Abstract
Abstract The problem of computer vision for the autonomous navigation of land vehicles is addressed. A combined sensor/processor subsystem has been developed for use in a cross-country vehicle which is to travel autonomously through unknown terrain. A high-resolution laser scanner is the visual sensor. The implemented real-time algorithm for obstacle detection and terrain analysis from range images is presented. Results obtained with the vision system are presented. It is concluded that reliable obstacle detection—without identification—is possible with moderate computing requirements.
Full Text 
Sign-in/Register to access full text options
Sign-in/Register to access full text options 
Published version (
Free)
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
