Scientists at the North Carolina State University have developed a computer vision programme that would enable vehicles to take control and drive safely during heavy traffic or in emergency situations.
"We have developed computer vision programme, which allow a computer to understand what a video camera is looking at – whether it is a stop sign or a pedestrian," said co-author Dr Wesley Snyder.
"This research has many potential uses. It can lead to the development of new automobile safety features like taking control during heavy traffic, keeping cars in their lanes and driving safely if the driver has fallen asleep at the wheel or had a heart attack or gone into diabetic shock," Snyder said.
This can also help in development of military applications related to surveillance, reconnaissance and transportation of materials, the university said.
"At present, the programme we have created is designed to allow a computer to keep a car within a lane on a highway, because we plan to use the programme to drive a car" Snyder said.
"Although there are some vision systems out there already that can do lane finding, our programme maintains an awareness of multiple lanes and traffic in those lanes," he added.
This programme, which uses algorithms to sort visual data and make decisions related to finding the lanes of a road, detect how those lanes change as a car is moving and control the car to stay in the correct lane.
A paper describing the research will be presented in Anchorage at the IEEE International Conference on Robotics and Automation next month.