Charalambos Kyriakou and Symeon E. Christodoulou

Detecting Pavement Patches Utilizing Smartphones Technology and Vehicles

Abstract: Presented herein is a study on the utilization of low-cost technology for detection of roadway pavement anomalies (patches and potholes), by use of sensors on smartphones and of automobilesÕ on-board diagnostic (OBD-II) devices for the collection and analysis of vibration-related data while vehicles are in movement. The mobile data collection kit consists of a triaxial accelerometer, a gyroscope and a global positioning sensor. The smartphone-based data collection is complimented with robust regression analysis and a bagged-trees classification model for the classification of pavement anomalies. The proposed system is readily available, low-cost and adequately accurate, and can be utilized in crowd-sourced applications for pavement monitoring. Further, the proposed methodology has been field-tested, exhibiting detection accuracy levels higher than 90% for pavement patches, and it is currently expanded to include larger datasets and a bigger number of pavement defect types.

Keywords: Pavement Anomalies, Detection and Classification, Smartphones Technology, Robust Regression, Bagged Trees

DOI: https://doi.org/10.24928/JC3-2017/0109

Full text: content.pdf (1,528,885 bytes) (available to registered users only)

Series: jc3:2017 (browse)
Cluster:
Class:
Similar papers:
Sound: N/A.

• Users who put this record into basket also placed into basket these records.
• Users who displayed this record also displayed these records.