An Automotive Robot Vision System
by Joe Durre and Brain Keith The development of autonomous vehicle guidance and control systems with the use of video recognition is only now being developed in labs across the nation. The purpose of this project is to use newly acquired video equipment to track roadway features. The newly acquired equipment consists of a MAC IIci, Nu Vista frame
grabbing hardware and software along with a Sony V99 Hi-8 video camera
and Sony Multisync monitors. Road data taken with the V99 camcorder is
stored in the computer via the Nu Vista frame grabber. The pict files (picture
data files) are then accessed through C language and MAC toolbox commands.
Line matching techniques are used to find y intercept and slope values
of linear features mapped to the image plane. Assuming the vehicle is on
a planar surface and camera height and tilt angle are known a 3-d to 2-d
algorithm converts change in vehicle pan angle and cross track to changes
in slope and y intercept. This information may be used to steer a vehicle.
|
[Prospective Students]
[Current Students]
[Alumni]
[Faculty]
[Home] [Contact us] [Curriculum] [Senior Projects] [Research] [People] [Links] Copyright (c)1995-2013 Bradley University. All rights reserved. . . |