Dangerous scene identification method and system based on graph classification

Abstract

The invention discloses a dangerous scene recognition method and system based on graph classification, and belongs to the technical field of automobile intelligent interaction. The method comprises the following steps: collecting operation information of a driver, extracting driving characteristic parameters, and collecting traffic scene information around the vehicle; extracting dynamic and static characteristics of the traffic scene according to the acquired traffic scene information; expressing as an undirected graph with node labels by using a graph method according to the acquired dynamicand static characteristics of the traffic scene; and identifying the danger level of the traffic scene according to the generated undirected graph of the traffic scene with the node labels. Urban traffic environment dangerous scene identification is realized based on graph classification, a dangerous scene label is obtained according to clustering of driving operation information and vehicle driving information, a label more conforming to data distribution characteristics is generated, a dangerous scene in a traffic scene is accurately identified through the driving information, the traffic dangerous scene identification accuracy is improved. The identified traffic danger scene is enabled to better accord with the actual driving environment, and the adaptability and safety of the drivingenvironment are improved.

Description

technical field [0001] The invention belongs to the technical field of automobile intelligent interaction, and in particular relates to a method and system for identifying dangerous scenes based on graph classification. Background technique [0002] With the start of car intelligence, people's demand for a good car experience makes people hope that cars will understand themselves more and more, and customize corresponding service content and assisted driving according to their own status and needs. [0003] Inaccurate or slow recognition of dangerous scenes by drivers is one of the important reasons leading to traffic accidents. At present, there are many problems in the identification methods of dangerous scenes. The elements in the system (such as vehicles and non-motor vehicles, etc.) are identified separately and the overall danger level of the scene is calculated, but there are problems such as inaccurate identification. And because there is no unified representation f...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems in the prior art that the identification accuracy of dangerous traffic scenes is low, the technical difficulty is high, and there is no unified framework to represent traffic scenes, the purpose of the present invention is to provide a A method and system for identifying dangerous scenes of urban traffic environment based on graph classification, by establishing a unified framework to represent traffic scenes, realizing the identification of dangerous scenes of urban traffic environment, improving the accuracy of identifying traffic dangerous scenes, and the present invention has strong environmental adaptability , the identified traffic hazard scene is more in line with the actual driving environment, improving driving safety

Images