CRATER: A Crowd Sensing Application to Estimate Road Conditions

This is the authors' abstract. We don't add key points for this paper.

We developed a crowd sensing application to estimate road conditions (CRATER). CRATER is a smartphone application that opportunistically measures acceleration when it finds itself on the road in order to map and measure the locations of potholes and speedbumps. It does not require input from users, but can report detected potholes and speedbumps to a cloud-hosted application engine, which stores partially processed data received from smartphones of participating users and jointly processes it to obtain a better estimate of road conditions. The information is published in map form on the web. This map allows both citizens and municipal authorities to localize potholes, road segments in need of repair, and imbalances in infrastructure maintenance efforts across cities. Road tests demonstrate that CRATER succeeds in correctly detecting roughly 90% of potholes and 95% of speedbumps, while generating false alarms only about 10% and 5% of the time, respectively.