Publication
Qualitative vision for the guidance of legged robots in unstructured environments
Journal Article (2001)
Journal
Pattern Recognition
Pages
1585-1599
Volume
34
Number
8
Doc link
http://dx.doi.org/10.1016/S0031-3203(00)00093-5
File
Abstract
Visual procedures especially tailored to the constraints and requirements of a legged robot are presented. They work for an uncalibrated camera, with pan and zoom, freely moving towards a stationary target in an unstructured environment that may contain independently moving objects. The goal is to dynamically analyse the image sequence in order to extract information about the robot motion, the target position and the environment structure. The development is based on the deformations of an active contour fitted to the target. Experimental results confirm that the proposed approach constitutes a promising alternative to the prevailing trend based on the costly computation of displacement or velocity fields.
Categories
robots.
Author keywords
image sequences, egomotion recovery, 3d reconstruction, uncalibrated camera, unstructured environment, contour tracking, visual robot navigation
Scientific reference
E. Martinez and C. Torras. Qualitative vision for the guidance of legged robots in unstructured environments. Pattern Recognition, 34(8): 1585-1599, 2001.
Follow us!