Car type and road detection

Car type and road detection

A system capable of warning the driver when the vehicle starts to depart the roadway, or controlling the lateral position of the vehicle to keep it in its lane, could potentially eliminate many of these crashes. Nearly 70% of these crashes occur in rural or suburban settings on undivided two lane roads. Since it is unlikely these roads will be upgraded in the foreseeable future, a system for preventing these crashes must rely on the existing road structure.

Our research into such systems has focused on machine vision techniques that detect particular features in video images of the road ahead of the vehicle, and determine the desired vehicle trajectory based on the relative positions of these features. Using a strong, a priori model of the road's appearance, we employed strong detection algorithms to locate these characteristic features. Most challenges in this area result from the fact that the environmental context can greatly impact road appearance. Changes in illumination due to shadows, glare or darkness, and obstructions by other vehicles, rain, snow, salt or other foreign objects often cause dramatic changes in the road's appearance.