 statistical software V27 was used for the analysis. Approximately half of the participants (50.5%) had experienced fatigue while driving in the previous six months. According to a logistic regression analysis, the contextual factors were all independently related to falling asleep and fatigue while driving. This study provides a thorough understanding of the contextual factors related to drowsy driving and emphasizes the importance of taking these things into consideration when developing interventions aimed at improving the driver's wellbeing and health and lowering the risk of errors and accidents.

Effect of distance information and number of warning signs on driving safety of young adults near road work zones in China

The continuous growth of automobile ownership and road mileage in China has brought a lot of road maintenance work. The work zone shall be set for road maintenance work. Due to the road characteristics near the work zone, more accidents and a higher accident risk exist. Traffic signs are one of the essential means to ensure traffic safety. The location and number of road work signs (sign level) play a crucial role in driver safety near the work zone. The repeated road work signs can form a warning system to regulate driver behavior. This paper evaluates the effect of the number of warning signs with and without distance information on driver behavior (psychological load and physiological characteristics) near the work zone. The matter-element extension model is used for comprehensive evaluation. The study resulted in several findings. First, adding distance information improves the difficulty and time of visual recognition and enhances driver alertness. On the other hand, too many road signs are not conducive to maintaining driver alertness. Second, distance information on the work signs and the repeated setting of road warning signs add extra burden on the driver and increase driver fatigue. Third, driver's response to the repeated road work signs will gradually become stable; The speed transition under the warning signs Levels 2 and 3 are more stable than that under the warning sign Levels 1 and 4. Finally, the warning sign level shall not be more than 3. If the advanced warning area is short, it is recommended to select a warning sign Level 1. If the advanced warning area is relatively long, it is recommended to choose a warning sign Level 2. Finally, adding distance information will improve the overall effect of the warning scheme. These findings can provide a valuable reference for setting the road work signs near the work zone in practice in China.

Real Time Alert System for Slumberous and Fatigue Driver Using Eye Blink Sensor

Various technologies are being created to reduce accidents, which are rising rapidly in the modern day. Driver weariness or drowsiness is a significant factor in the occurrence of accidents. Drowsiness is detected using a variety of deep learning and image processing techniques. However, these techniques are pricey, and they might not work for those who wear glasses. This suggested solution employs an eye blink sensor to stop drowsiness-related accidents. This serves as an accident avoidance mechanism. The eye blink sensor-equipped goggles that the driver is required to wear include these features.To detect driver drowsiness, the goggles must be worn by the driver the entire time they are operating a vehicle and must blink for a few seconds. When the alarm system detects that the driver is dozing off, it will sound an alert until they open their eyes. Along with detecting drowsiness, the LDR sensor is used to control the high intensity of the headlights when two vehicles are approaching from opposite directions. Additionally, it helps to avoid accidents caused by blurry vision. When a driver snoozes more than five times, the GSM modem alerts the vehicle's owner. In this situation, the both owner and the driver could be alerted when the driver is drowsy.

Driver Drowsiness Detection Using Deep Learning

Abstract: The main reason for accidents worldwide is the sleepiness experienced by individuals operating vehicles. Fatigue and drowsiness are prevalent among numerous drivers due to insufficient rest and tiredness. The most effective approach to preventing road accidents resulting from drowsiness is to provide advance warnings to the driver. There are plentiful techniquesto detect drowsiness. The project, driver drowsiness detection using deep learning is implemented using a convolution neural network(CNN), an approach of deep learning. In this project first, we capture a person’s face with the help of a web camera after which with the help of the deep learning algorithm we predict if the person is drowsy or not. If the person is detected as drowsyit immediately rings an alarm to alert the person along with a warning voice message. The prime goal of this project is to alert drowsy people before the cause of accidents which helps us in preventing the cause of road due to drowsiness of the person

Driver Drowsiness Detection using Artificial Intelligence

The goal of the research is to show how artificial intelligence may be used to identify driver tiredness using visual processing. Experts estimate that over a quarter of all serious car accidents are brought on by drivers who are too sleepy to pay attention to the road. As a result, we know that tiredness is a more common contributor to car accidents than intoxication. Vision-based ideas were used to design the Drowsiness Detection System. The gadget relies on a small camera to detect drowsiness in drivers by examining their eyes and scanning their face. The Viola-Jones and Hough transform are the techniques utilised by the system to first scan the driver's face, then the eyes, and then check whether the eyes are open or closed using artificial intelligence software. The system works with binary pictures to scan the sides of the face, reducing the space where the eyes will be located. Let's say that the eyes are shown to be closed for five or more consecutive frames. When this occurs, the system tracks the driver's level of activity and determines that the driver is dozing off, so it sounds an alert or produces an alarm signal to wake him up.

