A Deep Convolutional Neural Network for Location Recognition and Geometry based Information

Francesco Bidoia, Matthia Sabatelli, Amirhossein Shantia, Marco A. Wiering, Lambert Schomaker

2018

Abstract

In this paper we propose a new approach to Deep Neural Networks (DNNs) based on the particular needs of navigation tasks. To investigate these needs we created a labeled image dataset of a test environment and we compare classical computer vision approaches with the state of the art in image classification. Based on these results we have developed a new DNN architecture that outperforms previous architectures in recognizing locations, relying on the geometrical features of the images. In particular we show the negative effects of scale, rotation, and position invariance properties of the current state of the art DNNs on the task. We finally show the results of our proposed architecture that preserves the geometrical properties. Our experiments show that our method outperforms the state of the art image classification networks in recognizing locations.

Paper Citation

in Harvard Style

Bidoia F., Sabatelli M., Shantia A., Wiering M. and Schomaker L. (2018). A Deep Convolutional Neural Network for Location Recognition and Geometry based Information.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 27-36. DOI: 10.5220/0006542200270036

in Bibtex Style

@conference{icpram18,
author={Francesco Bidoia and Matthia Sabatelli and Amirhossein Shantia and Marco A. Wiering and Lambert Schomaker},
title={A Deep Convolutional Neural Network for Location Recognition and Geometry based Information},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={27-36},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006542200270036},
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 - A Deep Convolutional Neural Network for Location Recognition and Geometry based Information
SN - 978-989-758-276-9
AU - Bidoia F.
AU - Sabatelli M.
AU - Shantia A.
AU - Wiering M.
AU - Schomaker L.
PY - 2018
SP - 27
EP - 36
DO - 10.5220/0006542200270036