scholarly journals A Data Augmentation Approach to Distracted Driving Detection

2020 ◽  
Vol 13 (1) ◽  
pp. 1
Author(s):  
Jing Wang ◽  
ZhongCheng Wu ◽  
Fang Li ◽  
Jun Zhang
Keyword(s):  
Data Augmentation ◽  
Driving Behavior ◽  
Mapping Method ◽  
Distracted Driving ◽  
Detection Model ◽  
Driving Behaviors ◽  
Actual Application ◽  
Original Dataset ◽  
Dangerous Driving ◽  
Activation Mapping

Distracted driving behavior has become a leading cause of vehicle crashes. This paper proposes a data augmentation method for distracted driving detection based on the driving operation area. First, the class activation mapping method is used to show the key feature areas of driving behavior analysis, and then the driving operation areas are detected by the faster R-CNN detection model for data augmentation. Finally, the convolutional neural network classification mode is implemented and evaluated to detect the original dataset and the driving operation area dataset. The classification result achieves a 96.97% accuracy using the distracted driving dataset. The results show the necessity of driving operation area extraction in the preprocessing stage, which can effectively remove the redundant information in the images to get a higher classification accuracy rate. The method of this research can be used to detect drivers in actual application scenarios to identify dangerous driving behaviors, which helps to give early warning of unsafe driving behaviors and avoid accidents.

scholarly journals INDIVIDUAL VALUE SYSTEM CHARACTERISTICS AND DRIVING BEHAVIOR RELATIONSHIPS

2017 ◽  
Vol 1 ◽  
pp. 570
Author(s):  
Krists Jānis Lazdiņš ◽  
Kristīne Mārtinsone
Keyword(s):  
Driving Behavior ◽  
Distracted Driving ◽  
Value System ◽  
System Integrity ◽  
Dangerous Driving ◽  
The Future ◽  
And Gender ◽  
The Individual ◽  
Individual Value ◽  
System Characteristics

The aim of research was to examine characteristics of individual value system prediction for driving behavior. It raised fundamental question for the research: 1. which of the individual value system characteristics predict driving behavior controlling gender and age. In the study participated 108 respondents, 40 (37.0%) men and 68 (63.0%) women who filled the questionnaire on the internet. There was used two questionnaires – „Latvian driving behavior survey”, The value and levels of availability relations in different spheres of life” The results showed that the value system integrity / disintegrity indicator predicts distracted driving, explains 18% of variation and is statistically significantly. Internal vacuum and age statistically significantly negatively predicts risky driving explaining 17% of variation. Age statistically significantly predicts safe and courteous driving, explains 12% of variation. Value system integrity / disintegrity indicator and gender, statistically significantly negatively predicts summary indicator of dangerous driving, explains 22% of variation. Age statistically significantly negatively predicts distracted driving, explains 30% of variation. Limitations of the research are related to the size of the sample, alignment of participants and use of new instruments, as well as data collection method. If the study would be repeated in the future, it would be desirable to increase the sample size and use approbated instrument. It would be interesting to find out how the value of individual factors predicts objective size of accidents and violations caused by driving. The results can serve as the basis to create new driving behavior interventions and also applicable to psychologist's professional work, when counseling individuals of this group, as well as can be used in the future development of the field, science and research.

scholarly journals Prediction for driving behaviour in connection with socio – demographic characteristics and individual value system

2018 ◽  
Vol 40 ◽  
pp. 03009
Author(s):  
K.J. Lazdins ◽  
K. Martinsone
Keyword(s):  
Driving Behavior ◽  
Demographic Characteristics ◽  
Distracted Driving ◽  
Value System ◽  
Driving Behaviour ◽  
System Integrity ◽  
Dangerous Driving ◽  
And Gender ◽  
The Individual ◽  
Individual Value

The aim of research „prediction for driving behaviour in connection with socio – demographic characteristics and individual value system” was to examine characteristics of individual value system prediction for driving behavior. It raised fundamental question for the research: 1. which of the individual value system characteristics predict driving behavior controlling gender and age. In the study 108 respondentsparticipated, 40 (37.0%) men and 68 (63.0%) women who filled the questionnaire on the Internet. Two questionnaires were used – „Latvian driving behavior survey” [1], the value and levels of availability relations in different spheres of life” [2, 3]. The results showed that the value system integrity / disintegrity indicator predicts distracted driving, explains 18% of variation and is statistically significantly. Internal vacuum and age statistically significantly negatively predicts risky driving explaining 17% of variation. Age statistically significantly predicts safe and courteous driving, explains 12% of variation. Value system integrity / disintegrity indicator and gender, statistically significantly negatively predicts summary indicator of dangerous driving explain 22% of variation. Age statistically significantly negatively predicts distracted driving, explains 30% of variation. The results can serve as the basis to create new driving behavior interventions and also applicable to psychologist's professional work, when counseling individuals of this group, as well as can be used in the future development of the field, science and research.

scholarly journals DrivingSense: Dangerous Driving Behavior Identification Based on Smartphone Autocalibration

