Deep Residual Learning-Based Convolutional Variational Autoencoder for Driver Fatigue Classification

Abstract

Driving under the influence of fatigue often results in uncontrollable vehicle dynamics, which causes severe and fatal accidents. Therefore, early warning on the fatigue onset is crucial to avoid occurrences of such kind of a disaster. In this paper, the authors have investigated a novel semi-supervised convolutional variational autoencoder-based classification approach to classify the state of the driver. A convolutional variational autoencoder is a generative network. The authors have proposed a discriminative model using convolutional variational autoencoders and residual learning. This approach calculates an intermediate loss base on deep features of the network in addition to the label information in training. The loss obtained by this method helps the training to be more effective on the model and leads to better accuracy in driver fatigue classification. The trained model has managed to classify driver fatigue with higher accuracy (97%) than the other successful models taken into comparison, proving that the proposed method is more practical for computing classification loss for driver fatigue to currently available methods.