Image Time Series Classification based on a Planar Spatio-temporal Data Representation

Mohamed Chelali, Camille Kurtz, Anne Puissant, Nicole Vincent

2020

Abstract

Image time series such as MRI functional sequences or Satellite Image Time Series (SITS) provide valuable information for the automatic analysis of complex patterns through time. A major issue when analyzing such data is to consider at the same time their temporal and spatial dimensions. In this article we present a novel data representation that makes image times series compatible with classical deep learning model, such as Convolutional Neural Networks (CNN). The proposed approach is based on a novel planar representation of image time series that converts 2D + t data as 2D images without loosing too much spatial or temporal information. Doing so, CNN can learn at the same time the parameters of 2D filters involving temporal and spatial knowledge. Preliminary results in the remote sensing domain highlight the ability of our approach to discriminate complex agricultural land-cover classes from a SITS.

Paper Citation

in Harvard Style

Chelali M., Kurtz C., Puissant A. and Vincent N. (2020). Image Time Series Classification based on a Planar Spatio-temporal Data Representation. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 276-283. DOI: 10.5220/0008949202760283

in Bibtex Style

@conference{visapp20,
author={Mohamed Chelali and Camille Kurtz and Anne Puissant and Nicole Vincent},
title={Image Time Series Classification based on a Planar Spatio-temporal Data Representation},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={276-283},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0008949202760283},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Image Time Series Classification based on a Planar Spatio-temporal Data Representation
SN - 978-989-758-402-2
AU - Chelali M.
AU - Kurtz C.
AU - Puissant A.
AU - Vincent N.
PY - 2020
SP - 276
EP - 283
DO - 10.5220/0008949202760283
PB - SciTePress