Driver Safety Systems Research Articles

A review on recent driver safety systems and its emerging solutions

Road safety and accident prevention are critical concerns in modern transportation. This paper presents a comprehensive survey of driver safety systems, focusing on the latest advancements in this field. We analyze the existing literature to identify key research trends in driver safety systems, encompassing various categories of solutions. Our survey delves into the reasons behind road accidents and assesses the effectiveness of emerging technologies and solutions in accident prevention. By categorizing and evaluating these solutions based on the Internet of Things and Machine Learning, we provide valuable insights into the landscape of road accident detection and prevention systems. This survey not only highlights the current state of the art but also serves as a reference for future research and innovation in the domain of driver safety. Abbreviations IoT: Internet of things; CNN: Convolutional Neural Network; SVM: Support vector machine; HRV: Heart rate variability; RRI: R-R Interval; MSPC: Multivariate Statistical process control; EAR: Eye aspect ratio; HUD: Head-up display; GPS: Global positioning system; CAN: Controller area network; GPU: Graphics processing unit; IR: Infrared; GSM: Global system for mobile communication; EEG: Electroencephalogram; PCA: Principal component analysis; SVC: Support vector classifier; SdsAEs: Stacked denoising sparse autoencoders; ECG: Electrocardiogram; LED: Light emitting diode; NFC: Near field communication; PSO: Personal security officer; PPG: Photoplethysmography; EDA: Electrodermal activity; EMG: Electromyography; LCD: Liquid crystal display; RF SoCs: Radiofrequency system on chip; PLR: Piecewise linear representation; BAC: Blood alcohol content; BPNN: Backpropagation Neural Network; ADSD: Automated driver sleepiness detection; EOG: Electroocoulogram; KNN: K nearest neighbor; CBR: Case-based reasoning; RF: Random forest; NIR: Near-infrared; LBP: Local binary pattern; PERCLOS: Percentage of Eye Closure; SVD: Singular value decomposition; FFT: Fast Fourier transform; LSTM: Long short-term memory; DDD: Drunk driver detection; BLE: Bluetooth low energy; SWM: Steering wheel movements; M-SVM: Mobile-based Support Vector Machine; AI: Artificial intelligence; ML: Machine learning; DL: Deep learning; PCA: Principal component analysis; IPCA: Incremental principal component analysis; ANN: Artificial neural network; CAV: Connected and automated vehicles

Road Hypnosis Detection using Lane Detection

The study "Road Hypnosis Detection Using Lane Detection" focuses on the phenomenon known as "road hypnosis" or "highway hypnosis," a mental state in which a person can operate a vehicle for extended distances while reacting to outside events as expected, all without recalling that they did so consciously. Long stretches of time spent driving on smooth, featureless highways can cause this syndrome, which lowers awareness and causes a lack of stimulation. The study suggests a novel approach that makes use of lane identification algorithms to identify road hypnosis. It keeps track of the car's location in the lane and the driver's steering movements using sophisticated image processing and machine learning algorithms. Unusualities in these patterns, which could signal the start of road hypnosis, can be detected by the system. This system attempts to improve road safety and avoid accidents caused by decreased driver alertness due to road hypnosis by giving the driver real-time feedback or initiating automatic safety measures. The suggested approach is thoroughly tested and validated throughout the study in a variety of driving situations and conditions, proving its efficacy and suitability for incorporation into contemporary car safety systems. This study addresses a prevalent but frequently disregarded problem that might result in catastrophic accidents, making a substantial contribution to the field of driver safety systems. It also creates new opportunities for utilizing technology to raise driver awareness and enhance general traffic safety.

Assessing the Criticality of Longitudinal Driving Scenarios Using Time Series Data

Unfortunately, many people die in car accidents. To reduce these accidents, cars are equipped with driving safety systems. With autonomous vehicles, the driver’s behavior becomes irrelevant as the car drives autonomously. All autonomous driving algorithms must undergo extensive testing and validation, especially for safety-critical scenarios. Therefore, the detection of safety-critical driving scenarios is essential for autonomous vehicles. This publication describes safety indicator metrics based on time series covering longitudinal driving data to detect safety-critical driving scenarios. Scientific Question: Which safety indicator metrics can be used to identify safety-critical driving scenarios based on time series covering longitudinal driving data?

