Qualitative vision for the guidance of legged robots in unstructured environments

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 d...

Descripción completa

Detalles Bibliográficos
Autores: Martínez Marroquín, Elisa, Torras, Carme
Tipo de recurso: artículo
Fecha de publicación:2001
País:España
Institución:Consejo Superior de Investigaciones Científicas (CSIC)
Repositorio:DIGITAL.CSIC. Repositorio Institucional del CSIC
OAI Identifier:oai:digital.csic.es:10261/30528
Acceso en línea:http://hdl.handle.net/10261/30528
Access Level:acceso abierto
Palabra clave:Image sequences
Egomotion recovery
3D-reconstruction
Uncalibrated camera
Unstructured environment
Contour tracking
Visual robot navigation
Descripción
Sumario: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.