Intelligent Vehicle Experimental Test-beds


Human-Centered Driver Assistance Systems

Vision Systems for Occupant Posture Analysis


Vision Systems for Driver Analysis and Interface


Related Research


Lane Detection Research

Lane detection is a well-researched area of computer vision with applications in autonomous vehicles and driver support systems. This is in part because, despite the perceived simplicity of finding white markings on a dark road, it can be very difficult to determine lane markings on various types of road. These difficulties arrive from shadows, occlusion by other vehicles, changes in the road surfaces itself, and differing types of lane markings. A lane detection system must be able to pick out all manner of markings from cluttered roadways and filter them to produce a reliable estimate of the vehicle position and trajectory relative to the lane.

By integrating the lane marking detector with the lane tracking system, we have developed a robust lane detection system that works well in a variety of different conditions.  The detection is performed using steerable filters which are suitable for detecting bots dots, solid lines, and dashed lines.  For solid and dashed lines, the filters can be tuned to respond to a specific lane angle, thereby removing extraneous road features.

Here are some results of the filtering process

A typical highway scene in California.

Results of filtering for Bots Dots.

Results from filter for a line tuned to the lane angle

And filtering in difficult situations

Image and Results from filter for a line tuned to the lane angle with tree shadows and non-uniform road materials

Here are some results of the combined detector and tracker.

Results with clutter from nearby cars and tree shadows.

Results during a lane change.

Results with lighting changes from going through an overpass.

Results with shadowing from trucks and only Bots Dots lane markings.

Lane Position Output from the lane Tracking System

Steering angle output from the lane tracking system

Videos of these results can be viewed in the Videos portion of this web site

More details on these research topics can be viewed in the Publications portion of this web site.