Self-Learning 3D Object Classification

Jens Garstka, Gabriele Peters

2018

Abstract

We present a self-learning approach to object classification from 3D point clouds. Existing 3D feature descriptors have been utilized successfully for 3D point cloud classification. But there is not a single best descriptor for any situation. We extend a well-tried 3D object classification pipeline based on local 3D feature descriptors by a reinforcement learning approach that learns strategies to select point cloud descriptors depending on qualities of the point cloud to be classified. The reinforcement learning framework learns autonomously a strategy to select feature descriptors from a provided set of descriptors and to apply them successively for an optimal classification result. Extensive experiments on more than 200.000 3D point clouds yielded higher classification rates with partly more reliable results than a single descriptor setting. Furthermore, our approach proved to be able to preserve classification strategies that have been learned so far while integrating additional descriptors in an ongoing classification process.

Paper Citation

in Harvard Style

Garstka J. and Peters G. (2018). Self-Learning 3D Object Classification.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 511-519. DOI: 10.5220/0006649905110519

in Bibtex Style

@conference{icpram18,
author={Jens Garstka and Gabriele Peters},
title={Self-Learning 3D Object Classification},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={511-519},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006649905110519},
isbn={978-989-758-276-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Self-Learning 3D Object Classification
SN - 978-989-758-276-9
AU - Garstka J.
AU - Peters G.
PY - 2018
SP - 511
EP - 519
DO - 10.5220/0006649905110519