Driver eye movement glancing-based safe driving recommendation method in urban environment

Abstract

The invention discloses a driver eye movement glancing-based safe driving recommendation method in an urban environment, and the method comprises the following steps: collecting a driving video of a subject, obtaining the fixation points of the subject and a model, and obtaining key features through a classical attention model; constructing a neural network, and selecting the most suitable fixation point; determining a final recommended safe driving scheme by optimizing the fixation point; under a crowded road environment, by comparing the difference between the glancing tracks between the subject and the model, the glancing accuracy can be improved, the safety can be met, a safe driving scheme can be recommended, safe driving can be realized, and a reference is provided for completely autonomous driving in the future.

Description

technical field [0001] The invention relates to driver attention analysis and modeling technology, in particular to a safe driving recommendation method in an urban environment based on the driver's eye movement saccade. Background technique [0002] Computational modeling of human visual attention has received extensive attention in recent decades. In contemporary advanced industrial applications, it has been shown to predict human visual attention very similarly. However, there has been controversy over whether the eye saccade position predicted by human visual attention (Visual Saccades) or the eye saccade position predicted by the computational visual attention model (Saccades Predicted by Computational Visual Attention Model) is more reliable and whether it is actually helpful for actual driving. . [0003] Considering that biological inspiration for driving-related attention models can be obtained from skilled drivers under complex driving conditions, the driver's at...

AI Technical Summary

Problems solved by technology

However, there has been controversy over whether the eye saccade position predicted by human visual attention (Visual Saccades) or the eye saccade position predicted by the computational visual attention model (Saccades Predicted by Computational Visual Attention Model) is more reliable and whether it is actually helpful for actual driving.

Images