A symmetry-based forward vehicle detection and collision warning system on Android smartphone

Abstract

This study proposes a symmetry-based forward vehicle detection and collision warning system (FCW) on smartphone. The proposed system identifies forward vehicle by shadow with vehicular symmetry. Through Bayes classifier tracking approach, it can reduce the error detection of image processing. Shadow detection with symmetry-based approach could improve the robustness of identifying forward vehicle. The detection system is migrated the FCW algorithm to Android, and employs mobile camera embedded Android smartphone to capture image of road environment. The FCW kernel processes captured images to obtain vehicle-marking of forward vehicle.