Real-time Non-intrusive Monitoring Research Articles

Real-time non-intrusive monitoring and prediction of driver distraction

This paper presents a non-intrusive algorithm for monitoring and predicting driver vigilance in real time. The proposed technique is applied to a truck driving simulator by monitoring the driver response through steering wheel and accelerator pedal. The simulation results of the truck simulator are validated with a commercial TruckSim® software using identical parameters of a given tractor semitrailer during similar driving conditions. Several distraction indicators are proposed in order to predict the driver distraction, namely the jerk profile, spikiness index and the rate of change for both the steering wheel angle and the accelerator pedal position. The results of several driving experiments emphasise the effectiveness of using steering wheel rate to estimate driver distraction. Moreover, in comparison to other techniques for predicting driver vigilance, the presented work requires low computational power and has a great potential for developing a real-time simple system that can be affordable and reliable.

Real-time non-intrusive monitoring and prediction of driver distraction

Real-time non-intrusive monitoring and prediction of driver distraction

Real-Time Nonintrusive Monitoring and Prediction of Driver Fatigue

This paper describes a real-time online prototype driver-fatigue monitor. It uses remotely located charge-coupled-device cameras equipped with active infrared illuminators to acquire video images of the driver. Various visual cues that typically characterize the level of alertness of a person are extracted in real time and systematically combined to infer the fatigue level of the driver. The visual cues employed characterize eyelid movement, gaze movement, head movement, and facial expression. A probabilistic model is developed to model human fatigue and to predict fatigue based on the visual cues obtained. The simultaneous use of multiple visual cues and their systematic combination yields a much more robust and accurate fatigue characterization than using a single visual cue. This system was validated under real-life fatigue conditions with human subjects of different ethnic backgrounds, genders, and ages; with/without glasses; and under different illumination conditions. It was found to be reasonably robust, reliable, and accurate in fatigue characterization.