Traffic accident responsibility determination system based on machine learning

Abstract

The present invention discloses a traffic accident responsibility determination system based on machine learning, and relates to the technical field of traffic accident responsibility determination. The system comprises a traffic information interaction center, an image processing system and an accident responsibility analysis system. The traffic information interaction center comprises an image character receiving module and a determination result sending module; the image processing system comprises an image loading module, a color extraction module, a contour extraction module, a Gaussian Blur module and a distance analysis module; and the accident responsibility analysis system comprises a feature case search module and a comparison computing module. The traffic accident responsibilitydetermination system based on machine learning allow a reporter to replace the traffic police to perform photograph and evidence collection of a scene of a traffic accident and pass back informationin real time for responsibility analysis and determination so as to effectively reduce the time of scene measurement evidence collection, analysis and determination, is high in efficiency and accuratein determination, reduce human subjective factors, can recover the traffic as soon as possible and can avoid traffic congestion.

Description

Technical field [0001] The present invention relates to the technical field of traffic accident liability identification, and specifically relates to a traffic accident liability identification system based on machine learning and a liability identification method thereof. Background technique [0002] As people's living standards continue to improve, the number of motor vehicles continues to increase. Some drivers do not have a strong sense of safety, and road traffic accidents occur from time to time. After a traffic accident occurs, it is often accompanied by incidental traffic problems such as traffic congestion. As a result, the traffic police often cannot go to the accident site to collect evidence and analyze the responsibility in time. After the traffic police arrive at the scene, the road section of the accident should be closed to facilitate manual measurement of the ground markings at the scene of the accident and the brake marks of motor vehicles, and then determine ...

AI Technical Summary

Problems solved by technology

Some drivers do not have a strong sense of safety, and road traffic accidents occur from time to time

After a traffic accident, it is often accompanied by traffic jams and other incidental traffic problems, resulting in the traffic police often not being able to arrive at the accident scene in time to collect evidence and analyze their responsibilities

After the traffic police arrived at the scene, the road section of the accident should be closed to facilitate manual measurement of the ground markings at the accident site and the brake marks of motor vehicles, and then determine the responsibility for the accident. If the road section where the accident occurred is more complicated, On-site measurement and evidence collection may take a long time, and due to the different drawing levels of the traffic police, it cannot be standardized, and it may also take longer to draw

The longer the manual measurement time, the greater the impact on road traffic, which is very likely to cause secondary accidents

[0003] The Chinese Patent Publication No. CN104574882A discloses a judging system and judging method for traffic accidents in vehicles. The traffic accidents are monitored mainly through the vehicle-mounted terminal installed in the vehicle. The vehicle-mounted terminal mainly includes a GPS satellite module, a GSM module, and a 3D dynamic acceleration sensor. The GPS satellite module is used to accurately position the vehicle, the GSM module is used to transmit voice information, the 3D dynamic acceleration sensor is used to judge whether the vehicle has collided or rolled over, and the CPU processor is used to process the data. The vehicle-mounted terminal has a high technological component. Although it can realize the judgment of traffic accidents, it can only work on one car, which increases the purchase cost of the user and is not conducive to the rational use of resources.

[0004] The Chinese Patent Publication No. CN107067718A discloses a traffic accident liability assessment method, a traffic accident liability assessment device and a traffic accident liability assessment system, which are mainly used in driving recorders, including obtaining video images and driving information, and analyzing video images in combination with driving information. For traffic accidents, the analysis results are displayed as the basis for the assessment of the responsibility of traffic accidents, but its carrier is a driving recorder, and it is impossible to obtain the specific information of the accident in all directions, and there are certain defects

Images