PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Using Multi-view Recognition and Meta-data Annotation to Guide a Robot's Attention
Alexander Thomas, Vittorio Ferrari, Bastian Leibe, Tinne Tuytelaars and Luc Van Gool
The International Journal of Robotics Research Volume 28, Number 8, pp. 976-998, 2009. ISSN 0278-3649

Abstract

In the transition from industrial to service robotics, robots will have to deal with increasingly unpredictable and variable environments. We present a system that is able to recognize objects of a certain class in an image and to identify their parts for potential interactions. The method can recognize objects from arbitrary viewpoints and generalizes to instances that have never been observed during training, even if they are partially occluded and appear against cluttered backgrounds. Our approach builds on the Implicit Shape Model of Leibe et al. (2008). We extend it to couple recognition to the provision of meta-data useful for a task and to the case of multiple viewpoints by integrating it with the dense multi-view correspondence finder of Ferrari et al. (2006). Meta-data can be part labels but also depth estimates, information on material types, or any other pixelwise annotation. We present experimental results on wheelchairs, cars, and motorbikes.

PDF - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:5462
Deposited By:Alexander Thomas
Deposited On:24 September 2009