A Novel Model-Based Driving Behavior Recognition System Using Motion Sensors.

Minglin Wu,Sheng Zhang,Yuhan Dong

doi:10.3390/s16101746

Minglin Wu, Sheng Zhang + Show 1 more

Open Access

https://doi.org/10.3390/s16101746

Copy DOI

Abstract

In this article, a novel driving behavior recognition system based on a specific physical model and motion sensory data is developed to promote traffic safety. Based on the theory of rigid body kinematics, we build a specific physical model to reveal the data change rule during the vehicle moving process. In this work, we adopt a nine-axis motion sensor including a three-axis accelerometer, a three-axis gyroscope and a three-axis magnetometer, and apply a Kalman filter for noise elimination and an adaptive time window for data extraction. Based on the feature extraction guided by the built physical model, various classifiers are accomplished to recognize different driving behaviors. Leveraging the system, normal driving behaviors (such as accelerating, braking, lane changing and turning with caution) and aggressive driving behaviors (such as accelerating, braking, lane changing and turning with a sudden) can be classified with a high accuracy of 93.25%. Compared with traditional driving behavior recognition methods using machine learning only, the proposed system possesses a solid theoretical basis, performs better and has good prospects.

Highlights

With rapid economic development, vehicle ownership worldwide has been increasing in recent years
We proposed a novel model-based driving behavior recognition system using motion sensors
The physical model built and data change rule deduced promise the system a good performance with an average accuracy of 93.25% in classifying all 14 types of driving behaviors acquired in real traffic conditions

Summary

Introduction

Vehicle ownership worldwide has been increasing in recent years. In addition to increasingly severe road congestion, the growing number of vehicles is posing a threat to traffic safety and social security. About 60 thousand people die and over 200 thousand people get wounded in traffic accidents every year and more than ninety percent of fatal accidents are caused by offensive driving behavior [2]. To admonish aggressive drivers and eliminate this phenomenon, many articles [3,4,5,6,7] have discussed and emphasized the recognition of typical driving behaviors. Recognizing drivers’ behaviors (including normal driving behaviors and aggressive driving behaviors), recording their driving patterns and feeding information on their driving behaviors back to themselves or relevant departments can help to promote safer driving, reduce traffic accidents and contribute to social safety

Methods

Results

Conclusion