Title :
Time-to-collision from first-order models of the motion field
Author :
Meyer, François G.
Author_Institution :
IRISA, Rennes, France
fDate :
12/1/1994 12:00:00 AM
Abstract :
Time-to-collision provides vital information for obstacle avoidance and for the visual navigation of a robot. The original contribution of this paper is to demonstrate with sequences of real images that time-to-collision can be robustly and accurately recovered with a single calibrated camera, using first order models of the motion field
Keywords :
computerised navigation; image sequences; mobile robots; path planning; robot vision; vehicles; motion field first-order models; obstacle avoidance; real image sequences; time-to-collision; visual navigation; Aircraft navigation; Biomedical optical imaging; Cameras; Image motion analysis; Machine vision; Optical noise; Optical sensors; Robot vision systems; Robustness; Vehicles;
Journal_Title :
Robotics and Automation, IEEE Transactions on
