Classification of driver fatigue expressions by combined curvelet features and gabor features, and random subspace ensembles of support vector machines

Abstract

In order to develop Human-centric Driver Fatigue Monitoring Systems HDFMS with aims to increase driving safety, an efficient combined features extraction from Curvelet transform and Gabor wavelet transform for fatigue expressions descriptions of vehicle drivers is proposed, and Random Subspace Ensemble RSE of Support Vector Machines SVMs with polynomial kernel as the base classifier is then exploited for classification of three predefined fatigue expressions classes, namely, awake expressions, moderate fatigue expressions, and severe fatigue expressions. The results of holdout and cross-validation experiments show that CF by RSE of SVMs with polynomial kernel outperforms other seven classifiers, i.e., Curvelet features by SVMs classifier, Gabor features by SVMs classifier, CF by five individual SVMs classifiers. With CF and RSE of SVMs with polynomial kernel, the classification accuracies of drivers' fatigue expressions are over 90% in both of the holdout and cross-validation experiments, which show the proposed approach of combined features extraction and RSE of SVMs can be used for developing Human-centric Driver Fatigue Monitoring Systems to increase driving safety.