Land Cover Clustering based on Improved Dictionary Learning Method from Modis Data

Mariem Zaouali, Sonia Bouzidi, Ezzeddine Zagrouba

2016

Abstract

An approach based on k-means clustering algorithm combined with the concept of sparse representation is proposed in this paper. We intend to discriminate, each vegetation type, by its temporal behavior. Our method is composed of two main parts : The first part consists of designing the dictionary that we are going to use. For this reason, we propose a modification of the k-svd algorithm by switching the use of OMP algorithm by the SunSAL algorithm. Then we carry on an unsupervised clustering process using k-means algorithm on sparse vectors. As a result, we found that SunSAL algorithm outperforms the OMP algorithm and we succeed to elaborate discriminative temporal behaviors of the vegetation in our region of study. As perspectives, our approach could be considered as an attempt to overcome the shortage of high spatial resolution data since we are relying only on coarse remote sensing images like MODIS to monitor Land Cover dynamics.

Paper Citation

in Harvard Style

Zaouali M., Bouzidi S. and Zagrouba E. (2016). Land Cover Clustering based on Improved Dictionary Learning Method from Modis Data . In Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: RGB-SpectralImaging, (VISIGRAPP 2016) ISBN 978-989-758-175-5, pages 697-704. DOI: 10.5220/0005851006970704

in Bibtex Style

@conference{rgb-spectralimaging16,
author={Mariem Zaouali and Sonia Bouzidi and Ezzeddine Zagrouba},
title={Land Cover Clustering based on Improved Dictionary Learning Method from Modis Data},
booktitle={Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: RGB-SpectralImaging, (VISIGRAPP 2016)},
year={2016},
pages={697-704},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005851006970704},
isbn={978-989-758-175-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 11th Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: RGB-SpectralImaging, (VISIGRAPP 2016)
TI - Land Cover Clustering based on Improved Dictionary Learning Method from Modis Data
SN - 978-989-758-175-5
AU - Zaouali M.
AU - Bouzidi S.
AU - Zagrouba E.
PY - 2016
SP - 697
EP - 704
DO - 10.5220/0005851006970704