2017 ◽  
Vol 2017 ◽  
pp. 1-15 ◽  
Author(s):  
Chunmei Ma ◽  
Xili Dai ◽  
Jinqi Zhu ◽  
Nianbo Liu ◽  
Huazhi Sun ◽  
...  
Keyword(s):  
Estimation Error ◽  
Drunk Driving ◽  
Speed Control ◽  
Driving Behavior ◽  
Sensor Reading ◽  
Driving Behaviors ◽  
Direction Change ◽  
Dangerous Driving ◽  
Filter Noise ◽  
The Impact

Since pervasive smartphones own advanced computing capability and are equipped with various sensors, they have been used for dangerous driving behaviors detection, such as drunk driving. However, sensory data gathered by smartphones are noisy, which results in inaccurate driving behaviors estimations. Some existing works try to filter noise from sensor readings, but usually only the outlier data are filtered. The noises caused by hardware of the smartphone cannot be removed from the sensor reading. In this paper, we propose DrivingSense, a reliable dangerous driving behavior identification scheme based on smartphone autocalibration. We first theoretically analyze the impact of the sensor error on the vehicle driving behavior estimation. Then, we propose a smartphone autocalibration algorithm based on sensor noise distribution determination when a vehicle is being driven. DrivingSense leverages the corrected sensor parameters to identify three kinds of dangerous behaviors: speeding, irregular driving direction change, and abnormal speed control. We evaluate the effectiveness of our scheme under realistic environments. The results show that DrivingSense, on average, is able to detect the driving direction change event and abnormal speed control event with 93.95% precision and 90.54% recall, respectively. In addition, the speed estimation error is less than 2.1 m/s, which is an acceptable range.

Classification of Distracted Driving Based on Visual Features and Behavior Data using a Random Forest Method

2018 ◽  
Vol 2672 (45) ◽  
pp. 210-221 ◽  
Author(s):  
Ying Yao ◽  
Xiaohua Zhao ◽  
Hongji Du ◽  
Yunlong Zhang ◽  
Jian Rong
Keyword(s):  
Random Forest ◽  
Characteristic Curve ◽  
Driving Behavior ◽  
Distracted Driving ◽  
Visual Features ◽  
Good Reliability ◽  
Driving Behaviors ◽  
Distraction Task ◽  
The Relationship

This research is to explore the relationship between a driver’s visual features and driving behaviors of distracted driving, and a random forest (RF) method is developed to classify driving behaviors and improve the accuracy of detecting distracted driving. Drivers were required to complete four distraction tasks while they followed simulated vehicles in the experiment. In data analysis, the features of distracted driving behaviors are first described, and the visual data are classified into three distraction levels based on the AttenD algorithm. Based on the collected data, this paper shows the relationship between visual features and driving behavior. Significant differences are discovered between different distraction tasks and distraction levels. Additionally, driving behavior data is used to build an RF model to classify distracted driving into three levels. Results demonstrate that this model is feasible to capture the classification of distraction and its accuracy for each distraction task is over 90%. Areas under receiver operating characteristic curve calculated through error-correcting output codes are mainly around 0.9, indicating good reliability. With this classification method, distraction levels could be classified with vehicle operation characteristics. The model established by this method could detect distractions in actual driving through the detection of driving behavior without the need of eye tracking systems.

Autonomous Vehicles’ Car-Following Drivability Evaluation Based on Driving Behavior Spectrum Reference Model

2021 ◽  
pp. 036119812199485
Author(s):  
Xiao Qi ◽  
Ying Ni ◽  
Yiming Xu ◽  
Ye Tian ◽  
Junhua Wang ◽  
...  
Keyword(s):  
Autonomous Vehicles ◽  
Reference Model ◽  
Numerical Test ◽  
Safety Evaluation ◽  
Driving Behavior ◽  
Car Following ◽  
Driving Behaviors ◽  
Human Driver ◽  
Normal Human ◽  
Naturalistic Driving

A large portion of the accidents involving autonomous vehicles (AVs) are not caused by the functionality of AV, but rather because of human intervention, since AVs’ driving behavior was not properly understood by human drivers. Such misunderstanding leads to dangerous situations during interaction between AV and human-driven vehicle (HV). However, few researches considered HV-AV interaction safety in AV safety evaluation processes. One of the solutions is to let AV mimic a normal HV’s driving behavior so as to avoid misunderstanding to the most extent. Therefore, to evaluate the differences of driving behaviors between existing AV and HV is necessary. DRIVABILITY is defined in this study to characterize the similarity between AV’s driving behaviors and expected behaviors by human drivers. A driving behavior spectrum reference model built based on human drivers’ behaviors is proposed to evaluate AVs’ car-following drivability. The indicator of the desired reaction time (DRT) is proposed to characterize the car-following drivability. Relative entropy between the DRT distribution of AV and that of the entire human driver population are used to quantify the differences between driving behaviors. A human driver behavior spectrum was configured based on naturalistic driving data by human drivers collected in Shanghai, China. It is observed in the numerical test that amongst all three types of preset AVs in the well-received simulation package VTD, the brisk AV emulates a normal human driver to the most extent (ranking at 55th percentile), while the default AV and the comfortable AV rank at 35th and 8th percentile, respectively.

