A Multisensor System for Road Surface Identification

Abstract

[EN] This work introduces a multisensor road surface identification system that considers features from four different kind of sensors: microphones, accelerometers, speed signals, and handwheel signals. Features are extracted separately from each sensor, joined together, and then filtered using feature selection before classification. The proposed system was tested on a set of signals extracted from a specially-converted passenger car driving on a closed course. Three types of road surfaces were considered: smooth flat asphalt, cobblestones, and stripes. Three classifiers were considered: linear discriminant analysis, support vector machines, and random forests. All the considered classifiers reached over 90% accuracy, with a maximum accuracy of 96.52% for RDF. These results show the potential of the proposed system for road surface identification.