Processing Attribute Profiles as Scale-series for Remote Sensing Image Classification

Melike Ilteralp, Erchan Aptoula

2021

Abstract

Attribute profiles (APs) are among the most prominent “shallow” spatial-spectral pixel description methods, providing multi-scale, flexible and efficient pixel descriptions, even with modest amounts of training data. In this paper, we investigate their collaboration with long short-term memory networks (LSTMs). Our hypothesis is that a profile can be viewed as a “scale-series” and LSTMs can exploit their sequential nature, akin to temporal series. Plus, feeding a deep network with input of already strong descriptive potential (such as APs) can help them produce advanced features more efficiently w.r.t. training from scratch. Moreover, contrary to the state-of-the-art, we report the results of experiments conducted with non-overlapping training and testing sets, highlighting a significant boost of performance through the combined use of APs with LSTMs.

Paper Citation

in Harvard Style

Ilteralp M. and Aptoula E. (2021). Processing Attribute Profiles as Scale-series for Remote Sensing Image Classification. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 558-565. DOI: 10.5220/0010350005580565

in Bibtex Style

@conference{visapp21,
author={Melike Ilteralp and Erchan Aptoula},
title={Processing Attribute Profiles as Scale-series for Remote Sensing Image Classification},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP},
year={2021},
pages={558-565},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010350005580565},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 4: VISAPP
TI - Processing Attribute Profiles as Scale-series for Remote Sensing Image Classification
SN - 978-989-758-488-6
AU - Ilteralp M.
AU - Aptoula E.
PY - 2021
SP - 558
EP - 565
DO - 10.5220/0010350005580565
PB - SciTePress