Driver Drowsiness Detection and Alert System Development Using Object Detection

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.

The most important aspect of automatic driving and traffic surveillance is vehicle detection. In addition, poor road conditions caused by potholes are the cause of traffic accidents and vehicle damage. The proposed work uses deep learning models. The proposed method can detect vehicles and potholes using images. The faster region-based convolutional neural network (CNN) and the inception network V2 model are used to implement the model. The proposed work compares the performance, accuracy numbers, detection time, and advantages and disadvantages of the faster region-based convolution neural network (Faster R-CNN) with single shot detector (SSD) and you only look once (YOLO) algorithms. The proposed method shows good progress than the existing methods such as SSD and YOLO. The measure of performance evaluation is Accuracy. The proposed method shows an improvement of 5% once compared with the previous methods such as SSD and YOLO.

A generative adaptive convolutional neural network with attention mechanism for driver fatigue detection with class-imbalanced and insufficient data

In this study, statistical features of traffic accidents in Northern Cyprus (TRNC) especially for the last decade were examined. Such that, risk factors (causes) of traffic accident and their demographic reflections were identified by evaluating official statistics. The main findings of this study are these: Fast driving as the most important cause of traffic accidents; Straight road as the chief location of severe traffic accidents; Inverse relationship between the severe traffic accidents and driver's licenses period (experience); and Inverse relationship between the severe traffic accidents and the age of accused persons.

Every year, traffic congestion and traffic accidents have been rapidly increasing in proportion to increasing number of vehicles. Although the roadway design and signal system have been improved to relieve traffic congestion, traffic casualties and property damage do not decrease. The traffic accident is a serious issue of society because vehicle is a primary means of transportation. This paper develops a real-time traffic accident detection system (RTADS): This system helps us to cope with accidents and discover the causes of traffic accident by detecting the accident. We gathered video data recorded at several intersections and used them to detect accidents at different intersections which have different traffic flow and intersection design. However, because the data gathered from intersections have incompleteness, uncertainty and complicated causal dependency between them, we construct probability-based networks which calculate based on the probability for correct accident detection. This system instantly sends the detected result to managers using accident alarm system. RTADS features real time accident detection and analysis of the cause of accidents. In performance evaluation, the proposed system achieved a detection rate of 97% with a correct detection rate of 92% and a false alarm rate of 0.77%.

Fatigue driving is one of the main causes of traffic accidents today. In this study, a fatigue driving detection system based on a 3D convolutional neural network combined with a channel attention mechanism (Squeeze-and-Excitation module) is proposed. The model obtains information of multiple channels of grayscale, gradient and optical flow from the input frame. The temporal and spatial information contained in the feature map is extracted by three-dimensional convolution, after which the feature map is fed to the attention mechanism module to optimize the feature weights. EAR and MAR are used as fatigue analysis criteria and, finally, a full binary tree SVM classifier is used to output the four driving states. In addition, this study uses the frame aggregation strategy to solve the frame loss problem well and designs application software to record the driver’s status in real time while protecting the driver’s facial privacy and security. Compared with other classical fatigue driving detection methods, this method extracts features from temporal and spatial dimensions and optimizes the feature weights using the attention mechanism module, which significantly improves the fatigue detection performance. The experimental results show that 95% discriminative accuracy is achieved on the FDF dataset, which can be effectively applied to driving fatigue detection.

The high impact of traffic accidents makes it imperative to formulate public policies to reduce their occurrence. In this task, knowing the cause of accidents is of paramount importance. The use of data mining and big data adapts to the complexity of the phenomenon under study. In order to classify some possible causes of traffic accidents, we built a data model to describe the behavior and dynamic of the participant agents in the traffic accident event in Colombia. This paper presents the application of MLP and Naive Bayes algorithms to identify the possible immediate cause and the rules decision algorithm PART for the root cause of traffic accidents. Models have been tested aiming to obtain the goodness of fit by increasing metrics like Recall, Precision, ROC and Kappa index, and minimize the RMSE.

