Slide 1

Produção, visualização e análise de grandes volumes de imagens de sensoriamento remoto modeladas como cubos de dados multidimensionais para todo o território brasileiro.

Slide 1

O Data Cube Explorer é um portal web para visualização de cubos de dados, coleções de imagens e classificações.

previous arrow
next arrow

Stmetrics: A Python Package for Satellite Image Time-Series Feature Extraction

by Anderson R. Soares¹; Hugo N. Bendini¹; Daiane V. Vaz¹; Tatiana D. T. Uehara¹; Alana K. Neves¹; Sarah Lechler²; Thales S. Körting¹; Leila M. G. Fonseca¹

¹General Coordination of Earth Observation – OBT, Brazil’s National Institute for Space Research (INPE), São José dos Campos, SP, Brazil

²Institute for Geoinformatics, University of Muenster


Publisher: IEEE Explorer | Published: 2 Oct. 2020

Published in: IGARSS 2020 – 2020 IEEE International Geoscience and Remote Sensing Symposium


Producing reliable land use and land cover maps to support the deployment and operation of public policies is a necessity, especially when environmental management and economic development are considered. To increase the accuracy of these maps, satellite image time-series have been used, as they allow the understanding of land cover dynamics through the time. This paper presents the stmetrics, a python package that provides the extraction of state-of-the-art time-series features. These features can be used for remote sensing time-series image classification and analysis. stmetrics aims to be an easy-to-use package. The package is available under the GNU GPL software license, and the full source code is available for download at:

Keywords: time-series, python, multi-temporal features, remote sensing

Share and Cite

Soares, A. R.; Bendini, H. N.; Vaz, D. V.; Uehara, T. D. T.; Neves, A. K.; Lechler, Sarah; Korting, T. S.; Fonseca, L. M. G. STMETRICS: A Python Package for Satellite Image Time-Series Feature Extraction. In: IGARSS 2020: 2020 IEEE International Geoscience and Remote Sensing Symposium. Virtual Symposium. September 26 – October 2, 2020 2020.

Brazil Data Cube - 2019 - 2024