As the world continues to enhance and strengthen its emergency services, mobile phones may be used to aid in safe driving practices and detection of emergencies. To our knowledge, no work has been reported in understanding vehicle motion using accelerometers/compass in cell phones. In this paper, we used the multiple sensors in a Google phone to classify safe versus unsafe driving. In particular, we used breaking distance, acceleration, and deceleration for detecting safe verses unsafe braking. Next, we calculated the displacement in the axis perpendicular to the trajectory of vehicle and used it to classify safe and unsafe lane changes. The direction of the phone with respect to the motion of the vehicle is important during calibration of the above measurements, so we used 2D and 3D rotation matrices for transforming device orientation. Future work includes calibration of braking distance, lane changes, and reliable transformation of phone orientation with respect to trajectory of the vehicle.
[1]
P. Caselli,et al.
Classification of Motor Activities through Derivative Dynamic Time Warping applied on Accelerometer Data
,
2007,
2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.
[2]
Ling Bao,et al.
Activity Recognition from User-Annotated Acceleration Data
,
2004,
Pervasive.
[3]
B. G. Celler,et al.
Classification of basic daily movements using a triaxial accelerometer
,
2004,
Medical and Biological Engineering and Computing.
[4]
Stephen Foster,et al.
Are you with me
,
2007
.
[5]
Reto Meier.
Professional Android Application Development
,
2008
.
[6]
Blake Hannaford,et al.
"Are You with Me?" - Using Accelerometers to Determine If Two Devices Are Carried by the Same Person
,
2004,
Pervasive.