A traffic accident recording and reporting model at intersections

In this paper, we suggested a vision-based traffic accident detection algorithm and developed a system for automatically detecting, recording, and reporting traffic accidents at intersections. A system with these properties would be beneficial in determining the cause of accidents and the features of an intersection that impact safety. This model first extracts the vehicles from the video image of the charge-couple-device camera, tracks the moving vehicles (MVs), and extracts features such as the variation rate of the velocity, position, area, and direction of MVs. The model then makes decisions on the traffic accident based on the extracted features. In a field test, the suggested model achieved a correct detection rate (CDR) of 50 % and a detection rate of 60 %. Considering that a sound-based accident detection system showed a CDR of 1% and a DR of 66.1%, our result is a remarkable achievement.