A neuro-dynamic architecture for one shot learning of objects that uses both bottom-up recognition and top-down prediction

Learning to recognize objects from a small number of example views is a difficult problem of robot vision, of particular importance to assistance robots who are taught by human users. Here we present an approach that combines bottom-up recognition of matching patterns and top-down estimation of pose...

Full description

Saved in:
Bibliographic Details
Main Authors: Faubel, C., Schoner, G.
Format: Conference Proceeding
Language:English
Subjects:
Computer vision
Human robot interaction
Intelligent robots
Layout
Object recognition
Pattern matching
Pattern recognition
Robot vision systems
Signal processing
USA Councils
Citations: Items that cite this one
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Learning to recognize objects from a small number of example views is a difficult problem of robot vision, of particular importance to assistance robots who are taught by human users. Here we present an approach that combines bottom-up recognition of matching patterns and top-down estimation of pose parameters in a recurrent loop that improves on previous efforts to reconcile invariance of recognition under view changes with discrimination among different objects. We demonstrate and evaluate the approach both in a service robotics implementation as well as on the COIL database. The robotic implementation highlights features of our approach that enable real-time pose tracking as well as recognition from views where figure ground segmentation is difficult.
ISSN:2153-0858
2153-0866
DOI:10.1109/IROS.2009.5354380