Abstract
Introduction:Traffic accidents are easy to occur in the tunnel due to its special environment, and the consequences are very serious. The existing vehicle accident detection system and CCTV system have the issues of low detection rate.Methods:A method of using Mel Frequency Cepstrum Coefficient (MFCC) to extract sound features and using a deep neural network (DNN) to learn sound features is proposed to distinguish accident sound from the non-accident sound.Results and Discussion:The experimental results show that the method can effectively classify accident sound and non-accident sound, and the recall rate can reach more than 78% by setting appropriate neural network parameters.Conclusion:The method proposed in this research can be used to detect tunnel accidents and consequently, accidents can be detected in time and avoid greater disasters.
Highlights
Traffic accidents are easy to occur in the tunnel due to its special environment, and the consequences are very serious
The method proposed in this research can be used to detect tunnel accidents and accidents can be detected in time and avoid greater disasters
Compared with vehicle accident detection systems and video detection, sound detection has the advantages of low cost and fast detection speed
Summary
Traffic accidents are easy to occur in the tunnel due to its special environment, and the consequences are very serious. The increase in tunnel accidents has become an important issue as the number and length of tunnels have been increased due to many mountains' geographical characteristics and the human pursuit of low time and inexpensive transportation costs [1]. Because of narrow space and tunnel vision, secondary accidents often occur, so the consequences of tunnel accidents are more serious than ordinary roads [2]. There are three characteristics of tunnel accidents. Tunnels are prone to fire, and the number of casualties is more than that of ordinary roads [3]. Tunnel accident detection system is more important than the general road traffic management system
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
