Researchers from North Carolina State University have developed a system that allows a car to stay in its lane without human control.
The team has written a program that uses algorithms to sort visual data and make decisions related to finding the lanes of a road. It can detect how those lanes change as a car is moving, and control the car to make sure it stays in the correct lane.
The system isn’t affected by shadows, road color or by whether road markings are continuous or dashed. And although other vision systems exist that can handle lane finding, this one can cope with multiple lanes and traffic in those lanes, says Dr Wesley Snyder, a professor of electrical and computer engineering at NC State.
“This computer vision technology will also enable the development of new automobile safety features, including systems that can allow cars to stay in their lane, avoid traffic and gracefully react to emergency situations – such as those where a driver has fallen asleep at the wheel, had a heart attack or gone into diabetic shock,” he says.
He said other uses for the technology include the development of military applications related to surveillance, reconnaissance and transportation of materials.