RoadMic: Road surface monitoring using vehicular sensor networks with microphones

Abstract

Road surface analysis including pothole reports is an important problem for road maintainers and drivers. In this paper we propose a methodology for pothole detection using mobile vehicles equipped with off the shelf microphone and global positioning devices attached to an on-board computer. The approach is generic enough to be extended for other kind of event detection using different sensors as well. The vehicles are driving on public streets and measuring pothole induced sound signals. Our approach was tested and evaluated by real world experiments in a road segment for which we had established the ground truth beforehand. The results show pothole detection with high accuracy despite the background noise and other audio events. © 2010 Springer-Verlag Berlin Heidelberg.