Driver Head Research Articles

Forensic analysis of head injuries of a driver in a fatal car injury

Among the main tasks facing a forensic expert during the examination related to an injury inside the car interior is to determine the mechanism of injury formation, its severity and the location of the victims. This often requires solving issues related to the peculiarities of the mechanism of cranial trauma formation, its morphology and severity. The purpose of the study is to determine the features of localization of injuries to the driver's head in a fatal car injury. As a result of the study, it was found that there were no significant differences in the comparison groups in the ISS scale range from 0 to 10 and 11 to 20. In the ISS intervals from 21 to 30 and 31 to 40, fatal injuries among drivers of domestic cars prevailed. In the range from 41 to 50 – drivers of foreign cars. A comparative analysis of the severity of head injuries in drivers of domestic and foreign-made cars using the ISS scale revealed significant differences in cases with fatal TBI, which suggests the presence of additional factors affecting the severity of injuries, which should be studied further and taken into account when answering the question about the location of the victim in the car interior.

Design and implementation of a driving safety assistant system based on driver behavior

<p>These days, road accidents are one of Morocco's biggest problems. Fatigue, drowsiness, and driver behavior are among the primary causes.This research aims to develop an embedded system by image processing and computer vision to ensure driving safety by monitoring driver behavior and assist drivers to awaken from micro-sleep or fatigue due to long driving hours and various other reasons. Indeed, the driver inattention, drowsiness or driver fatigue can be detected. The suggested method is designed to support drivers if needed, based on the vehicle velocity. Once the driver crosses a certain speed limit, the program starts face detection and analyzing this data to determine whether the driver is tired, sleepy, or inattentive. This activates different alarm depending on the criticality level. It can sound a voice alert to help him wake up and drive more cautiously. The system is based on AI algorithms in image processing based on OpenCV libraries and the Python language to capture the movements of the driver's eyes and head when starting the automobile. Every algorithm is run on a Raspberry-Pi 4 card, and numerous experimentation series have demonstrated overall credible performance with success accuracy of over 93% in EAR and MAR calculations.</p>

HEART RATE VARIABILITY BASED DRIVER DROWSINESS DETECTION

Driver drowsiness may cause traffic injuries and death. Various methods have been given to detect drowsiness, for instance, image-based biometric-signals-based. In this project, a new approach using heart rate and head tilt is discussed. The aim of the project is to provide a device with simple components that enables the driver to save his life by avoiding accidents caused by frequent sleepiness by giving a sound alert (alarm), which forces the driver to wake up and regain control of the car This device is not considered a treatment for the problem of sleep, but rather a preventive tool from accidents daily the project was designed with simple components, the most important of which are (ECG sensor and acceleration sensor Arduino, alarm device). ECG sensor: it used to give an ECG signal to Arduino to analysis it. ADXL335 sensor: it is placed behind the driver's head. This sensor senses the fall of the driver's head when he sleeps. It was added to sense better.

The role of driver head pose dynamics and instantaneous driving in safety critical events: Application of computer vision in naturalistic driving

This paper investigates the role of driver behavior especially head pose dynamics in safety–critical events (SCEs). Using a large dataset collected in a naturalistic driving study, this paper analyzes the head pose dynamics and driving behavior in moments leading up to crashes or near-crashes. The study uses advanced computer vision and mixed logit modeling techniques to identify patterns and relationships between drivers’ head pose dynamics and crash involvement. The results suggest that driver-head pose dynamics, especially poses that indicate distraction and movement volatility, are important factors that can contribute to undesirable safety outcomes. Marginal effects show that angular deviation for head pose dynamics indicated by yaw, pitch and roll increase the likelihood of crash intensity by 4.56%, 4.92% and 8.26% respectively. Furthermore, traffic flow and lane changing also contribute to increase in likelihood of crash intensity. These findings provide new insights into pre-crash factors, especially human factors and safety–critical events. The study highlights the importance of considering human factors in designing driver assistance systems and developing safer vehicles. This research contributes by examining naturalistic driving data at the microscopic level with early detection of behaviors that lead to SCEs and provides a basis for future research on automation.

