Research on recognition method of vehicle automatic lane change behavior

Bo Fan; Yongneng Xu

doi:10.1117/12.2627999

14 March 2022 Research on recognition method of vehicle automatic lane change behavior

Bo Fan, Yongneng Xu

Proceedings Volume 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021); 121650P (2022) https://doi.org/10.1117/12.2627999
Event: 2021 International Conference on Intelligent Traffic Systems and Smart City, 2021, Zhengzhou, China

Abstract

Automatic safe lane changing is the key to the realization of unmanned vehicles. To accurately identify the lane changing state of driving vehicles to ensure driving safety, this paper establishes a vehicle automatic lane changing behavior recognition model based on the multi-class support vector machine. This paper selects vehicle trajectory data from the NGSIM data set for classification processing and uses genetic algorithm optimized particle swarm optimization (GA-PSO) to optimize and calibrate the penalty parameter C and the kernel parameter g in the multi-class support vector machine model. Using sample data to train and test lane-changing behavior recognition models and the research shows that the model can well recognize the behavior of the vehicle during the automatic lane changing process and provide support for the study of the vehicle lane changing phase.

Citation Download Citation

Bo Fan and Yongneng Xu "Research on recognition method of vehicle automatic lane change behavior", Proc. SPIE 12165, International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2021), 121650P (14 March 2022); https://doi.org/10.1117/12.2627999

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available