Abstract

Because aggressive driving often causes large-scale loss of life and property, techniques for advance detection of adverse driver emotional states have become important for the prevention of aggressive driving behaviors. Previous studies have primarily focused on systems for detecting aggressive driver emotion via smart-phone accelerometers and gyro-sensors, or they focused on methods of detecting physiological signals using electroencephalography (EEG) or electrocardiogram (ECG) sensors. Because EEG and ECG sensors cause discomfort to drivers and can be detached from the driver’s body, it becomes difficult to focus on bio-signals to determine their emotional state. Gyro-sensors and accelerometers depend on the performance of GPS receivers and cannot be used in areas where GPS signals are blocked. Moreover, if driving on a mountain road with many quick turns, a driver’s emotional state can easily be misrecognized as that of an aggressive driver. To resolve these problems, we propose a convolutional neural network (CNN)-based method of detecting emotion to identify aggressive driving using input images of the driver’s face, obtained using near-infrared (NIR) light and thermal camera sensors. In this research, we conducted an experiment using our own database, which provides a high classification accuracy for detecting driver emotion leading to either aggressive or smooth (i.e., relaxed) driving. Our proposed method demonstrates better performance than existing methods.

Highlights

  • Aggressive driving causes most car accidents and accounts for the largest percentage of fatal crashes [1]

  • In view of the problems and constraints of previous works explained in Section 2, our research proposes a convolutional neural networks (CNN)-based method for detecting a driver’s aggressive driving emotion using facial images obtained from both NIR and thermal cameras

  • This is, because humans failed to observe tiny and fine changes in the facial images, whereas CNN could successfully extract these changes as features for emotion recognition

Read more

Summary

Introduction

Aggressive driving causes most car accidents and accounts for the largest percentage of fatal crashes [1]. For such a serious problem, detection of aggressive driving has been relegated mainly to traffic police officers. Most previous studies have attempted to detect the drivers’ aggressive behaviors by observing vehicle movement using accelerometers and gyro-sensors installed on a smart phone [2,3,4,5,6]. Not aimed at detecting aggressive driving, there was a study on driving behavior using steering wheel angles as the input and output [7]. Others used the drivers’ facial features [8,9,10,11], voice signals, car–voice interactions [12,13], or bio-signals [11,14,15,16] to help recognize up to six types of emotions

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call