Abstract
Introduction:An acoustic signal-based tunnel accident detection system was developed in this study. In a tunnel environment, the sound diffusion effect is minimized and thanks to that, discrimination of accident sounds (crash and skid) from other noises can apparently be accomplished.Discussion:The system is composed of three parts: algorithm, field device, and center system. To distinguish accident-related acoustic signals such as a crash or skid among various other sounds in a tunnel, a delicate algorithm that can discriminate those signals from other normal signals generated from moving vehicles was created.Conclusion:The developed algorithm processes acoustic signals to filter out noises and to identify accident-related signals. The field device, installed in a tunnel, collects analog sounds, transforms them into digital signals, and transmits the digital signals to the server in the tunnel traffic management center. Lastly, in the tunnel traffic management center, the acoustic signal processing algorithm described above, installed in a server system, can instantaneously detect accidents. Once confirmed by the system operators, the information on the detected accidents is intended to be provided to drivers following behind as well as relevant agencies to prevent secondary accidents and to respond promptly. The developed system was evaluated in a real tunnel environment using traffic accident sounds acquired from real crash tests. The detection rates were 95, 91, and 80% at distances of 10, 30, and 50 m, respectively with a detection duration less than 1.4 s. Compared to conventional detection systems using loop detectors or video images that have a long detection time of around 1 min, the developed system can be regarded as superior in that it has an extremely short detection time, which, of course, is one of the most important factors for automatic incident detection systems.
Highlights
An acoustic signal-based tunnel accident detection system was developed in this study
Compared to False-alarm Rate (FAR) and Mean Time to Detection (MTTD), Detection Rate (DR) represented significantly different performances by distance, showing a decreasing performance pattern as the field device becomes further from the sound generator
The consequence of the minor difference in FAR may be highly significant because, according to a survey, the reluctance of road agencies to deploy incident detection systems is normally attributed to high FARs [22]
Summary
An acoustic signal-based tunnel accident detection system was developed in this study. The sound diffusion effect is minimized and thanks to that, discrimination of accident sounds (crash and skid) from other noises can apparently be accomplished. The NTF technique is applied to improve the Signal-to-Noise Ratio (SNR) by discriminating incident-associated sounds from other normal sounds in the basis tensor database and subsequently to initially detect incidents using the mean-to-max threshold on the channel gain of acoustic signals. (3) shows the noise-filtering process by the NTF algorithm on tunnel incidents (crash and skid), and the improvements in SNRs for sounds (30 samples) gathered at distances of 10 and 50 m from the sound generator were 14 and 17 dB on average, indicating that the proposed algorithm can be effectively applied to a tunnel environment where the principal noises are composed of echoes from the wall.
Sign-in/Register to view highlights & summary 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 callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
