| Complexity of Driving Scenarios Based on Traffic Accident Data
|
| Xinchi Dong 1, Daowen Zhang 1, Yaoyao Mu 1, Tianshu Zhang 3, Kaiwen Tang 1 |
1School of Automobile and Transportation , Xihua University
2Vehicle Measurement Control and Safety Key Laboratory of Sichuan Province , Xihua University
3Engineering, Computer and Mathematical Sciences , The University of Adelaide |
|
|
|
|
|
|
|
| ABSTRACT |
|
To solve the problems of diffi cult quantifi cation of complex driving scenes and unclear classifi cation, a method of complex
measurement and scene classifi cation was proposed. Based on the Bayesian network, the posterior probability distribution
was obtained, the variable weights were determined by information entropy theory and BP neural network, and the gravitational
model was improved so that the complex metric model of the driving scene was established, the static and dynamic
complexity of the scene was quantifi ed respectively, and a weighted fusion of the two was conducted. The K-means clustering
method was used to divide the driving scenario into three categories, i.e., simple scenario, medium complex scenario, and
complex scenario, and the rationality of the method was verifi ed by experiments. This scenario complex metric method can
provide a reference for studying the complex metrics and scene classifi cation of smart vehicle test scenarios. |
| Key Words:
Traffi c safety · Driving scenes · Scene complexity · Traffi c accident data · Complex quantitative model |
|
Corresponding Author.
Daowen Zhang , Email. 
Preview 
Full text via DOI 
Download Citation
Print
