Driver Monitoring System Based on CNN Models: An Approach for Attention Level Detection

Abstract

Drivers provide a wide range of focus characteristics that can evaluate their attention level and analyze their behavioral states while driving. This information is critical for the development of new automated driving functionalities that support and assist the driver according to his/her state, ensuring safety for them and other users on the road. In this sense, this paper proposes a Driver Monitoring System (DMS) based on image processing and Convolutional Neural Networks (CNN), that analyzes two important driver distraction aspects: inattention of the road and drowsiness. Our approach makes use of CNN models for detecting the gaze and the head direction, which involves training datasets with different pre-defined labels. Additionally, the system is complemented with the drowsiness level measurement, using face features to detect the time that the eyes are closed or opened, and the blinking rate. Crossing the inference results of these models, the system can provide an accurate estimation of driver attention level. The different parts of the presented DMS have been trained in a Hardware-in-the-loop driving simulator with an eye fish camera. It has been tested as a real-time application recording driver with different characteristics.