Abstract:

Today, as the number of vehicles on the roads increases, the importance of traffic safety increases. Traffic accidents involving more than one vehicle threaten the lives of drivers and passengers. Heavy-duty vehicles such as trucks and buses, for which the use of tachographs is mandatory, cause more deaths, injuries and financial losses in traffic accidents. Conventional tachographs do not provide any information on the severity of lateral maneuvers such as turns and lane changes. The effects of aggressive driver behaviors on traffic accidents and fuel consumption can be significant. In this study, a new algorithm was designed and a new tachograph device was developed to detect and rate driver behavior using accelerometer and gyroscope data. For this purpose, a low-cost IMU (Inertial Measurement Unit) sensor module has been added to the tachograph device to detect lateral maneuvers. In order to detect right-left turn and lane change maneuvers with high precision, first the edges of the events are captured with the gyroscope-Z data and the start and end points are determined. Then, a new algorithm that scores lateral maneuvers is proposed by combining the accelerometer-X, gyroscope-Z and speed data in the range with a formula. In the tests performed, it was observed that the algorithm approached 100% accuracy in detecting turns and 88% accuracy in lane changes.

Keywords: