Fusion of optimized indicators from Advanced Driver Assistance Systems (ADAS) for driver drowsiness detection

Abstract

This paper presents a non-intrusive approach for monitoring driver drowsiness using the fusion of several optimized indicators based on driver physical and driving performance measures, obtained from ADAS (Advanced Driver Assistant Systems) in simulated conditions. The paper is focused on real-time drowsiness detection technology rather than on long-term sleep/awake regulation prediction technology. We have developed our own vision system in order to obtain robust and optimized driver indicators able to be used in simulators and future real environments. These indicators are principally based on driver physical and driving performance skills. The fusion of several indicators, proposed in the literature, is evaluated using a neural network and a stochastic optimization method to obtain the best combination. We propose a new method for ground-truth generation based on a supervised Karolinska Sleepiness Scale (KSS). An extensive evaluation of indicators, derived from trials over a third generation simulator with several test subjects during different driving sessions, was performed. The main conclusions about the performance of single indicators and the best combinations of them are included, as well as the future works derived from this study.

Figure 1.

Simulation test design. (a) Simulation environment overview; (b) Driving sessions schema.

Figure 2.

General architecture of our Drowsiness Detection System.

Figure 3.

Temporal serie for PERCLOS.

Figure 4.

Evaluated indicators.

Figure 5.

Lateral position indicators. (a) Lateral position signal; (b) the standard deviation of the vehicle lateral position (STD_lp); (c) the mean squared error of the lateral position with respect to the center of the driving lane (MSE_lp); (d) optimized fraction of lane exits (Lanex_opti); and (e) time to line crossing of 5 s (TLC_5 s).

Figure 6.

Steering wheel indicators. (a) Steering wheel signal; (b) the steering-wheel angle (STD_sw) and (c) rapid steering-wheel movement (RSWM_opti).

Figure 7.

Heading error indicators. (a) Heading error signal; (b) the standard deviation of the heading error (STD_he) and (c) the mean squared error of the heading error (MSE_he).

Figure 8.

Optimization process.

Figure 9.

The designed feed forward neural network.