Practical Analysis of Dangerous Driving Characteristic via Recorded Data of Drive-recorder

Abstract

In this research, from the viewpoint of improving traffic safety policies, we focus on clarifying the characteristics of dangerous driving events (stop sign violation, ignoring traffic light, pedestrian disturbance, excessive speed etc.) which are thought to be closely related to traffic accidents. Conventional studies on traffic safety focused mainly on improvement of road structure etc. and aimed at extraction of dangerous places or spots from probe data, meanwhile this research focuses on dangerous driving behaviors which are initial but hidden cause of traffic accident. In addition, analysis of whole set of data which includes both of Video and GPS data during whole travel hours stored in drive recorders of 175 participants, which is unprecedented. As a result, it was shown that the dangerous driving has a certain occurrence tendency, which is attributed to the individual characteristics of the driver, the driving place, and the driving hours. The results of this research can be expected to contribute to effective driving safety enlightenment campaigns for reducing traffic accidents.