01590361

Component

The study presented herein explores the use of data, collected by sensors from smartphones and from automobiles’ on-board diagnostic (OBD-II) devices while vehicles are in movement, for the detection of roadway anomalies. The smartphone-based data collection is complimented with artificial neural network techniques for classifying detected roadway anomalies. Thirty-one factors are used for the detection (subsequently reduced to eleven, without loss of accuracy). The proposed method and system architecture are checked against three types of roadway anomalies, and validated against hundreds of roadway runs (relating to several thousands of data points) with above 90% accuracy rate. The study’s results confirm the value of smartphone sensors in the low-cost (and eventually crow-sourced) detection of roadway anomalies.

This paper was sponsored by TRB committee AFD20 Standing Committee on Pavement Monitoring and Evaluation.

01584066

16-3384

English

11p

2016

Transportation Research Board 95th Annual Meeting

Digital/other

Figures; Photos; References; Tables

Accuracy; Detection and identification; Neural networks; Pavement distress; Potholes; Smartphones

Anomaly detection

Data and Information Technology; Highways; Pavements; I23: Properties of Road Surfaces

Transportation Research Board Annual Meeting 2016 Paper #16-3384

TRIS, TRB, ATRI

Jan 12 2016 5:29PM