A Crowdsourcing-based Road Anomaly Classification System

Abstract

Road networks are the most important facility to the public transportation in modern cities. Governments around the world allocate large amounts of budgets for the pavement maintenance every year. In this paper, we proposed a crowd-sourcing solution to categorize road anomalies into safety related anomalies such as speed bumps and rumble strips, and dangerous anomalies such as bumps and potholes. The proposed system is composed of three parts: a smart probe car crowds (SPC-crowd) that serve as the anomaly data source; cloud servers that are the core for the anomaly classification; and application services that provide various innovative applications to facilitate the pavement maintenance. To support the crowdsourcing procedure, in the SPC-crowd side, we proposed cross-SPC techniques by adopting the underdamped oscillation model (UOM). In the cloud side, a supervised learning classification model was adopted on the anomaly data generated from the SPC-crowd. To validate the proposed system, extensive field trial was performed. The experimental results shown that our system can facilitate the pavement maintenance through the crowdsourcing solution.