Sensing Driving Conditions To Estimate Vehicle Speed In Urban Environments

Acquiring instant vehicle speed is desirable and a corner stone to many importantvehicular applications such as vehicle localization, improving driving safety, drivingbehaviour analyzing and building intelligent transportation system.Due to the high deployment and maintenance cost, the traditional vehicle speedestimating methods could not keep pace with the demands of vehicular applications.In realizing that, this work utilizes smartphone sensors to estimate the vehicle speed,especially when GPS is unavailable or inaccurate in urban environments. In particular,weestimatethevehiclespeedbyintegratingtheaccelerometer’sreadingsovertimeandfnd the acceleration errors can lead to large deviations between the estimated speedand the real one. Further analysis shows that the changes of acceleration errors arevery small over time which can be corrected at some points, called reference points,where the true vehicle speed is known.Recognizing this observation, we propose an accurate vehicle speed estimationsystem, which senses natural driving conditions in urban environments including mak-ing turns, stopping and passing through uneven road surfaces, to derive referencepoints and further eliminates the speed estimation deviations caused by accelerationerrors.After that, we further improve our system with a sampling rate adaptive schemethatcouldcutdowntheenergycostofSenSpeedwhilekeepingthespeedestimationac-curacy uncompromised. Extensive experiments demonstrate that SenSpeed is accurateand robust in real driving environments.