Driver Head Movements Research Articles

One‐shot learning‐based driver's head movement identification using a millimetre‐wave radar sensor

Concentration of drivers on traffic is a vital safety issue; thus, monitoring a driver being on road becomes an essential requirement. The key purpose of supervision is to detect abnormal behaviours of the driver and promptly send warnings to him/her for avoiding incidents related to traffic accidents. In this paper, to meet the requirement, based on radar sensors applications, the authors first use a small-sized millimetre-wave radar installed at the steering wheel of the vehicle to collect signals from different head movements of the driver. The received signals consist of the reflection patterns that change in response to the head movements of the driver. Then, in order to distinguish these different movements, a classifier based on the measured signal of the radar sensor is designed. However, since the collected data set is not large, in this paper, the authors propose One-shot learning to classify four cases of driver's head movements. The experimental results indicate that the proposed method can classify the four types of cases according to the various head movements of the driver with a high accuracy reaching up to 100%. In addition, the classification performance of the proposed method is significantly better than that of the convolutional neural network (CNN) model.

Classification of Driver Head Motions Using a mm-Wave FMCW Radar and Deep Convolutional Neural Network

Eight different driver head movements are measured using a millimeter-wave FMCW radar mounted in the dashboard of a car. The micro-Doppler signatures are converted into a spectrogram image format for analysis and classification purposes. The eight different head motions exhibit unique time-frequency profiles, which can be classified by deep learning algorithms. In this study, a convolutional neural network is used to classify the eight head motions with an optimized window size. Various dataset permutations are considered, such as the effect of window width on classification accuracy and the classification accuracy of head motions in a still car compared to a moving car.

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.

Standardized evaluation of camera-based driver state monitoring systems

Driver state sensing technologies, such as vehicular systems, start to be widely considered by automotive manufacturers. To reduce the cost and minimize the intrusiveness towards driving, the majority of these systems rely on the in-cabin camera &#x0028 s &#x0029 and other optical sensors. With their great capabilities in detecting and intervening of driver distraction and inattention, these technologies may become key components in future vehicle safety and control systems. However, to the best of our knowledge, currently, there is no common standard available to objectively compare the performance of these technologies. Thus, it is imperative to develop one standardized process for evaluation purposes. In this paper, we propose one systematic and standardized evaluation process after successfully addressing three difficulties: 1&#x0029 defining and selecting the important influential individual and environmental factors, 2&#x0029 countering the effects of individual differences and randomness in driver behaviors, and 3&#x0029 building a reliable in-vehicle driver head motion tracking tool to collect ground-truth motion data. We have collected data on a large scale on a commercial driver state-sensing platform. For each subject, 30 to 40 minutes of head motion data was collected and included variables, such as lighting conditions, head &#x002F face features, and camera locations. The collected data was analyzed based on a proposed performance measure. The results show that the developed process can efficiently evaluate an individual camera-based driver state sensing product, which builds a common base for comparing the performance of different systems.

DRIVER HEAD MOVEMENT ESTIMATOR ON ARM BIG.LITTLE PROCESSOR

A driving environment that is changing constantly and rapidly, demands a driver to make large head turns. Drivers head movements are strong indicators of drivers focus on the road. In this paper a vision based algorithm is presented to estimate the driver head pose. Determining the head pose using vision based algorithms is a non-invasive method in intelligent driver assistance systems. Many existing state of the art vision based head pose algorithms have difficulties in monitoring the driver head movements. This is because in single camera perspective spatially large head turns disturb the facial features which are necessary to determine the head pose. A distributed camera framework and the use of Constrained Local Model algorithm for head pose tracking is presented. The proposed approach monitors the driver head over wide range of movements.

Infrared-Based In-Vehicle Head Tracking: A Prototype for Tracking Drivers' Head Movements in Real Time

Future assistance systems in vehicles will require data that indicate the 3D position of the driver's head and eyes in real time. The head tracking is necessary, for example, so that information can be displayed in a contact-analog way, eventually increasing the driver's comfort and safety. For this, a study with 15 participants was conducted to examine typical driver head movements while driving. The study revealed overall only slight vertical and lateral head movements as well as little differing vertical and lateral head positions across different participants. A head tracking method based on these results was developed employing 2D to 3D conversion while using a single thermographic camera. Reducing the system to one camera cuts expenses significantly; however, doing so introduces small errors in the 3D detection. The choice was made in favor of thermal image processing since this allows the images to be treated independently of external light conditions, making the system reliable and suitable for nighttime driving.

Visual Analysis of Eye State and Head Pose for Driver Alertness Monitoring

This paper presents visual analysis of eye state and head pose (HP) for continuous monitoring of alertness of a vehicle driver. Most existing approaches to visual detection of nonalert driving patterns rely either on eye closure or head nodding angles to determine the driver drowsiness or distraction level. The proposed scheme uses visual features such as eye index (EI), pupil activity (PA), and HP to extract critical information on nonalertness of a vehicle driver. EI determines if the eye is open, half closed, or closed from the ratio of pupil height and eye height. PA measures the rate of deviation of the pupil center from the eye center over a time period. HP finds the amount of the driver's head movements by counting the number of video segments that involve a large deviation of three Euler angles of HP, i.e., nodding, shaking, and tilting, from its normal driving position. HP provides useful information on the lack of attention, particularly when the driver's eyes are not visible due to occlusion caused by large head movements. A support vector machine (SVM) classifies a sequence of video segments into alert or nonalert driving events. Experimental results show that the proposed scheme offers high classification accuracy with acceptably low errors and false alarms for people of various ethnicity and gender in real road driving conditions.

