Driving Style Recognition of Leading Vehicles based on Semi-supervised Gaussian Mixture Model

Abstract

Driving style recognition of leading vehicles is important to ensure driving safety and improve the efficiency of road traffic. Current supervised learning based methods achieve high recognition accuracy, but their annotations are labor-intensive and time-consuming in practical scenarios. Although unsupervised learning based methods do not require manual labeling, their recognition accuracy is still low. In order to reduce the labeling cost and improve the accuracy of driving style recognition simultaneously, we propose a driving style recognition method based on semi-supervised Gaussian mixture model. Firstly, the driving data is collected and pre-processed by OBD-II vehicle recorder, and 22-dimensional driving style feature parameters are selected and constructed. Secondly, the kernel principal component analysis method is used to reduce the dimensionality and obtain 6-dimensional discriminative principal components. Finally, the Gaussian mixture model is trained by utilizing both the labeled data and unlabeled data. Concretely, the model parameters are measured by the expectation maximization algorithm and the likelihood function. The simulation experimental results demonstrate that the proposed method can effectively improve the driving style recognition accuracy, as well as reduce the reliance on labeled data.