IoT-enabled Biometric Security: Enhancing Smart Car Safety with Depth-based Head Pose Estimation

Advanced Driver Assistance Systems (ADAS) are experiencing higher levels of automation, facilitated by the synergy among various sensors integrated within vehicles, thereby forming an Internet of Things (IoT) framework. Among these sensors, cameras have emerged as valuable tools for detecting driver fatigue and distraction. This study introduces HYDE-F, a Head Pose Estimation (HPE) system exclusively utilizing depth cameras. HYDE-F adeptly identifies critical driver head poses associated with risky conditions, thus enhancing the safety of IoT-enabled ADAS. The core of HYDE-F’s innovation lies in its dual-process approach: it employs a fractal encoding technique and keypoint intensity analysis in parallel. These two processes are then fused using an optimization algorithm, enabling HYDE-F to blend the strengths of both methods for enhanced accuracy. Evaluations conducted on a specialized driving dataset, Pandora, demonstrate HYDE-F’s competitive performance compared to existing methods, surpassing current techniques in terms of average Mean Absolute Error (MAE) by nearly 1 ∘ . Moreover, case studies highlight the successful integration of HYDE-F with vehicle sensors. Additionally, HYDE-F exhibits robust generalization capabilities, as evidenced by experiments conducted on standard laboratory-based HPE datasets, i.e., Biwi and ICT-3DHP databases, achieving an average MAE of 4.9 ∘ and 5 ∘ , respectively.

UHead

The focus of Advanced driver-assistance systems (ADAS) is extending from the vehicle and road conditions to the driver because the driver's attention is critical to driving safety. Although existing sensor and camera based methods can monitor driver attention, they rely on specialised hardware and environmental conditions. In this paper, we aim to develop an effective and easy-to-use driver attention monitoring system based on UWB radar. We exploit the strong association between head motions and driver attention and propose UHead that infers driver attention by monitoring the direction and angle of the driver's head rotation. The core idea is to extract rotational time-frequency representation from reflected signals and to estimate head rotation angles from complex head reflections. To eliminate the dynamic noise generated by other body parts, UHead leverages the large magnitude and high velocity of head rotation to extract head motion information from the dynamically coupled information. UHead uses a bilinear joint time-frequency representation to avoid the loss of time and frequency resolution caused by windowing of traditional methods. We also design a head structure-based rotation angle estimation algorithm to accurately estimate the rotation angle from the time-varying rotation information of multiple reflection points in the head. Experimental results show that we achieve 12.96° median error of 3D head rotation angle estimation in real vehicle scenes.

Bus Driver Head Position Detection Using Capsule Networks under Dynamic Driving Conditions

Monitoring bus driver behavior and posture in urban public transport’s dynamic and unpredictable environment requires robust real-time analytics systems. Traditional camera-based systems that use computer vision techniques for facial recognition are foundational. However, they often struggle with real-world challenges such as sudden driver movements, active driver–passenger interactions, variations in lighting, and physical obstructions. Our investigation covers four different neural network architectures, including two variations of convolutional neural networks (CNNs) that form the comparative baseline. The capsule network (CapsNet) developed by our team has been shown to be superior in terms of efficiency and speed in facial recognition tasks compared to traditional models. It offers a new approach for rapidly and accurately detecting a driver’s head position within the wide-angled view of the bus driver’s cabin. This research demonstrates the potential of CapsNets in driver head and face detection and lays the foundation for integrating CapsNet-based solutions into real-time monitoring systems to enhance public transportation safety protocols.

A novel semi-active control of an integrated chassis and seat quasi-zero stiffness suspension system for off-road vehicles

This article introduces an innovative semi-active suspension system for off-road vehicles, incorporating a quasi-zero stiffness suspension to enhance driver comfort. The system includes a central pneumatic spring, double-acting pneumatic linear actuators for adjustable stiffness, and magnetorheological dampers for controlled damping. Using Lyapunov stability theory, a static output feedback control law is designed to address uncertainties in road profiles, driver body parameters, and actuator saturation, relying on measured variables as feedback. Performance constraints focus on driver head acceleration, suspension displacement, and dynamic tire load. The control law problem is converted into a convex optimization problem with linear matrix inequalities. The new semi-active QZSS system is theoretically tested via Matlab simulations and validated through hardware-in-the-loop testing. Comparative analysis between passive QZSS and the new semi-active QZSS on different roads, and vehicle speeds closely aligns with simulation results, with minor disparities attributable to network discrepancies and signal interruptions. Impressively, the semi-active QZSS system reduces driver head vertical acceleration between 26.53 and 35.0% compared to passive air QZSS, showing potential for significantly improving ride comfort, reducing vibration transfer, and enhancing driver wellbeing with minimal energy requirement.