Upskilling Professional Driving Instructors of Young Learner Drivers: What Are We Waiting For?

Decades of research and development to address young drivers’ over-involvement in road crashes has led to critical improvements in understanding and interventions, yet has mostly focused on young drivers or their parents. Driving instructors have a key role in the young driver safety system, yet substantially less attention has been paid to their accreditation and professional development specific to teaching young drivers. Neurobiological development during mid-to-late adolescence influences how young people drive and the inflated risks they face relative to adult learners. In this paper, we discuss several of our research studies and supporting literature to argue that: (a) adept higher-order professional instruction can improve young driver safety behaviour in ways that can reduce crashes; (b) instructors are willing to be upskilled in young driver specific training needs; and (c) young drivers currently lack adequate training in new motor vehicle features that can enhance their safety, as do many adults, creating further demand on the driver-training industry. Given this body of work, we argue that the field has sufficiently progressed to know both why and how we should innovate and transform the driver training industry in ways that will improve young driver safety. However, we also note current developments appear to be working against rather than towards improvements. Therefore, there is a need to prioritise and implement change, and to harness advantages of emerging technologies. Professional development opportunities for driving instructors not only have potential to benefit the industry and young drivers, but also parents; therefore, boosting traffic safety culture across the community.

The impact of driver safety system adoption on organizational performance in the petroleum industry in Zimbabwe

The impact of driver safety system adoption on organizational performance in the petroleum industry in Zimbabwe

Motorized Driving Safety System Using Eye Detection Analysis Method

Traffic accident, particularly two-wheeled vehicles, is a problem for the Government, especially the Resort Police Traffic Unit (Satlantas Polres). The factor that causes the traffic accident incident is divided into three types, namely human factor, vehicle factor, and road or environment factor. The human factor is the most common factor for an accident. Fatigue factor that causes someone to feel sleepy while driving often results in a traffic accident. Based on the problem, the researcher wanted to create a technology innovation of a motorized driving safety system in the form of a helmet. The researcher made an innovation of a helmet that can detect drowsiness through the driver's eye blink duration. The drowsiness will be detected by using a camera sensor. The camera sensor used was Open MV camera. The method used in detecting sleepy drivers was the eye detection analysis method. The method enable detection based on the data of the duration of eye condition when it is closed and open. The closed eye has a low RBG mean value of 110-113 and an RBG median value of 99-109. Whereas opened eye has a higher RGB mean value of 179-206 and RGB median value of 178-206. The result of the research showed that someone's sleepy condition occurred when closing their eyes for more than 0.4 seconds to 4 seconds. The helmet is also equipped with GPS to monitor the position in the event of an accident as an emergency response effort.

Implementation of Driving Safety Early Warning System Based on Trajectory Prediction on the Internet of Vehicles Environment

Traffic accidents cause a large number of casualties and economic losses every year. The primary causes of traffic accidents are the inadvertent response and inappropriate disposal of drivers. The Internet of Vehicles system is a large network based on intranets, the Internet, and mobile Internet. It performs wireless communication and information exchange between vehicles and roadways in accordance with the agreed-upon communication protocol and data exchange standards. It provides technical assistance in the implementation of vehicle hazard detection and opens up new avenues for safety early warning. In this study, a driving safety early warning system is proposed based on trajectory prediction on the Internet of Vehicles environment. After analyzing the system requirements, the driving safety system based on trajectory prediction is designed according to the demand analysis and tested. The trajectory prediction error is detected, and the collected trajectory is predicted. Data are divided into 3 groups, and to validate the performance of the system, the experiment is repeated five times. The test results show that the trajectory prediction accuracy of the trajectory prediction system designed is 89.4%, as compared to the accuracy of existing driving safety early warning systems, most of which are concentrated at accuracy lower than 89%. The proposed early warning method has the potential to reduce vehicle collisions and road traffic accidents.

FEM Simulation of the Riveting Process and Structural Analysis of Low-Carbon Steel Tubular Rivets Fracture.

