Qualitative vision for the guidance of legged robots in unstructured environments

Elisa Martínez, Carme Torras

Producció científica: Article en revista indexadaArticleAvaluat per experts

17 Cites (Scopus)

Resum

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.

Idioma originalAnglès
Pàgines (de-a)1585-1599
Nombre de pàgines15
RevistaPattern Recognition
Volum34
Número8
DOIs
Estat de la publicacióPublicada - d’ag. 2001
Publicat externament

Fingerprint

Navegar pels temes de recerca de 'Qualitative vision for the guidance of legged robots in unstructured environments'. Junts formen un fingerprint únic.

Com citar-ho