Research on Vehicle Lane Change Recognition Based on ABC-SVM Algorithm

Abstract

To solve the problem that it is difficult to accurately identify and predict vehicle lane change, a support vector machine (SVM) algorithm optimized by artificial bee colony is proposed to build a vehicle lane change recognition model. Using the real vehicle trajectory data set NGSIM, the reasonable lane-changing vehicle data is screened out, and the Kalman filter is used to denoise the sample data. To make lane change trajectory data more accurate, K-Means clustering algorithm is proposed to extract vehicle lane change data. Because the penalty factor and kernel function parameters of SVM are not easy to determine, artificial bee colony (ABC) algorithm is used to determine the key parameters of SVM. The experimental results show that the prediction accuracy of the improved vehicle lane change recognition model is more than 96.19%, which can improve the accuracy of vehicle lane change recognition.