Riveted joints are a common way to connect elements and subassemblies in the automotive industry. In the assembly process, tubular rivets are loaded axially with ca. 3 kN forces, and these loads can cause cracks and delamination in the rivet material. Such effects at the quality control stage disqualify the product in further assembly process. The article presents an analysis of the fracture mechanism of E215 low-carbon steel tubular rivets used to join modules of driver and passenger safety systems (airbags) in vehicles. Finite element method (FEM) simulation and material testing were used to verify the stresses and analysis of the rivet fracture. Numerical tests determined the state of stress during rivet forming using the FEM-EA method based on the explicit integration of central differences. Light microscopy (LM), scanning electron microscopy (SEM) and chemical composition analysis (SEM-EDS) were performed to investigate the microstructure of the rivet material and to analyze the cracks. Results showed that the cause of rivet cracking is the accumulation and exceeding of critical tensile stresses in the rivet flange during the tube processing and the final riveting (forming) process. Moreover, it was discovered that rivet fracture is largely caused by structural defects (tertiary cementite Fe,Mn3CIII along the boundaries of prior austenite grains) in the material resulting from the incorrectly selected parameters of the final heat treatment of the prefabricate (tube) from which the rivet was produced. The FEM simulation of the riveting and structural characterization results correlated well, so the rivet forming process and fracture mechanism could be fully investigated.

Advanced Driver Assistance Systems (ADAS): Who’s Driving What and What’s Driving Use?

The emergence of vehicle technologies that promote driver safety and convenience calls for investigation of the prevalence of driver assistance systems as well as of their use rates. A consumer driven understanding as to why certain vehicle technology is used remains largely unexplored. We examined drivers’ experience using 13 different advanced driver assistance systems (ADAS) and several reasons that may explain rates of use through a nationally-distributed survey. Our analysis focused on drivers’ levels of understanding and trust with their vehicle’s ADAS as well as drivers’ perceived ease, or difficulty, in using the systems. Respondents’ age and experience with Level 0 or Level 1 technologies revealed additional group differences, suggesting older drivers (55+), and those with only Level 0 systems as using ADAS more often. These data are interpreted using the Driver Behavior Questionnaire framework and offer a snapshot of the pervasiveness of certain driver safety systems.

Sistem Keamanan Model Sidik Jari (Digital Key Security) Menggunakan Pemrograman Arduino Pada Sepeda Motor

Abstract: The fingerprint-type digital key model driving safety system offers an accurate security system in minimizing motorcycle units from potential theft crimes that are rampant. This study aims to develop a security system for a fingerprint model on a motorcycle using the arduino-based prototype development method. The test was carried out to determine the results of the arduino programming configuration on the board with a fingerprint scanner. Research results: 1) the design processed using the Arduino application shows that done compiling means that the configuration is successful. 2) The fingerprint scanning test results show that the ignition of the starter is faster when the palm of the finger is dry; that is, the average is activated 2.31 seconds. 3) The result of detection on unknown finger will be activate the alarm. Keywords: Security system, Fingerprint, Arduino application

Near-Infrared Imaging Photoplethysmography During Driving

Imaging photoplethysmography (iPPG) could greatly improve driver safety systems by enabling capabilities ranging from identifying driver fatigue to unobtrusive early heart failure detection. Unfortunately, the driving context poses unique challenges to iPPG, including illumination and motion. First, drastic illumination variations present during driving can overwhelm the small intensity-based iPPG signals. Second, significant driver head motion during driving, as well as camera motion (e.g., vibration) make it challenging to recover iPPG signals. To address these two challenges, we present two innovations. First, we demonstrate that we can reduce most outside light variations using narrow-band near-infrared (NIR) video recordings and obtain reliable heart rate estimates. Second, we present a novel optimization algorithm, which we call AutoSparsePPG, that leverages the quasi-periodicity of iPPG signals and achieves better performance than the state-of-the-art methods. In addition, we release the first publicly available driving dataset that contains both NIR and RGB video recordings of a passenger’s face with simultaneous ground truth pulse oximeter recordings.

