Fast Self-supervised On-line Training for Object Recognition Specifically for Robotic Applications

Markus Schoeler, Simon Christoph Stein, Jeremie Papon, Alexey Abramov, Florentin Woergoetter

2014

Abstract

Today most recognition pipelines are trained at an off-line stage, providing systems with pre-segmented images and predefined objects, or at an on-line stage, which requires a human supervisor to tediously control the learning. Self-Supervised on-line training of recognition pipelines without human intervention is a highly desirable goal, as it allows systems to learn unknown, environment specific objects on-the-fly. We propose a fast and automatic system, which can extract and learn unknown objects with minimal human intervention by employing a two-level pipeline combining the advantages of RGB-D sensors for object extraction and high-resolution cameras for object recognition. Furthermore, we significantly improve recognition results with local features by implementing a novel keypoint orientation scheme, which leads to highly invariant but discriminative object signatures. Using only one image per object for training, our system is able to achieve a recognition rate of 79% for 18 objects, benchmarked on 42 scenes with random poses, scales and occlusion, while only taking 7 seconds for the training. Additionally, we evaluate our orientation scheme on the state-of-the-art 56-object SDU-dataset boosting accuracy for one training view per object by +37% to 78% and peaking at a performance of 98% for 11 training views.

Paper Citation

in Harvard Style

Schoeler M., Stein S., Papon J., Abramov A. and Woergoetter F. (2014). Fast Self-supervised On-line Training for Object Recognition Specifically for Robotic Applications . In Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014) ISBN 978-989-758-004-8, pages 94-103. DOI: 10.5220/0004688000940103

in Bibtex Style

@conference{visapp14,
author={Markus Schoeler and Simon Christoph Stein and Jeremie Papon and Alexey Abramov and Florentin Woergoetter},
title={Fast Self-supervised On-line Training for Object Recognition Specifically for Robotic Applications},
booktitle={Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)},
year={2014},
pages={94-103},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004688000940103},
isbn={978-989-758-004-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 9th International Conference on Computer Vision Theory and Applications - Volume 2: VISAPP, (VISIGRAPP 2014)
TI - Fast Self-supervised On-line Training for Object Recognition Specifically for Robotic Applications
SN - 978-989-758-004-8
AU - Schoeler M.
AU - Stein S.
AU - Papon J.
AU - Abramov A.
AU - Woergoetter F.
PY - 2014
SP - 94
EP - 103
DO - 10.5220/0004688000940103