A Study on Building a “Real-Time Vehicle Accident and Road Obstacle Notification Model” Using AI CCTV

Chaeyoung Lee,Illchul Doo,Hyomin Kim,Sejong Oh

doi:10.3390/app11178210

Abstract

This research produced a model that detects abnormal phenomena on the road, based on deep learning, and proposes a service that can prevent accidents because of other cars and traffic congestion. After extracting accident images based on traffic accident video data by using FFmpeg for model production, car collision types are classified, and only the head-on collision types are processed by using the deep learning object-detection algorithm YOLO (You Only Look Once). Using the car accident detection model that we built and the provided road obstacle-detection model, we programmed, for when the model detects abnormalities on the road, warning notification and photos that captures the accidents or obstacles, which are then transferred to the application. The proposed service was verified through application notification simulations and virtual experiments using CCTVs in Daegu, Busan, and Gwangju. By providing services, the goal is to improve traffic safety and achieve the development of a self-driving vehicle sector. As a future research direction, it is suggested that an efficient CCTV control system be introduced for the transportation environment.

Highlights

This study implements a system that prevents the occurrence of secondary traffic accidents and traffic jams by detecting abnormalities on roads, such as car accidents and obstacles, through AI and CCTV, and delivering information related to the accidents
The map shows the origin, destination location and CCTV location used in the experiment
It is assumed that virtual AI CCTVs are located at the northern end of Han River Bridge and the southern end of Banpo Bridge

Summary

Introduction

This study implements a system that prevents the occurrence of secondary traffic accidents and traffic jams by detecting abnormalities on roads, such as car accidents and obstacles, through AI (artificial intelligence) and CCTV (closed-circuit television), and delivering information related to the accidents. A secondary traffic accident here refers to an accident caused by a driver staying in or getting off the vehicle and colliding with a subsequent vehicle while stopping due to a vehicle failure or a prior accident. Secondary accidents occur when the drivers of a vehicle do not evacuate completely after the first car accident or when the drivers of follow-up vehicles do not pay enough attention or they lack caution. Secondary accidents are often caused by hitting a vehicle that has stopped, the death rate of which is about five times higher than first car accidents [1]. To prevent secondary accidents from occurring, it is required to notify the situation to the following vehicles through emergency lights and to avoid going into safe zones. This is why drivers can not be aware of obstacles on the road in advance, so car accidents happen

Methods

Results

Discussion

Conclusion