A Crowdsourcing Solution for Road Surface Roughness Detection Using Smartphones

Xiao Li, Ruizhi Chen, Tianxing Chu

Abstract:	The concept of “citizen as sensors” has recently attracted the attention of scientists and researchers in geospatial science because of the rapid development and widespread use of mobile devices such as smartphones. This paper presents a novel crowdsourcing solution for road surface roughness detection using commercial-off-the-shelf (COTS) smartphones. The proposed solution is based on the measurements of the built-in GPS and the accelerometer sensors. The goal is to identify the general roughness of the road surface and detect the transient events (e.g. bumps and potholes on the road surface) from the accelerometer data. Specifically, the proposed solution 1) retrieves GPS and accelerometer data from the smartphone, and 2) estimates the root mean square (RMS) values of the acceleration data perpendicular to the screen plane and 3) detect the number of transient events and evaluate the overall quality of the road surface roughness. A 50 km driving test containing 3 road segments with different surface roughness levels has been carried out. The testing results demonstrated that the road quality could be effectively identified, and the number of transient events could be properly detected and located.
Published in:	Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014) September 8 - 12, 2014 Tampa Convention Center Tampa, Florida
Pages:	498 - 502
Cite this article:	Li, Xiao, Chen, Ruizhi, Chu, Tianxing, "A Crowdsourcing Solution for Road Surface Roughness Detection Using Smartphones," Proceedings of the 27th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2014), Tampa, Florida, September 2014, pp. 498-502.
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In