GM-HMM (Gaussian Mixture-Hidden Markov Model) driving behavior prediction method based on visual characteristics

Abstract

The invention provides a GM-HMM (Gaussian Mixture-Hidden Markov Model) driving behavior prediction method based on visual characteristics. A six-degree-of-freedom driving simulator and an eye tracker system are selected to carry out a simulation experiment, a fuzzy K-means dynamic clustering algorithm is adopted to divide the distribution of a driver interest visual field area, and the Pauta criterion of an improved Bessel formula is adopted again to remove abnormal line of sight points without a definite boundary among divided driver interest visual field areas; then, from an entry point of the visual representation parameter of a driver, a container type graph analysis method in mathematical statistics is adopted to verify the difference of the parameter through a NEMENYI rank sum test in SPSS (Statistic Package for Social Science) software, and the visual representation parameter sequence of the driver is determined through R type index clustering; and finally, a GM-HMM driving behavior prediction model is established, and the reliability of the GM-HMM driving behavior prediction method is analyzed.

Description

technical field [0001] The invention relates to the technical fields of driver assistance safety and automobile active safety, in particular to a GM-HMM prediction driving behavior method based on visual characteristics. Background technique [0002] Survey data show that traffic accidents caused by changing lanes account for about 4.0% of the total number of accidents provided by the police, and about 75% of such accidents are directly related to drivers. As the only object with subjective active consciousness in the human-vehicle-road system, the driver plays a decisive role in the safety of the traffic system. The research report of Daimler-Benz Company in Germany shows that if the driver can be warned 0.5s before the accident, 60% of rear-end collisions can be avoided, and if the time is increased by 1 second, 90% of rear-end collisions can be avoided. Therefore, it can be considered that the key to preventing traffic accidents caused by drivers is to predict their lane...

AI Technical Summary

Problems solved by technology

This kind of research only uses the general clustering method to determine the interest area of ​​the driver's sight point, ignoring the elimination of abnormal sight points, so that the actual division of each area is inaccurate

When selecting the driver's visual parameters to carry out the research on the driver's visual search law, the similarity between the parameters is ignored. Redundant parameter selection complicates the establishment of the driving behavior research model and affects the calculation speed and accuracy of the model.

Images