The Research on Fatigue Driving Detection Algorithm

Researches on Driver Fatigue Detection System, which aims to ensure the safety of operations and to reduce traffic accidents caused by artificial factors, has been the major research subject in transportation safety. There is an enormous advantage in the method obtaining the driver's image by camera, We propose efficient tracking and detecting algorithm and with an appearance model based on haar-like features, finding out the accuracy and robustness of tracking of eyes movements and the conflict between real-time tracing and accuracy of fatigue detection algorithms systems. First, PERCLOS algorithm is adopted to analyze and determine whether a person is fatigue. Second, AdaBoost algorithm is applied to fast detect and the algorithm is implemented in FPGA. Third, We propose a compressed sample tracking algorithm, which compress samples of image using the sparse measurement matrix and train the classification online. The algorithms runs in real-time and is implemented based on ARM add FPGA platform. Experimental results show that the algorithm has high recognition accuracy and robust performance under real train driving environment, in the case of nonlinear tracking of the human eye, illumination change, multi-scale variations, the driver head movement and pose variation.

A Novel Approach to Head positioning using Fixed Center Interpolation Net with Weight Elimination Algorithm

A reliable algorithm for head movements inside a vehicle is designed. The proposed algorithm allowed the adjustment of basic functions such as indicators, mirrors and reverse lights based on the driver final head position. The algorithm system mapped a predefined coordinates for actuating system. Problem statement: Head position recognition is one of the most common problems encountered in engineering and scientific disciplines, which involves developing prediction or classification models from historic data or training samples. In the past few years face detection and person identification became important issues due to security concerns, leading to head gesture algorithm development and implementation. Approach: This study introduces a new approach that combines Fixed Center Interpolation Net Algorithm (FCIN) with Wight Elimination Algorithm (WEA). This enhances the ability to classify and predict head positions and poses and gives better representation capabilities for the overall system algorithm. Such algorithm is able to handle pattern recognition problems using Radial Basis Function (RBF) models. The system algorithm has been developed based on the mathematical properties of the interpolation and design matrices of RBF models. Results: A reliable, fast and robust approach for driver head position recognition is achieved and presented. Conclusion: A simple hybrid algorithm for driver's head movements is designed and tested. The obtained results proved the algorithm applicability and ability to predict and act upon head gestures.

Analysis of perception of flat ride feeling focused on driver's head motion and visual information

Analysis of perception of flat ride feeling focused on driver's head motion and visual information

1P1-A26 動揺病の数理モデルを用いた自動車乗員の頭部運動の解析

Driver receives the acceleration and the rotational stimulations when negotiating with a curve. In such a situation, the driver controls his/her posture such as the head and the body appropriately. Beside, it is pointed out that the head movement of the passenger is opposite to the driver. Moreover, by the fact that the driver does not get carsickness comparing with the passenger, it is suggested that the driver's head movement may be related to the decrease of carsickness and improvement of the ride comfort. Therefore, we build the mathematical model of the motion sickness and investigated the relation between the head movement and the motion sickness incidence. In addition, we simulate motion sickness incidence using driver's head movements measured in the experiments with a real car. From the result, it is shown that the head tilt movement of the driver's head movement has an effect to decrease the motion sickness.

Design, Modeling and Implementation of Pic Based Wireless Control System to Eliminate Blind Spots in Vehicle Side Mirrors

A PIC controlled IR system for the control of vehicle side mirror system movements for the purpose of revealing blind spots is designed and implemented. The designed and built system allows the side view mirrors to be adjusted based on the driver head movement. The infrared-based head tracking system maps a predetermined coordinates for head movements and results in a triangularly computable geometry, which is fed to the PIC, based controlling system. This will cause the vehicle mirror movement via carefully selected miniature motors.

2106 スラローム走行時のドライバの操作行動解析(OS6-2 運転行動と車両挙動,OS6 ヒューマンファクタ,オーガナイズド・セッション)

In the performance evaluation of the vehicle control, the evaluation by man-machine system is indispensable. In the motion control by the suspension system, it is important to evaluate driver's pose keeping and steering control to stabilize vehicle attitude. In this paper, analysis of driving maneuvers in slalom running has been executed using newly designed rolling simulator. As the result, it was confirmed that steering control including driver's head motion was analyzed and visual information and the size of roll angle took part in steering control.

Lane Change Intent Analysis Using Robust Operators and Sparse Bayesian Learning

In this paper, we demonstrate a driver intent inference system that is based on lane positional information, vehicle parameters, and driver head motion. We present robust computer vision methods for identifying and tracking freeway lanes and driver head motion. These algorithms are then applied and evaluated on real-world data that are collected in a modular intelligent vehicle test bed. Analysis of the data for lane change intent is performed using a sparse Bayesian learning methodology. Finally, the system as a whole is evaluated using a novel metric and real-world data of vehicle parameters, lane position, and driver head motion.

Driver behavior at flashing-light, rail-highway crossings

The risk of accident at flashing-light, rail-highway crossings has been found to be ten times higher than at crossings equipped with barriers. The purpose of the present investigation was to study driver behavior in rail-highway crossings and to relate measures of driver behavior to variables believed to be associated with increased risks of accident. About 2,000 drivers were observed in 16 different crossings with driver head movements as the major dependent variable. This variable exhibits wide variability among drivers as well as satisfactory interobserver reliability. The results showed that many drivers turned their head to look for trains in rail-highway crossings although the crossings were equipped with flashing warning lights. However, fewer drivers looked when the visibility was restricted, a factor that is associated with increased risk of accident, and in crossings with few trains per day. The conclusion from the present study is that flashing-light crossings should be designed in a way that redundant information about approaching trains should be easily available to the drivers.