scholarly journals Use of multilevel modeling to examine variability of distracted driving behavior in naturalistic driving studies

2021 ◽  
Vol 152 ◽  
pp. 105986
Author(s):  
Sara A. Freed ◽  
Lesley A. Ross ◽  
Alyssa A. Gamaldo ◽  
Despina Stavrinos
Keyword(s):  
Multilevel Modeling ◽  
Driving Behavior ◽  
Distracted Driving ◽  
Naturalistic Driving

scholarly journals Exploring the Influence of E-Hailing Applications on the Taxi Industry—From the Perspective of the Drivers

2021 ◽  
Vol 10 (2) ◽  
pp. 77
Author(s):  
Yitong Gan ◽  
Hongchao Fan ◽  
Wei Jiao ◽  
Mengqi Sun
Keyword(s):  
Driving Behavior ◽  
Urban Traffic ◽  
Behavior Changes ◽  
Transportation Industry ◽  
Trajectory Data ◽  
Long Distance ◽  
Taxi Drivers ◽  
Driving Behaviors ◽  
Taxi Industry ◽  
The Times

In China, the traditional taxi industry is conforming to the trend of the times, with taxi drivers working with e-hailing applications. This reform is of great significance, not only for the taxi industry, but also for the transportation industry, cities, and society as a whole. Our goal was to analyze the changes in driving behavior since taxi drivers joined e-hailing platforms. Therefore, this paper mined taxi trajectory data from Shanghai and compared the data of May 2015 with those of May 2017 to represent the before-app stage and the full-use stage, respectively. By extracting two-trip events (i.e., vacant trip and occupied trip) and two-spot events (i.e., pick-up spot and drop-off spot), taxi driving behavior changes were analyzed temporally, spatially, and efficiently. The results reveal that e-hailing applications mine more long-distance rides and new pick-up locations for drivers. Moreover, driver initiative have increased at night since using e-hailing applications. Furthermore, mobile payment facilities save time that would otherwise be taken sorting out change. Although e-hailing apps can help citizens get taxis faster, from the driver’s perspective, the apps do not reduce their cruising time. In general, e-hailing software reduces the unoccupied ratio of taxis and improves the operating ratio. Ultimately, new driving behaviors can increase the driver’s revenue. This work is meaningful for the formulation of reasonable traffic laws and for urban traffic decision-making.

scholarly journals Examining Risky Driving Behavior Among Older Drivers Using Self-Reported and Objective Data

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 465-465
Author(s):  
Jennifer Zakrajsek ◽  
Lisa Molnar ◽  
David Eby ◽  
David LeBlanc ◽  
Lidia Kostyniuk ◽  
...  
Keyword(s):  
Motor Vehicle ◽  
Seat Belt ◽  
Driving Behavior ◽  
Video Data ◽  
Older Drivers ◽  
Driving Frequency ◽  
Middle Aged ◽  
Risky Driving ◽  
Driving Behaviors ◽  
Study Results

Abstract Motor vehicle crashes represent a significant public health problem. Efforts to improve driving safety are multifaceted, focusing on vehicles, roadways, and drivers with risky driving behaviors playing integral roles in each area. As part of a study to create guidelines for developing risky driving countermeasures, 480 drivers (118 young/18-25, 183 middle-aged/35-55, 179 older/65 and older) completed online surveys measuring driving history, risky driving (frequency of engaging in distracted [using cell phone, texting, eating/drinking, grooming, reaching/interacting] and reckless/aggressive [speeding, tailgating, failing to yield right-of-way, maneuvering unsafely, rolling stops] driving behaviors), and psychosocial characteristics. A cluster analysis using frequency of the risky behaviors and seat belt use identified five risky behavior-clusters: 1) rarely/never distracted-rarely/never reckless/aggressive (n=392); 2) sometimes distracted-rarely/never reckless/aggressive (n=33); 3) sometimes distracted-sometimes reckless/aggressive (n=40); 4) often/always distracted-often/always reckless/aggressive (n=11); 5) no pattern (n=4). Older drivers were more likely in the first/lowest cluster (93.8% of older versus 84.2% of middle-aged and 59.3% of young drivers; p<.0001). Fifteen older drivers participated in a follow-up study in which their vehicles were equipped with a data acquisition system that collected objective driving and video data of all trips for three weeks. Analysis of video data from 145 older driver trips indicated that older drivers engaged in at least one distracted behavior in 115 (79.3%) trips. While preliminary, this suggests considerably more frequent engagement in distracted driving than self-reported and that older drivers should not be excluded from consideration when developing risky driving behavior countermeasures. Full study results and implications will be presented.

Sign in / Sign up

Export Citation Format

Share Document