Approaching Rutted Road-Segment Alert using Smartphone

Abstract

Driving on unfamiliar poorly paved roads is risky even if the vehicle speed is kept under limits. A driver may lose control if his vehicle suddenly comes into road anomalies, especially at night. In developing countries, road anomalies are not only common, but also new ones usually exist without precautions. We present an alerting system that detects and localizes road ruts in order to release a prior-rut notification to the driver using no additional devices but his smartphone. Our system uses crowd-sourcing techniques to collect labeled data from smartphones built-in sensors that describe road ruts. We use this data to feed a machine learning engine to build models that can detect new ruts. Our system localizes identified ruts on the map via GPS coordinates and alerts drivers when they approach a rutted road. Our experiments show that the accuracy of the system can be raised from 59% up to 99% if the learning technique is carefully selected and the sensors data set size is increased to 100000 samples.