Using 3D Contours and their Relations for Cognitive Vision and Robotics

Başeski, E., Bodenhagen, L., Pugeault, N. , Kalkan, S., Piater, J. and Krüger, N. (2009) Using 3D Contours and their Relations for Cognitive Vision and Robotics. In: 2009 24th International Symposium on Computer and Information Sciences, Guzelyurt, Cyprus, 14-16 Sep 2009, pp. 409-414. ISBN 9781424450213 (doi: 10.1109/ISCIS.2009.5291815)

Abstract

In this work, we make use of 3D visual contours carrying geometric as well as appearance information. Between these contours, we define 3D relations that encode structural information relevant to object-level operations such as similarity assessment and grasping. We show that this relational space can also be used as input features for learning which we exemplify for the grasping of unknown objects. Our representation is motivated by the human visual system in two respects. First, we make use of a visual descriptor that is motivated by hyper-columns in V1. Secondly, the contours can be seen as one stage in a visual hierarchy bridging between local symbolic descriptors to higher level stages of processing such as object coding and grasping.

• Item Type: Conference Proceedings
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Pugeault, Dr Nicolas
• Authors: Başeski, E., Bodenhagen, L., Pugeault, N., Kalkan, S., Piater, J., and Krüger, N.
• College/School: College of Science and Engineering > School of Computing Science
• ISBN: 9781424450213
• Published Online: 23 October 2009