Drivers Use of In-Vehicle Information Systems and Perceptions of Their Effects on Driving

In recent years the number of cars on the road with manufacturer installed in-vehicle information systems (IVIS) has increased dramatically, and with smartphones connecting directly to these systems drivers can access a wide range of applications on the move. Some IVIS features are designed to improve safety (e.g., speed and collision warnings) but access via an IVIS to all apps on a smartphone has the potential to distract drivers and increase crash risk. We undertook this study to find out what IVIS features and apps drivers use and to ask about their effects on driving. An online survey completed by 1017 drivers (50% female, 16- 85 years) revealed the most common activity drivers engaged in was listening to music, followed by listening to directions. Fewer than half of the drivers reported conversing on a hands-free phone and 25% reported texting/sending emails or using social media. Frequency of engagement in secondary tasks decreased with age. Using hand-held mobiles was rated as having the greatest negative impact on driving, with drivers attempting to mitigate the risk by carrying out the activity in slow moving traffic or at traffic lights. Females rated the risk of most of the secondary tasks as greater than males. Almost half of the sample had access to speed warnings systems but only a small proportion had experience of lane departure, dangerous curve or intersection warning systems. Of those with access to driver safety systems, 50-70% never used them despite rating the system as useful and as having safety benefits. As the number of vehicles with manufacturer installed IVIS continues to increase on the road, drivers’ engagement with them while driving is also likely to increase. To address this, there is a need for a multi-agency approach to educate drivers on the safe use of these systems and apps in their vehicles. Incentives for drivers to use the safety-related features may also be worth considering.

Driving Behavior Recognition Based on EEG Data From a Driver Taking Over Experiment on a Simulated Autonomous Vehicle

Driving behavior recognition is a critical part of the driver safety system. Most of the popular researches have utilized the driver’s questionnaire data and driving data to recognize driving behavior. But few studies have used physiological data to recognize different driving behaviors, such as EEG data. In this paper, a new method was presented to recognize different driving behaviors based on EEG data. The driving data and EEG data were collected when participants took over the autonomous vehicle. Through K-means, the driving data were classified into two groups, and the classification results were utilized as inputs to generate a k-Nearest-Neighbor model to recognize driving behavior groups via EEG data. The results showed that the average recognition accuracy was 80.6%, and the highest recognition accuracy was 84.2%, indicating that there is an obvious relation between EEG data and driver taking over behavior.

User rating and acceptance of attention-adaptive driver safety systems

Current statistics show that distraction is a central cause of traffic accidents. Safety systems with distance control currently available on the market have great potential for preventing accidents and significantly reducing their severity. However, depending on the driver’s level of attention, the systems warn too early or too late, which impairs use acceptance. Adaptive systems allow for personalization according to driver’s attention level. Studies were carried out in a driving simulator in order to compare the system adaptations with regard to acceptance for attentive and distracted driving phases. Seventy-two participants took part in the study, with a between-subjects test design. Acceptance ratings shows highest acceptability for the adaptive systems in distractive situations. We conclude that personalization of attention-adaptive systems shall be implemented in case safety benefits are proven.

Driver Safety System Implementation in Europe

In mining industry safety is top priority. There is a request for safety management, risk prevention and operator training. Operator fatigue and distraction leads to dangerous situations. The paper is aimed at reviewing the issues of fatigued or distracted driver operation. This is achieved through creating models in occupational safety strategies. Hereafter the implementation of fatigue and distraction control system within a pilot project is discussed. The pilot project was aimed at collecting realistic operation data from mining industry in Europe. Caterpillar Inc. offers a solution called Driver Safety System (DSS). When driver’s micro-sleep is detected, the system alerts operator through different alarms directly. Dangerous events are also recorded and classified individually in 24/7 monitoring centre. The DSS was tested at European limestone open pit mine with typical working regime. This paper discusses theories, results and transferable insights of the study.

Benefits of Redundant Visual In-Vehicle Information in Pedestrian–Vehicle Conflict Scenarios

The paper provides information relevant to the development of driver and pedestrian safety systems by examining drivers’ responses to infrastructure-based safety messages (DII) with a redundant in-vehicle display component. A driving simulator was used to create a conflict situation which required an immediate driver response to avoid a collision. At the start of the event, a pedestrian was occluded by a truck at an intersection. Partway through the event, the pedestrian dashed into the road and into the driver’s path. When redundant visual in-vehicle alerting messages were provided, drivers released the throttle more quickly, engaged the brake more quickly, and had longer minimum time to collision relative to the baseline condition which lacked visual alerts. This was an improvement over the DII-only condition, where drivers did not brake more quickly relative to baseline and had only marginally longer minimum time to collision compared with the baseline condition. The findings suggest that redundant in-vehicle message information provides a benefit to many drivers over systems that use only infrastructure-based safety systems in vehicle–pedestrian conflicts.

