Road Anomaly Detection and Classification Using Smartphones and Artificial Neural Networks
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.
-
Supplemental Notes:
- This paper was sponsored by TRB committee AFD20 Standing Committee on Pavement Monitoring and Evaluation.
-
Corporate Authors:
500 Fifth Street, NW
Washington, DC United States 20001 -
Authors:
- Kyriakou, Charalambos
- Christodoulou, Symeon E
- Dimitriou, Loukas
-
Conference:
- Transportation Research Board 95th Annual Meeting
- Location: Washington DC, United States
- Date: 2016-1-10 to 2016-1-14
- Date: 2016
Language
- English
Media Info
- Media Type: Digital/other
- Features: Figures; Photos; References; Tables;
- Pagination: 11p
- Monograph Title: TRB 95th Annual Meeting Compendium of Papers
Subject/Index Terms
- TRT Terms: Accuracy; Detection and identification; Neural networks; Pavement distress; Potholes; Smartphones
- Uncontrolled Terms: Anomaly detection
- Subject Areas: Data and Information Technology; Highways; Pavements; I23: Properties of Road Surfaces;
Filing Info
- Accession Number: 01590361
- Record Type: Publication
- Report/Paper Numbers: 16-3384
- Files: TRIS, TRB, ATRI
- Created Date: Feb 16 2016 4:01PM