Vigilance Decrement During On-Road Partially Automated Driving Across Four Systems.

This study uses a detection task to measure changes in driver vigilance when operating four different partially automated systems. Research show temporal declines in detection task performance during manual and fully automated driving, but the accuracy of using this approach for measuring changes in driver vigilance during on-road partially automated driving is yet unproven. Participants drove four different vehicles (Tesla Model 3, Cadillac CT6, Volvo XC90, and Nissan Rogue) equipped with level-2 systems in manual and partially automated modes. Response times to a detection task were recorded over eight consecutive time periods. Bayesian analysis revealed a main effect of time period and an interaction between mode and time period. A main effect of vehicle and a time period x vehicle interaction were also found. Results indicated that the reduction in detection task performance over time was worse during partially automated driving. Vehicle-specific analysis also revealed that detection task performance changed across vehicles, with slowest response time found for the Volvo. The greater decline in detection performance found in automated mode suggests that operating level-2 systems incurred in a greater vigilance decrement, a phenomenon that is of interest for Human Factors practitioners and regulators. We also argue that the observed vehicle-related differences are attributable to the unique design of their in-vehicle interfaces.

An EEG Channel Selection Framework for Driver Drowsiness Detection via Interpretability Guidance.

Drowsy driving has a crucial influence on driving safety, creating an urgent demand for driver drowsiness detection. Electroencephalogram (EEG) signal can accurately reflect the mental fatigue state and thus has been widely studied in drowsiness monitoring. However, the raw EEG data is inherently noisy and redundant, which is neglected by existing works that just use single-channel EEG data or full-head channel EEG data for model training, resulting in limited performance of driver drowsiness detection. In this paper, we are the first to propose an Interpretability-guided Channel Selection (ICS) framework for the driver drowsiness detection task. Specifically, we design a two-stage training strategy to progressively select the key contributing channels with the guidance of interpretability. We first train a teacher network in the first stage using full-head channel EEG data. Then we apply the class activation mapping (CAM) to the trained teacher model to highlight the high-contributing EEG channels and further propose a channel voting scheme to select the top N contributing EEG channels. Finally, we train a student network with the selected channels of EEG data in the second stage for driver drowsiness detection. Experiments are designed on a public dataset, and the results demonstrate that our method is highly applicable and can significantly improve the performance of cross-subject driver drowsiness detection.

Real-Time Deep Learning-Based Drowsiness Detection: Leveraging Computer-Vision and Eye-Blink Analyses for Enhanced Road Safety.

Drowsy driving can significantly affect driving performance and overall road safety. Statistically, the main causes are decreased alertness and attention of the drivers. The combination of deep learning and computer-vision algorithm applications has been proven to be one of the most effective approaches for the detection of drowsiness. Robust and accurate drowsiness detection systems can be developed by leveraging deep learning to learn complex coordinate patterns using visual data. Deep learning algorithms have emerged as powerful techniques for drowsiness detection because of their ability to learn automatically from given inputs and feature extractions from raw data. Eye-blinking-based drowsiness detection was applied in this study, which utilized the analysis of eye-blink patterns. In this study, we used custom data for model training and experimental results were obtained for different candidates. The blinking of the eye and mouth region coordinates were obtained by applying landmarks. The rate of eye-blinking and changes in the shape of the mouth were analyzed using computer-vision techniques by measuring eye landmarks with real-time fluctuation representations. An experimental analysis was performed in real time and the results proved the existence of a correlation between yawning and closed eyes, classified as drowsy. The overall performance of the drowsiness detection model was 95.8% accuracy for drowsy-eye detection, 97% for open-eye detection, 0.84% for yawning detection, 0.98% for right-sided falling, and 100% for left-sided falling. Furthermore, the proposed method allowed a real-time eye rate analysis, where the threshold served as a separator of the eye into two classes, the "Open" and "Closed" states.

A High Performance and Robust FPGA Implementation of a Driver State Monitoring Application.