Design of full vehicle PBNR based on side windows with embedded acoustic black holes

Acoustic black holes (ABH) have been proven to be a lightweight structure with wide application prospects in wave tuning, energy recovery, and vibration and noise reduction. The side window glass is one of the important noise propagating paths into vehicle interior. In this paper, a new side window glass based on ABHs is designed and the influence of the new side window glass on the full vehicle PBNR is analyzed. A full vehicle SEA model is established and verified using the PBNR test. The transmission paths contributing the most noise energy to the driver's head cavity under excitations at different positions are analyzed. The results show that the side window glass is the main weak component needed to be optimized in the analysis frequency band. The influence of the new type of side window glass on the whole vehicle PBNR is studied based on the full vehicle SEA model. It is observed that by comparing with the traditional glass, the new glass can significantly improve the PBNR at the coincidence frequency of glass under different paths and meanwhile reduce the weight of the glass. It can provide a new technology for improving vehicle interior noise control.

European NCAP Driver State Monitoring Protocols: Prevalence of Distraction in Naturalistic Driving.

examine the prevalence of driver distraction in naturalistic driving when implementing European New Car Assessment Program (Euro NCAP)-defined distraction behaviours. The 2023 introduction of Occupant Status monitoring (OSM) into Euro NCAP will accelerate uptake of Driver State Monitoring (DSM). Euro NCAP outlines distraction behaviours that DSM must detect to earn maximum safety points. Distraction behaviour prevalence and driver alerting and intervention frequency have yet to be examined in naturalistic driving. Twenty healthcare workers were provided with an instrumented vehicle for approximately two weeks. Data were continuously monitored with automotive grade DSM during daily work commutes, resulting in 168.8 hours of driver head, eye and gaze tracking. Single long distraction events were the most prevalent, with .89 events/hour. Implementing different thresholds for driving-related and driving-unrelated glance regions impacts alerting rates. Lizard glances (primarily gaze movement) occurred more frequently than owl glances (primarily head movement). Visual time-sharing events occurred at a rate of .21 events/hour. Euro NCAP-described driver distraction occurs naturalistically. Lizard glances, requiring gaze tracking, occurred in high frequency relative to owl glances, which only require head tracking, indicating that less sophisticated DSM will miss a substantial amount of distraction events. This work informs OEMs, DSM manufacturers and regulators of the expected alerting rate of Euro NCAP defined distraction behaviours. Alerting rates will vary with protocol implementation, technology capability, and HMI strategies adopted by the OEMs, in turn impacting safety outcomes, user experience and acceptance of DSM technology.

Driver head kinematics in grassroots dirt track racing crashes: A pilot analysis

Motorsport athletes experience head acceleration loading during crashes; however, there is limited literature quantifying the frequency and magnitude of these loads, particularly at the grassroots level of the sport. Understanding head motion experienced during crash events in motorsport is necessary to inform interventions to improve driver safety. This study aimed to quantify and characterize driver head and vehicle kinematics during crashes in open-wheel grassroots dirt track racing. Seven drivers (ages 16–22, n = 2 female) competing in a national midget car series were enrolled in this study over two racing seasons and were instrumented with custom mouthpiece sensors. Drivers’ vehicles were outfitted with an incident data recorder (IDR) to measure vehicle acceleration. Forty-one crash events were verified and segmented into 139 individual contact scenarios via film review. Peak resultant linear acceleration (PLA) of the vehicle and PLA, peak rotational acceleration (PRA), and peak rotational velocity (PRV) of the head were quantified and compared across the part of the vehicle contacted (i.e., tires or chassis), the vehicle location contacted (e.g., front, left, bottom), the external object contacted (i.e., another vehicle, wall, or the track), and the principal direction of force (PDOF). The median (95th percentile) PLA, PRA, and PRV of the head and PLA of the vehicle were 12.3 (37.3) g, 626 (1799) rad/s2, 8.92 (18.6) rad/s, and 23.2 (88.1) g, respectively. Contacts with a non-horizontal PDOF (n = 98, 71%) and contact with the track (n = 96, 70%) were common in the data set. Contact to the left side of the vehicle, with the track, and with a non-horizontal PDOF tended to have the greatest head kinematics compared to other factors in each sub-analysis. Results from this pilot study can inform larger studies of head acceleration exposure during crashes in the grassroots motorsports environment and may ultimately support evidence-based driver safety interventions.

The influence of the windshield shape of formula one racing car on the driver's head comfort

Since the actual use of the small windshield in Formula One (F1) cars is still unknown, the influence of the shape of the windshield edge on the driver's head will be the main research direction of this paper. In this paper, FLUENT is used to model three different shapes of windshield and the driver's head. The author analyzes the impact of windshield on the driver's head from the perspective of aerodynamics, speculates the actual use of different shapes of windshield, and gives some optimization schemes. Results show that the difference among the three shapes of windshield on the driver's head comfort is negligible, but the main role of the windshield is probably to create turbulence, allowing air to flow smoothly into the aerodynamic components at the rear of the car.

