A vision-based driver assistance system using collaborative edge computing

Abstract

A conceptual model for a vision-based driver assistance system based on collaborative mobile and edge computing is proposed. Cloudlets are the edges of the SG cellular network and are capable of providing edge computing solutions to their connected devices. The proposed system monitors the vehicles that are driving in front of an ego car and notifies the driver upon detecting any hazardous condition caused by the other vehicles movements. A smartphone, mounted on the ego car, captures and sends the required information to a cloudlet for further processing. The cloudlet then notifies the smartphone upon detecting any hazardous conditions. This system can be used as a cost-effective driver assistance system and have the potential to reach the mass market and be used in all ranges of vehicles including the lower-end models.