Road Detection from Satellite Images by Improving U-Net with Difference of Features

Ryosuke Kamiya, Kazuhiro Hotta, Kazuo Oda, Satomi Kakuta

Abstract

In this paper, we propose a road detection method from satellite images by improving the U-Net using the difference of feature maps. U-Net has connections between convolutional layers and deconvolutional layers and concatenates feature maps at convolutional layer with those at deconvolutional layer. Here we introduce the difference of feature maps instead of the concatenation of feature maps. We evaluate our proposed method on road detection problem. Our proposed method obtained significant improvements in comparison with the U-Net.

References

Download


Paper Citation


in Harvard Style

Kamiya R., Hotta K., Oda K. and Kakuta S. (2018). Road Detection from Satellite Images by Improving U-Net with Difference of Features.In Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-276-9, pages 603-607. DOI: 10.5220/0006717506030607


in Bibtex Style

@conference{icpram18,
author={Ryosuke Kamiya and Kazuhiro Hotta and Kazuo Oda and Satomi Kakuta},
title={Road Detection from Satellite Images by Improving U-Net with Difference of Features},
booktitle={Proceedings of the 7th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2018},
pages={603-607},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006717506030607},
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 - Road Detection from Satellite Images by Improving U-Net with Difference of Features
SN - 978-989-758-276-9
AU - Kamiya R.
AU - Hotta K.
AU - Oda K.
AU - Kakuta S.
PY - 2018
SP - 603
EP - 607
DO - 10.5220/0006717506030607