Smartphone sensors can collect data in many different contexts. They make it feasible to obtain large amounts of data at little or no cost because most people own mobile phones. In this work, we focus on the collection of smartphone data in the car. Motion sensors, such as accelerometers and gyroscopes, can help obtain information about the vehicle’s dynamics. The possible spatial orientations of the smartphone in the car are infinite, and this can be a problem in an attempt to extract patterns from the data. Thus, we propose an approach to automatically re-orient smartphone data collected in the car to a standardized orientation (i.e. with 0 yaw, roll, and pitch angles with respect to the vehicle). We use a combination of a least-square plane approximation and an ML model to infer the relative orientation angles. Then we populate rotation matrices and perform the data rotation. We trained the model by collecting data both in an actual vehicle and using a vehicle physics simulator.
ML-based re-orientation of smartphone-collected car motion data / Bassetti, Enrico; Luciani, Alessio; Panizzi, Emanuele. - 198:(2022), pp. 237-242. (Intervento presentato al convegno International Workshop on Artificial Intelligence Methods for Smart Cities (AISC 2021) tenutosi a Leuven; Belgium).
ML-based re-orientation of smartphone-collected car motion data
Bassetti, Enrico
;Luciani, Alessio;Panizzi, Emanuele
2022
Abstract
Smartphone sensors can collect data in many different contexts. They make it feasible to obtain large amounts of data at little or no cost because most people own mobile phones. In this work, we focus on the collection of smartphone data in the car. Motion sensors, such as accelerometers and gyroscopes, can help obtain information about the vehicle’s dynamics. The possible spatial orientations of the smartphone in the car are infinite, and this can be a problem in an attempt to extract patterns from the data. Thus, we propose an approach to automatically re-orient smartphone data collected in the car to a standardized orientation (i.e. with 0 yaw, roll, and pitch angles with respect to the vehicle). We use a combination of a least-square plane approximation and an ML model to infer the relative orientation angles. Then we populate rotation matrices and perform the data rotation. We trained the model by collecting data both in an actual vehicle and using a vehicle physics simulator.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.