Driving behavior assessment: A practical study and technique for detecting a driver's condition and driving style

Abstract

New research confirms that driving mistakes account for almost 75 % of all traffic accidents. Recently, many researchers have studied the recognition of driving behavior, including aggressive, fatigued or drowsy driving. The principal aim of this work is to present a combination approach for evaluating driver behavior, focuses on the analysis of numerous driving-related parameters and the detection of driver fatigue and drowsiness. Experimental research is carried out using a monitoring unit which can be mounted in any vehicle fitted with CAN (Control Area Network) technology, and which monitors current driving actions. This work combines the analysis of driving parameters such as engine speed, vehicle speed, accelerator pedal position, steering wheel angle, engine noise intensity, fuel consumption and, finally, the quantity of exhaust gases generated to define whether driving is normal or aggressive. Analysis of the driver's face enables us to detect fatigue and know whether the driver is asleep on the basis of facial features. This proposed detection method achieved an average accuracy of 99.10 %. The information gathered for each driving style is recorded, in order to build up our own data and analyze it carefully. In-depth study of these parameters reveals the boundaries that define driving status and style. Experimental and simulation results confirm that the proposed system can effectively detect driving states and driver reactions, with the aim of guaranteeing a sufficient and acceptable level of safety. This study can be used to improve policies and design more robust driver training and education programs.

Keywords

• Aggressive driving
• Automotive network
• Driving style classification
• Safety driving
• Yawn detection