Unposed Object Recognition using an Active Approach

Wallace Lawson, J. Gregory Trafton

2013

Abstract

Object recognition is a practical problem with a wide variety of potential applications. Recognition becomes substantially more difficult when objects have not been presented in some logical, “posed” manner selected by a human observer. We propose to solve this problem using active object recognition, where the same object is viewed from multiple viewpoints when it is necessary to gain confidence in the classification decision. We demonstrate the effect of unposed objects on a state-of-the-art approach to object recognition, then show how an active approach can increase accuracy. The active approach works by attaching confidence to recognition, prompting further inspection when confidence is low. We demonstrate a performance increase on a wide variety of objects from the RGB-D database, showing a significant increase in recognition accuracy.

Paper Citation

in Harvard Style

Lawson W. and Trafton J. (2013). Unposed Object Recognition using an Active Approach . In Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013) ISBN 978-989-8565-47-1, pages 309-314. DOI: 10.5220/0004285503090314

in Bibtex Style

@conference{visapp13,
author={Wallace Lawson and J. Gregory Trafton},
title={Unposed Object Recognition using an Active Approach},
booktitle={Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)},
year={2013},
pages={309-314},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004285503090314},
isbn={978-989-8565-47-1},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2013)
TI - Unposed Object Recognition using an Active Approach
SN - 978-989-8565-47-1
AU - Lawson W.
AU - Trafton J.
PY - 2013
SP - 309
EP - 314
DO - 10.5220/0004285503090314