In recent years, fatigue driving has become the main cause of traffic accidents, leading to increased attention towards fatigue detection systems. However, the pooling and strided convolutional operations in fatigue detection algorithm based on traditional deep learning methods may led to the loss of some useful information. This paper proposed a novel -shaped convolutional network ( ) aiming to address this issue. Unlike traditional network structures, incorporates the operations of upsampling features and concatenating high- and low-level features, enabling full utilization of useful information. Moreover, considering that the fatigue state is a mental state involving temporal evolution, we proposed the novel long short-term memory (LSTM)- -shaped convolutional network (LSTM- ), a parallel structure composed of LSTM and for fatigue detection, where extracts time-invariant features with location information, and LSTM extracts long temporal dependencies. We compared LSTM- with six competing methods based on two datasets. Results showed that the proposed algorithm achieved higher classification accuracy than the other methods, with 94.25% on EEG data (binary classification) and 82.19% on EOG data (triple classification). Additionally, the proposed algorithm exhibits low computational cost, good training stability, and robustness against insufficient training. Therefore, it is promising for further implementation of fatigue online detection systems.

With the rapid growth of the number of motor vehicles, road traffic accidents are becoming more and more serious. Fatigue driving has become one of the main causes of traffic accidents. It is particularly critical to find effective solutions to fatigue driving. At present, the academic community believes that the phenomenon of fatigue driving can be controlled by means of prevention and intervention. In terms of intervention countermeasures, using sound stimulation as a wake-up method has the advantages of easy implementation and significant effect, which has become the research focus in the driving fatigue mitigation scheme. Through the establishment of a simulation driving platform, driving fatigue detection system and driving fatigue wake-up system in the laboratory, the experimental research is carried out to study the fatigue generation of drivers in different emotional types of music environment and the effectiveness of wake-up countermeasures. Three sound environments were constructed in the experiment, which were driving noise environment, positive emotional music mixed with driving noise environment and negative emotional music mixed with driving noise environment. The subjects were tested in three sound environments in turn. When entering fatigue, they were given no stimulation, positive emotional music stimulation or negative emotional music stimulation according to the experimental design. The experimental results were obtained after considering the subjective evaluation questionnaire and the experimental data analysis based on pupil diameter variation coefficient, average blink rate and other indicators. The experimental results show that when driving for a long time, the driver will enter the fatigue state regardless of whether the driving background has different emotional music. The driver's fatigue depth in the positive emotional music environment is shallower than that in the negative emotional music environment and the music-free environment; there is no significant difference in the degree of fatigue between the driver 's fatigue in the negative emotional music environment and the fatigue in the absence of music environment. In the comparison of music arousal stimuli with different emotions, the introduction of positive emotional music as arousal stimulus has the best effect.

In Indonesia, traffic accidents occur on 23.55% of national roads and 75.08% of rural roads. The rural roads were identified as accident-prone areas. As a result, unsafe roads hinder population mobility, disrupt daily life, and reduce access to education, employment, and essential services, thereby affecting the well-being and development of rural communities. To identify the dominant factors that influence the frequency of collisions, a more thorough analysis of the multifactorial causes of traffic accidents in accident-prone areas is necessary. This study focused on analyzing the factors that contribute to road traffic accidents. Cross-tabulation was done using chi-square analysis. The chisquare test does not assume a normal distribution of data, which is beneficial when dealing with real-world data that may not follow normal distribution patterns. This flexibility makes it a robust choice for analyzing traffic accident data, which can be highly variable and not normally distributed. The results of the chi-square analysis for significance values below 0.05 indicate that there is a correlation between accident-causing factors (the independent variable) and collision frequency (the dependent variable). The results indicate that human factors, such as carelessness and high speed, as well as road and environmental factors, such as horizontal alignment, road width, clear zone, road signs, road markings, and land use, influence traffic accidents. Infrastructure factors such as horizontal alignment, road width, clear zones, shoulders, signs, and markings influence traffic accidents because they directly impact road user safety. Non-standard road geometry (horizontal alignment, road width, shoulder width, and clear zone) combined with incomplete road safety facilities (signs and markings) have the potential to cause traffic accidents. Therefore, harmonizing road geometry and equipment is necessary to improve arterial road safety, especially in accident-prone areas. Furthermore, speed management across a variety of land uses is required to reduce traffic accidents.