A high-performance Driver State Monitoring (DSM) application for the detection of driver drowsiness is presented in this paper. The popular Ensemble of Regression Trees (ERTs) machine learning method has been employed for the alignment of 68 facial landmarks. Open-source implementation of ERTs for facial shape alignment has been ported to different platforms and adapted for the acceleration of the frame processing speed using reconfigurable hardware. Reducing the frame processing latency saves time that can be used to apply frame-to-frame facial shape coherency rules. False face detection and false shape estimations can be ignored for higher robustness and accuracy in the operation of the DSM application without sacrificing the frame processing rate that can reach 65 frames per second. The sensitivity and precision in yawning recognition can reach 93% and 97%, respectively. The implementation of the employed DSM algorithm in reconfigurable hardware is challenging since the kernel arguments require large data transfers and the degree of data reuse in the computational kernel is low. Hence, unconventional hardware acceleration techniques have been employed that can also be useful for the acceleration of several other machine learning applications that require large data transfers to their kernels with low reusability.

Driver Drowsiness Detection and Alert System Implemented on Web

Driver Drowsiness Detection and Alert System Implemented on Web

Driver fatigue detection and human-machine cooperative decision-making for road scenarios

Driver fatigue detection and human-machine cooperative decision-making for road scenarios

A CNN-Based Approach for Driver Drowsiness Detection by Real-Time Eye State Identification

Drowsiness detection is an important task in road safety and other areas that require sustained attention. In this article, an approach to detect drowsiness in drivers is presented, focusing on the eye region, since eye fatigue is one of the first symptoms of drowsiness. The method used for the extraction of the eye region is Mediapipe, chosen for its high accuracy and robustness. Three neural networks were analyzed based on InceptionV3, VGG16 and ResNet50V2, which implement deep learning. The database used is NITYMED, which contains videos of drivers with different levels of drowsiness. The three networks were evaluated in terms of accuracy, precision and recall in detecting drowsiness in the eye region. The results of the study show that all three convolutional neural networks have high accuracy in detecting drowsiness in the eye region. In particular, the Resnet50V2 network achieved the highest accuracy, with a rate of 99.71% on average. For better visualization of the data, the Grad-CAM technique is used, with which we obtain a better understanding of the performance of the algorithms in the classification process.

A Product Fuzzy Convolutional Network for Detecting Driving Fatigue.

Existing driving fatigue detection methods rarely consider how to effectively fuse the advantages of the electroencephalogram (EEG) and electrocardiogram (ECG) signals to enhance detection performance under noise conditions. To address the issues, this article proposes a new type of the deep learning (DL) framework based on EEG and ECG called the product fuzzy convolutional network (PFCN). It should be noted that this article first investigates how to fuse EEG and ECG signals to deal with driving fatigue detection under noise conditions in both simulated and real-field driving environments. Specifically, the PFCN includes three subnetworks. The first uses a fuzzy neural network (FNN) with feedback and a product layer, effectively capturing the particularity and temporal variation of high-dimensional EEG signals and reducing the time-space complexity. The second subnetwork uses a 1-D convolution to convert the ECG data into feature sequences, providing high accuracy and low computational complexity in ECG data classification. The third subnetwork proposes a fusion-separation mechanism to effectively fuse the extracted ECG and EEG features, suppressing the noise interference and ensuring higher detection accuracy. To evaluate the performance of PFCN, a series of experiments has been set up in both simulated and real-field driving environments. The results indicate that the proposed PFCN model has better robustness and detection accuracy compared with several mainstream fatigue detection models.

The Effectiveness of a Drowsiness Detection System in Reducing Drowsy Driving Accidents

Abstract: The identification of drowsiness is critical for human-computer interaction and transportation safety. We present a unique approach that combines physiological and behavioural markers to identify drowsiness in real time. A camera, an electroencephalogram (EEG), and a body-worn accelerometer are all part of our system. To identify tiredness based on changes in the eyes and head, the camera collects face pictures and extracts information such as eye aspect ratio and head position. The EEG examines brain activity, detecting tiredness based on changes in brain activity by extracting components such as alpha and theta waves. The body-worn accelerometer detects tiredness by measuring body motions and extracting information such as body acceleration and angular velocity. We propose an ensemble technique for improving overall accuracy by combining the outputs of many classifiers. When we tested our system on a dataset of participants, it detected drowsiness with 96.5% accuracy, beating state-of-the-art approaches.