Pilot Collection and Evaluation of Head Kinematics in Stock Car Racing.

The goal of this work was to collect on-track driver head kinematics using instrumented mouthpieces and characterize environmental exposure to accelerations and vibrations. Six NASCAR drivers were instrumented with custom-fit mouthpieces to collect head kinematic data. Devices were deployed at four tracks during practice and testing environments and configured to collect approximately 11 min of linear acceleration and rotational velocity data at 200 Hz. This continuous data collection, combined with film review, allowed extraction of complete laps of data. In addition to typical data processing methods, a moving-point average was calculated and subtracted from the overall signal for both linear acceleration and rotational velocity to determine the environmental component of head motion. The current analysis focuses on 42 full laps of data collected at four data collection events. The number of laps per track ranged from 2 to 23. Linear acceleration magnitudes for all 42 laps ranged from 2.46 to 7.48 g and rotational velocity ranged from 1.25 to 3.35 rad/s. After subtracting the moving average, linear acceleration ranged from 0.92 to 5.45 g and rotational velocity ranged from 0.57 to 2.05 rad/s. This study has established the feasibility of using an instrumented mouthpiece to measure head kinematics in NASCAR and presented a technique for isolating head motion due to cornering acceleration from those due to short-term perturbations experienced by the driver.

Two-Stream Spatial-Temporal Graph Convolutional Networks for Driver Drowsiness Detection.

Convolutional neural networks (CNNs) have achieved remarkable performance in driver drowsiness detection based on the extraction of deep features of drivers' faces. However, the performance of driver drowsiness detection methods decreases sharply when complications, such as illumination changes in the cab, occlusions and shadows on the driver's face, and variations in the driver's head pose, occur. In addition, current driver drowsiness detection methods are not capable of distinguishing between driver states, such as talking versus yawning or blinking versus closing eyes. Therefore, technical challenges remain in driver drowsiness detection. In this article, we propose a novel and robust two-stream spatial-temporal graph convolutional network (2s-STGCN) for driver drowsiness detection to solve the above-mentioned challenges. To take advantage of the spatial and temporal features of the input data, we use a facial landmark detection method to extract the driver's facial landmarks from real-time videos and then obtain the driver drowsiness detection result by 2s-STGCN. Unlike existing methods, our proposed method uses videos rather than consecutive video frames as processing units. This is the first effort to exploit these processing units in the field of driver drowsiness detection. Moreover, the two-stream framework not only models both the spatial and temporal features but also models both the first-order and second-order information simultaneously, thereby notably improving driver drowsiness detection. Extensive experiments have been performed on the yawn detection dataset (YawDD) and the National TsingHua University drowsy driver detection (NTHU-DDD) dataset. The experimental results validate the feasibility of the proposed method. This method achieves an average accuracy of 93.4% on the YawDD dataset and an average accuracy of 92.7% on the evaluation set of the NTHU-DDD dataset.

Toward Human-Centered Automated Driving: A Novel Spatiotemporal Vision Transformer-Enabled Head Tracker

Accurate dynamic driver head pose tracking is of great importance for driver–automotive collaboration, intelligent copilot, head-up display (HUD), and other human-centered automated driving applications. To further advance this technology, this article proposes a low-cost and markerless head-tracking system using a deep learning-based dynamic head pose estimation model. The proposed system requires only a red, green, blue (RGB) camera without other hardware or markers. To enhance the accuracy of the driver’s head pose estimation, a spatiotemporal vision transformer (ST-ViT) model, which takes an image pair as the input instead of a single frame, is proposed. Compared to a standard transformer, the ST-ViT contains a spatial–convolutional vision transformer and a temporal transformer, which can improve the model performance. To handle the error fluctuation of the head pose estimation model, this article proposes an adaptive Kalman filter (AKF). By analyzing the error distribution of the estimation model and the user experience of the head tracker, the proposed AKF includes an adaptive observation noise coefficient; this can adaptively moderate the smoothness of the curve. Comprehensive experiments show that the proposed system is feasible and effective, and it achieves a state-of-the-art performance.

