An Analysis on Acoustic Characteristic of the Intersection Noise for Perfomance Improvement in the Accident Sound Detection System

In this paper, it was performed the analysis on various intersection acoustic patterns for detection rate improvement of accident sound detection system: an acoustic pattern analysis on general traffic noise, an acoustic pattern analysis on engine noise, an acoustic pattern analysis on interfering elements in accident sound detection system.Consequently, traffic accident detection rate will be increased more about 2~3 percent than present 90 percent more or less if the result of this research will be applied to the today's image detection system. There are remarkable differences between an acoustic pattern of traffic noise and one of accident sound, and we must consider a changeable factor when we compose an accident traffic detection system by acoustics because there is error range of 20[dB] according to the volume of traffic in intersection. Also, it is prospected that the acoustic patterns of vehicles type-related engine noise have an insignificant effect on the accident sound detection system because the numerical values of sound pressure are considerably low. Generally, the acoustic patterns of vehicles' horn sound and special purposed- vehicles' sirens have similar sound pressure to the one of accident acoustic patterns but their frequency wave forms are distinctive periodic type, which is quite different from one of accident sound. Consequently, traffic accident detection rate will be increased more about 2~3 percent than present 90 percent more or less if the result of this research will be applied to the today's image detection system.