No abstract

Presented herein is a study on the use of low-cost technology for the data collection and clasification on roadway pavement defects, by use of sensors from smartphones and from automobiles' on-board diagnostic (OBD-II) devices while vehicles are in movement. The smartphone-based data collection is complimented with artificial intelligence-based (AI) pattern recognition techniques for the classification of detected anomalies. The proposed system architecture and methodology utilize eleven metrics in the analysis, are checked against three types of roadway anomalies, and are validated against hundreds of roadway runs (relating to several thousands of data points) with an accuracy rate of over 90 percent.

Nowadays, pavement monitoring agencies typically assess pavement quality approximately only once per year. The main reason for this low frequency of inspections is the fact that current methods are expensive and laborious. The paper presents a data-driven framework and related field studies on the use of pattern recognition techniques and smartphone sensor technologies for the detection, classification and georeferencing of roadway pavement surface anomalies. The proposed system provides continuous and reliable information about the five most common roadway pavement surface anomalies which are valuable for pavement management systems and public safety.

No abstract

No abstract