Tiredness, and sleeping of the drivers while driving is one of the main causes of traffic accidents. Observations of the drivers to detect tiredness and fatigue is a complex task which includes behavioral and physical elements. Different approaches were made, including computer vision with the ability to track and monitor the drivers behind the wheel without the intervention in the driving. The proposed system can observe the alertness or tiredness of drivers in order to prevent them from sleeping while driving. In this work, a framework is developed to detect the fatigue-ness from tracking the cornea of eyes by focusing on the face of the driver. It utilizes applying image morphological changes like dilution, erosion, image segmentation like background elimination and Circular Hough Transform (CHT) to detect cornea of an eye on the captured images on drivers. Whenever the fatigue is recognized it will buzz an alarm at the system and necessary actions can be taken. It additionally decreases incorrect outcomes of by disposing of low-quality faces that happened to a video sequence because of issues in sensible lighting, head movement, and posture variety.

Road traffic accidents constitute the primary cause of fatalities associated with injuries and engender substantial economic ramifications for affected individuals, their families, and entire nations. The Sultanate of Oman, like other countries, suffers from traffic accident injuries and traffic congestion. The accident rate for the period 2021 was recorded as one accident every six hours. Despite a 70% increase in total number of vehicles and an 81% rise in licensed drivers between 2012 and 2019, data on traffic accidents demonstrate an improving trend with a notable 55% decline in crash fatalities. However, it is important to recognize that road traffic accidents in Oman encompass not only social issues but also pose a significant economic burden, resulting in substantial financial costs for the nation. Notwithstanding, it was discovered that more than 50% of fatal crashes in Oman were primarily caused by excessive speeding. The main goal of this research is to analysis the causes and trends of traffic accidents at the national level in the Sultanate of Oman. Data analysis reveals speed as the primary cause of traffic accidents in Oman, with Muscat and Dhofar registering the highest accident rates. In addition, the distribution of deaths and injuries resulting from accidents varies according to Gender and nationality. According to the road accident scenario analysis in the state, more traffic accidents occurred in males than females. Traffic accidents have witnessed a notable decline over the past decade, attributable to the diligent efforts and interventions implemented by the Royal Oman Police.

Traffic accidents are caused by road, vehicle and human factors, the latter one causing, either by itself or associated with other factors, more than 90% of car accidents. There are three types of human errors: errors in perception, attention and memory. The study included thirty healthy drivers, aged 28-40, with 500 km driven per a week, who had caused at least one traffic accident, but not being intoxicated by alcohol or drugs during the accident. The same number of controls were included. Both the cases and controls were interviewed. We found no difference regarding the marital status, education, conflicts with family members or problems at work, frequency of using the car, speed and habit of fastening seat belts among car drivers who had caused traffic accidents and those who had not. However, we did find significant differences in the frequency of alcohol consumption in general and before driving. Car drivers who had caused traffic accidents used alcohol regularly in greater percentage than those drivers who had not caused any accident--i.e. not a single control claimed to use alcohol regularly. A statistically significant difference was also recorded in alcohol consumption immediately before driving. Such results had been expected, bearing in mind the influence of alcohol on the time needed by drivers to react in emergency. Alcohol consumption is an important factor causing traffic accidents. Since drivers included in our study did not cause a road accident after consuming alcohol, we have found that alcohol consumption, both regular and just before driving, is an important cause of traffic accidents.

Accident Prone System is an accident detection model with an object detection algorithm as its backbone. Object detection algorithms are an integral part of the deep learning. The proposed system aims for optimal automatic post-accident recovery, by deploying the latest open-source computational technology at hand, in the surveillance and dash cameras to detect accidents in real time. Attempts have been made previously where algorithms such as clustering, deep neural networks and Regional CNN have been used to create accident detection models but either they weren't able to achieve efficiency or real time detection speed or both. The proposed system uses the latest algorithm at hand and a comparative study is presented by implementing accident detection models with algorithms such as Single Shot Detector (SSD) and You Only Look Once (YOLO) which are way faster than traditional algorithms and also much efficient than its predecessors. Thus, the proposed system can be deployed for real time accident detection and help save life by faster post-accident recovery.

Driver fatigue is one of the main causes of frequent traffic accidents. In this case, driver fatigue detection system has very important significance in avoiding traffic accidents. This paper presents a real-time method based on fusion of multiple facial features, including eye closure, yawn and head movement. The eye state is classified as being open or closed by a linear SVM classifier trained using HOG features of the detected eye. The mouth state is determined according to the width-height ratio of the mouth. The head movement is detected by head pitch angle calculated by facial landmark. The driver’s fatigue state can be reasoned by the model trained by above features. According to experimental results, drive fatigue detection obtains an excellent performance. It indicates that the developed method is valuable for the application of avoiding traffic accidents caused by driver’s fatigue.