Online Perception Method of Driver's Passive Driving State Based on Hierarchical Network Model

Abstract

The invention discloses a hierarchical network model-based driver passive driving state online sensing method, which comprises the following steps of: grading driver passive driving states, selectingcharacteristic parameters capable of representing the driver passive driving states, and constructing a hierarchical network model for training until the hierarchical network model meets system errorrequirements; acquiring driving information, operation information and face information in the current driving process in real time, and extracting driving characteristic information in the driving information, operation characteristic information in the operation information and face characteristic information in the face information; and inputting the extracted feature information into a hierarchical network model for calculation to obtain the negative driving degree of the current driver. According to the method, the negative driving state of the driver can be identified on line through theextracted features, the negative driving state detection precision can be effectively improved, a foundation is laid for improving the driving safety, and the method has good real-time performance and mobility and has wide application prospects.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and mainly relates to an online perception method of a driver's passive driving state based on a layered network model. Background technique [0002] With the rapid increase of China's car ownership in recent years, the issue of road traffic safety has become a social focus. According to incomplete statistics, nearly 100,000 people lose their lives due to vehicle traffic accidents in my country every year. Traffic accidents have become the most casualties in various accidents in the country, and traffic safety accidents caused by passive driving state account for a large proportion. Part of it seriously threatens the life and property safety of the broad social groups. Therefore, monitoring and adjusting the driver's negative driving state that affects driving behavior can better reduce dangerous driving behavior and ensure traffic safety. [0003] At present, the domestic and foreign rese...

AI Technical Summary

Problems solved by technology

Among them, the research on the mechanism of negative driving state, the behavior performance and adverse effects of negative driving state is relatively mature, but there are few studies on the perception of negative driving state, and the subjective investigation method is mainly used, that is, through interviews, questionnaires and observations. Discriminate the driver's passive driving state in the form of other methods

Although the subjective investigation method is direct and simple, it is easily affected by the driver's subjective factors and has a time lag, and cannot provide timely and effective assistance to the driver and early warning of negative states such as driving safety.

Images