Data Augmentation for Deep Learning Algorithms that Perform Driver Drowsiness Detection

Abstract

Driver drowsiness is one of the main causes of driver-related motor vehicle collisions, as this impairs a person's concentration whilst driving. With the enhancements of computer vision and deep learning (DL), driver drowsiness detection systems have been developed previously, in an attempt to improve road safety. These systems experienced performance degradation under real-world testing due to factors such as driver movement and poor lighting. This study proposed to improve the training of DL models for driver drowsiness detection by applying data augmentation (DA) techniques that model these real-world scenarios. This paper studies six DL models for driver drowsiness detection: four configurations of a Convolutional Neural Network (CNN), two custom configurations as well as the architectures designed by the Visual Geometry Group (VGG) (i.e. VGG16 and VGG19); a Generative Adversarial Network (GAN) and a Multi-Layer Perceptron (MLP). These DL models were trained using two datasets of eye images, where the state of eye (open or closed) is used in determining driver drowsiness. The performance of the DL models was measured with respect to accuracy, F1-Score, precision, negative class precision, recall and specificity. When comparing the performance of DL models trained on datasets with and without DA in aggregation, it was found that all metrics were improved. After removing outliers from the results, it was found that the average improvement in both accuracy and F1 score due to DA was +4.3%. Furthermore, it is shown that the extent to which the DA techniques improve DL model performance is correlated with the inherent model performance. For DL models with accuracy and F1-Score ≤ 90%, results show that the DA techniques studied should improve performance by at least +5%.

Driver Drowsiness Multi-Method Detection for Vehicles with Autonomous Driving Functions

“…Even so, the algorithm is much more reliable than a variant which uses the eye detection variant (using the classification model 'EyePairBig' or 'EyePairSmall') when the detection is much worse. The face tracking algorithm in this case is sufficiently robust to work properly even in relatively extreme cases (Figure 11) [36][37][38]. Having detected the feature points, we can apply a point tracker algorithm, whic our case was the Kanade-Lucas-Tomasi (KLT) algorithm [35].…”

Detection of Drowsiness among Drivers Using Novel Deep Convolutional Neural Network Model

“…In one of the experimental studies, we applied several data augmentation steps such as rescaling, flipping, zooming, and rotating, as suggested in earlier research [22,43], to address the issue of limited data availability, which causes over-fitting of the model. Below, an explanation of each data augmentation method is given along with its impact.…”