Survey on Detection and Identification of Abnormal Driving Behaviors

Abstract

Real-time abnormal driving behaviors monitoring is a corner stone to improving driving safety. Existing
works on driving behaviors monitoring using smart phones only provide a coarse-grained result, i.e. distinguishing
abnormal driving behaviors from normal ones. To improve drivers’ awareness of their driving habits so as to prevent
potential car accidents, we need to consider a fine-grained monitoring approach, which not only detects abnormal
driving behaviors but also identifies specific types of abnormal driving behaviors, i.e. Weaving, Swerving, Side slipping,
Fast U-turn, Turning with a wide radius and Sudden braking. Through empirical studies of the 6-month driving traces
collected from real driving environments, we find that all of the six types of driving behaviors have their unique patterns
on acceleration and orientation. Recognizing this observation, we further propose a fine-grained abnormal Driving
behavior Detection and identification system to perform real-time high-accurate abnormal driving behaviors monitoring
using smart phone sensors. We extract effective features to capture the patterns of abnormal driving behaviors [2]. After
that, two machine learning methods, rash driving, or officially driving under the Influence (DUI) of alcohol, is a major
cause of traffic accidents throughout the world. In this, we propose a highly efficient system aimed at early detection and
alert of dangerous vehicle maneuvers typically related to rash driving. The whole solution requires only a mobile placed
in vehicle and with accelerometer sensor. A program installed on the mobile automatically computes accelerations based
on sensor readings, and compares them with typical rash driving patterns extracted from real driving tests. Once any
evidence of rash driving is present, the mobile phone will automatically alert the driver or sends a message to predefined
number in application for help well before accident actually happens.