Control System for Maintaining Safe Following Distance while Driving

Safety is the most important issue while driving. Many traffic accidents occur because of insufficient safe distance. With the advancement of technology, there are cars with a front distance safety warning system. Some of them are with fixed safe distance regardless of the speed of the car. Other advanced distance detection systems switch between different modes such as high speed and low speed. In this paper, we proposed a driving safety system which can dynamically adjust the safe distance between vehicles depending on the speed and weather conditions. This system can be used to determine and maintain safe distances both in front and rear of a car. This idea has obtained an invention patent of Taiwan. A car with this system can be driven more safely.

SMARTPHONE-BASED APPROACH TO DETERMINING DRIVING STYLE WITH ON-BOARD SENSORS

Introduction: Driving behavior analysis and driving style evaluation allow you to pay the drivers' attention to their driving skills and characteristics, reduce reckless driving rate, increase the vehicle usage efficiency and thereby reduce the number of traffic accidents. However, the available driver assistance systems lack personalization, which in its turn decreases the efficiency of these systems and limits the scope of their usage. Purpose: Developing an approach to analysis and evaluation of a driving style, based on smartphone features such as a front-facing camera and sensors, and focused on its usage in driver safety systems. Results: The article discusses a scheme of combining data from smartphone sensors for a driver assistant system. It presents an information model of a driver's profile. An algorithm has been developed for the analysis of an individual driving style in order to to improve the quality of recognizing dangerous states in one's driving behavior, taking into account the previous experience of using the system. This algorithm allows drivers to evaluate their driving style and thereby to pay more attention to their driving skills. A prototype has been developed for a system evaluating a driving style based on the data from smartphone sensors related to the vehicle operation parameters, taking into account the history of driver's interaction with the assistant system. Practical relevance: The obtained results allow you to increase the accuracy of recognizing dangerous states and, thereby, improve the efficiency of the driver assistance system. They also can be used for generating and displaying driving reports for insurance agents, fleet managers and logistic managers who observe and monitor the driving statistics.

SafeDrive

Distracted driving causes a large number of fatalities every year and is now becoming an important issue in the traffic safety study. In this paper, we present SafeDrive, a driving safety system that leverages wearable wrist sensing techniques to detect and analyze driver distracted behaviors. Existing wrist-worn sensing approaches, however, do not address challenges under real driving environments, such as less distinguishable gesture patterns due to in-vehicle physical constraints, various gesture hallmarks produced by different drivers and significant noise introduced by various driving conditions. In response, SafeDrive adopts a semi-supervised machine learning model for in-vehicle distracting activity detection. To improve the detection accuracy, we provide online updated classifiers by collecting real-time gesture data, while at the same time utilize smartphone sensing to generate soft hints filtering out anomalies and non-distracted hand movements. In the evaluation, we conduct extensive real-road experiments involving 20 participants (10 males and 10 females) and 5 vehicles (a sedan, a minivan and three SUVs). Our approach can achieve an average classification accuracy of over 90% with a error rate of a few percent, which demonstrate that SafeDrive is robust to real driving environments, and has great potential to help drivers shape safe driving habits.

Driver’s anger state identification by using facial expression in cooperation with artificial intelligence

Preventive safety system of vehicle is highlighted to reduce the number of traffic accidents. Driver’s state adaptive driving safety system may be one of candidates of the safety system. Identifying driver’s psychosomatic states is indispensable to establish those safety systems. Anger of driver state is often seen in traffic congestion which may be involved in severe traffic accidents. This research adopted Kohonen neural network as classification algorithm to identify anger state of driver by using facial expression. We adopted six types of facial expression which are ordinary, drowsiness, anger, sorrow, delight and surprise according previous research. We classified six types of facial expressions by using KNN. Finally, this research proposes driver’s anger state alert function by using facial expression classification in cooperation with artificial intelligence to prevent potential risks of traffic accidents. Keywords : driver’s anger; facial expression; Kohonen neural network; artificial intelligence.