System for warning about intersection danger based on situation prediction

Abstract

Provided is a system for warning about intersection danger on the basis of behavior prediction. The system includes a sensor for detecting and predicting actions of surrounding objects, such as vehicles and pedestrians, and a function of providing an alarm feedback and can perform independent computation due to a separate processor installed therein for edge computing.

Description

CROSS-REFERENCE TO RELATED APPLICATION[0001]This application claims priority to and the benefit of Korean Patent Application No. 10-2020-0165864, filed on Dec. 1, 2020, the disclosure of which is incorporated herein by reference in its entirety.BACKGROUND1. Field of the Invention[0002]The present invention relates to a system for warning about intersection danger on the basis of situation prediction.2. Discussion of Related Art[0003]Pedestrian accidents account for 30% or more of the total traffic accident fatalities with about 1,300 people per year, and thus measures are necessary to reduce accidents. Particularly, at intersections, accidents caused by blind spots when vehicles make a right turn, accidents in school zones, etc. occur frequently. However, there are few systems and services that can mitigate the accidents other than speeding crackdown and punishment.[0004]Pedestrian safety systems currently in operation are manually managed through operation, such as 24-hour monitori...

AI Technical Summary

Benefits of technology

The present invention provides a system for warning about intersection danger based on behavior prediction. The system includes sensors to detect and predict the actions of surrounding objects, such as vehicles and pedestrians, and a function of providing alarm feedback. The system can perform independent computation due to a separate processor installed for edge computing. The system may include a first box for detecting vehicles and a second box for detecting pedestrians, with the same appearance, installed symmetrically with respect to a post. The system utilizes image data to determine the actions of the pedestrian and the movement of the vehicle. The system predicts the dangerous situation that may occur and notifies drivers and pedestrians through a warning display.

Problems solved by technology

Particularly, at intersections, accidents caused by blind spots when vehicles make a right turn, accidents in school zones, etc. occur frequently.

However, there are few systems and services that can mitigate the accidents other than speeding crackdown and punishment.

However, according to the pedestrian safety systems, manpower is inefficiently managed, and there is no alarm function.

Accordingly, there is no function of notifying pedestrians of danger, and it is not possible to perform the service function when information transmission is delayed due to communication between a server and RSUs or there is a communication failure.

This technology is useful for a straight road but has a disadvantage in that it is necessary to install auxiliary facilities at a crosswalk entrance and exit which pedestrians frequently pass through.

However, the information collector uses the LiDAR for all traveling vehicles, and thus it is difficult to accurately detect a vehicle that is actually dangerous to pedestrians.

Also, a driver is warned through a screen of a vehicle and thus prone to miss a dangerous situation.

Images