Intelligent traffic accident detection system based on mobile edge computing

Abstract

The lack of awareness of the traffic accident ahead would probably cause serious congestion or more serious secondary traffic accidents. Usually, accident detection is to use equipment in vehicles to detect accidents and send accident information to related people by SMS containing texts only, which is expensive, inconvenient and cannot avoid secondary accidents. This paper proposes an intelligent traffic accident detection system based on Mobile Edge Computing with proximity, low latency and computing and vehicle identification. Our system utilizes common smartphones to obtain acceleration and speed, and identifies images showing accident scenes mainly at servers in case of false positives, realizing automation of accident detection and notifying surroundings and departments like hospitals and department of transportation in real time. Besides, our system can also report the finishing of accidents according to crowd sensing. The experimental results demonstrate our system can work in real time with simulated data.