Open AccessDivision of Driver’s Vision Plane Based on K-means Cluster Analysis
Author(s) -
Bingkui Ji,
Xueping Yao,
Yuzhuo Men,
Mingda Li
Publication year - 2020
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/440/4/042043
Subject(s) - cluster analysis , division (mathematics) , plane (geometry) , computer vision , computer science , artificial intelligence , fixation (population genetics) , cluster (spacecraft) , mathematics , geometry , population , arithmetic , demography , sociology , programming language
The division of the driver’s vision plane is the basis of study on the driver’s fixation objects and area of interest. This paper firstly collected the driver’s eye movement data through a large number of real road tests. Then, considering the driver’s areas of interest in driving, the K-means clustering was adopted to cluster plane coordinates of the drivers’ the fixation points to divide the driver’s vision plane. Through the comparison of the clustering results, the best clustering result was selected, and the driver’s vision plane was divided into eight regions. Finally, this paper studied the distribution of the drivers’ fixation points in each region at parking, straight going, left turn and right turn. The results have verified the higher accuracy of the K-means clustering for the division of the driver’s vision plane.