Wayward drivers could soon be getting a nudge in the right direction thanks to a computer program created by researchers from North Carolina State University. The program allows a computer to understand what a camera is looking at and makes decisions based on what it sees. If a car strays from its lane the program will detect the lane change and set the car back on course without human control.
The program uses algorithms to sort visual data and make decisions related to finding the lanes on a road, detecting how those lanes change as a car is moving, and controlling the car to stay in the correct lane. The researchers admit that there are already some vision systems out there that can do lane finding, but say the program is able to maintain an awareness of multiple lanes and traffic in those lanes as well.
“We develop computer vision programs, which allow a computer to understand what a video camera is looking at – whether it is a stop sign or a pedestrian. For example, this particular program is designed to allow a computer to keep a car within a lane on a highway, because we plan to use the program to drive a car,” says Dr. Wesley Snyder, a professor of electrical and computer engineering at NC State and co-author of a paper describing the research.
While not quite yet at the level of the fully autonomous vehicles being pursued by the likes of Audi and OshKosh, the team says its computer vision research has many potential uses, such as the development of military applications related to surveillance, reconnaissance and transportation of materials.
It could also enable the development of new automobile safety features, including systems that can allow cars to stay in their lane, avoid traffic and 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.
A paper describing the research entitled, “Concurrent visual multiple lane detection for autonomous vehicles,” will be presented at the IEEE International Conference on Robotics and Automation in Anchorage, Alaska in May.