A low-cost remote driver sleep monitoring system

Today, the use of smart transportation systems has become widespread due to the change in the structure of cities, technological developments, and the increase in the number of vehicles. It aims at targets such as reducing the damage to people and the environment by increasing traffic safety with smart transportation systems. In addition, one of the big problems of long-distance drivers is falling asleep while driving. This is an event that puts both the driver’s life, the passengers in the vehicle, and the vehicles on the road in danger, and puts the company in a difficult situation if it works for a company. In this direction, the driver sleep alarm project has been developed. This project is a control system based on monitoring the user, measuring, and analyzing their movements. Literature research, which is the first stage of the project, was conducted and research continued throughout the project process. Within the scope of this project, a headset was designed for the driver’s sleep alarm and a mobile application was created. The first prototype of the project was built. First, in the project, the angle values made by the driver's head were produced with the IMU connected to the microcontroller. 10° to 20° margins identified as sleeping state for roll, pitch, and yaw angles. Later, a wearable headset was designed for the driver. Based on these angles produced in the microcontroller, an algorithm has been created that detects whether the driver is asleep. These generated angle values and status information were transferred from the headset to the mobile application via Bluetooth. This data transferred in the mobile application is reflected on the screen. In addition, an algorithm has been created in the mobile application, which sends a notification to the driver when sleep status is detected and sends an informative SMS to the headquarters if the driver is unresponsive to this notification. For the second prototype, it was aimed to produce a PCB for the headset and thus make a new mechanical design. Data mining applications are planned with the collected data from drivers for future works.

Computational Study on the Flow Characteristics of the Golf Driver Head

Computational Study on the Flow Characteristics of the Golf Driver Head

Learning Spatio-Temporal Representations With a Dual-Stream 3-D Residual Network for Nondriving Activity Recognition

Accurate recognition of nondriving activity (NDA) is important for the design of intelligent human machine interface to achieve a smooth and safe control transition in the conditionally automated driving vehicle. However, some characteristics of such activities like limited-extent movement and similar background pose a challenge to the existing 3-D convolutional neural network based action recognition methods. In this article, we propose a dual-stream 3-D residual network, named DS3D residual network (ResNet), to enhance the learning of spatio-temporal representation and improve the activity recognition performance. Specifically, a parallel two-stream structure is introduced to focus on the learning of short-time spatial representation and small-region temporal representation. A two-feed driver behavior monitoring framework is further build to classify four types of NDAs and two types of driving behavior based on the driver's head and hand movement. A novel NDA dataset has been constructed for the evaluation, where the proposed DS3D ResNet achieves 83.35% average accuracy, at least 5% above three selected state-of-the-art methods. Furthermore, this study investigates the spatio-temporal features learned in the hidden layer through the saliency map, which explains the superiority of the proposed model on the selected NDAs.

DriverMVT: In-Cabin Dataset for Driver Monitoring including Video and Vehicle Telemetry Information

Developing a driver monitoring system that can assess the driver’s state is a prerequisite and a key to improving the road safety. With the success of deep learning, such systems can achieve a high accuracy if corresponding high-quality datasets are available. In this paper, we introduce DriverMVT (Driver Monitoring dataset with Videos and Telemetry). The dataset contains information about the driver head pose, heart rate, and driver behaviour inside the cabin like drowsiness and unfastened belt. This dataset can be used to train and evaluate deep learning models to estimate the driver’s health state, mental state, concentration level, and his/her activity in the cabin. Developing such systems that can alert the driver in case of drowsiness or distraction can reduce the number of accidents and increase the safety on the road. The dataset contains 1506 videos for 9 different drivers (7 males and 2 females) with total number of frames equal 5119k and total time over 36 h. In addition, evaluated the dataset with multi-task temporal shift convolutional attention network (MTTS-CAN) algorithm. The algorithm mean average error on our dataset is 16.375 heartbeats per minute.

Driver's Head Pose and Gaze Zone Estimation Based on Multi-Zone Templates Registration and Multi-Frame Point Cloud Fusion.

Head pose and eye gaze are vital clues for analysing a driver’s visual attention. Previous approaches achieve promising results from point clouds in constrained conditions. However, these approaches face challenges in the complex naturalistic driving scene. One of the challenges is that the collected point cloud data under non-uniform illumination and large head rotation is prone to partial facial occlusion. It causes bad transformation during failed template matching or incorrect feature extraction. In this paper, a novel estimation method is proposed for predicting accurate driver head pose and gaze zone using an RGB-D camera, with an effective point cloud fusion and registration strategy. In the fusion step, to reduce bad transformation, continuous multi-frame point clouds are registered and fused to generate a stable point cloud. In the registration step, to reduce reliance on template registration, multiple point clouds in the nearest neighbor gaze zone are utilized as a template point cloud. A coarse transformation computed by the normal distributions transform is used as the initial transformation, and updated with particle filter. A gaze zone estimator is trained by combining the head pose and eye image features, in which the head pose is predicted by point cloud registration, and the eye image features are extracted via multi-scale spare coding. Extensive experiments demonstrate that the proposed strategy achieves better results on head pose tracking, and also has a low error on gaze zone classification.