An Automatic Detection Method of Traffic Accidents Based on Collision Sound

Abstract

The invention relates to an automatic detection method for traffic accidents based on collision sound. The collected sound signals are divided into frames, and the total energy distribution in the time domain is detected first. Processing of one frame; next, judge the energy distribution in the frequency domain, use wavelet to extract the characteristic components of the energy distribution and judge, if the collision condition is met, further recognition will be carried out, otherwise, it will directly jump out and wait for the processing of the next frame; finally, perform ACF detection , if the condition of collision is met, it is judged as a collision sound, otherwise, it waits for the processing of the next frame. The invention can suppress the calculation amount to the minimum while improving the detection accuracy rate and reducing the false alarm rate.

Description

technical field [0001] The invention relates to the technical field of automatic detection of traffic accidents, in particular to a method for detecting traffic accidents using sound signals. Background technique [0002] Compared with the development of automatic incident detection technology, the research on major traffic accident detection lags behind. Traditional traffic incident detection devices are mainly divided into vehicle detection equipment based on magnetic frequency signals, vehicle detection equipment based on spectrum signals and vehicle detection equipment based on video signals. However, various sensors including cameras, ultrasonic waves, and microwaves are used to detect traffic incidents, mainly focusing on macroscopic road traffic flow information such as road flow, vehicle occupancy, traffic density, etc. The detection of microscopic phenomena such as traffic accidents is indirect. ,not effectively. At present, the most effective method of calling th...

AI Technical Summary

Problems solved by technology

[0005] Most of the existing detection algorithms based on audio signals are conducted offline experiments in a laboratory environment. For limited specific samples, a high detection rate and a low false positive rate have been achieved.

However, for the actual complex traffic environment, the sound signal changes in various ways, and the ideal effect cannot be achieved; some algorithms also have the disadvantage that the huge amount of calculation is not conducive to real-time detection

Images