Anomalies on road pavement cause discomfort to drivers and passengers, and may cause mechanical failure or even accidents. Governments spend millions of Euros every year on road maintenance, often causing traffic jams and congestion on urban roads on a daily basis. This paper analyses the difference between the deployment of a road anomalies detection and identification system in a “conditioned” and a real world setup, where the system performed worse compared to the “conditioned” setup. It also presents a system performance analysis based on the analysis of the training data sets; on the analysis of the attributes complexity, through the application of PCA techniques; and on the analysis of the attributes in the context of each anomaly type, using acceleration standard deviation attributes to observe how different anomalies classes are distributed in the Cartesian coordinates system. Overall, in this paper, we describe the main insights on road anomalies detection challenges to support the design and deployment of a new iteration of our system towards the deployment of a road anomaly detection service to provide information about roads condition to drivers and government entities.

Road pavement conditions influence the daily lives of both drivers and passengers. Anomalies in road pavement can cause discomfort, increase stress, cause mechanical failures in vehicles and compromise safety of road users. Detecting and surveying road condition/anomalies requires expensive and specially designed equipment and vehicles, that cost considerable amounts of money, and require specialized workers to operate them. As an alternative, an emergent sensing paradigm is being discussed as a promising mechanism for collecting large-scale real-world data. In this paper we describe our experience on the design, implementation and deployment of a cloud based road anomaly information management service, that combines Collaborative Mobile Sensing and data-mining approaches, to provide a practical solution for detecting, identifying and managing road anomaly information. Additionally, we identify technical challenges and propose guidelines that may help to improve this type of services and applications.