Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Standard

Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. / Oehmcke, Stefan; Thrysøe, Christoffer; Borgstad, Andreas ; Vaz Salles, Marcos Antonio; Brandt, Martin Stefan; Gieseke, Fabian Cristian.

Proceedings of the IEEE International Conference on Big Data, Big Data 2019: Special Session on Intelligent Data Mining. IEEE, 2019. s. 2403-2412 9006251,.

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

Harvard

Oehmcke, S, Thrysøe, C, Borgstad, A, Vaz Salles, MA, Brandt, MS & Gieseke, FC 2019, Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. i Proceedings of the IEEE International Conference on Big Data, Big Data 2019: Special Session on Intelligent Data Mining., 9006251, IEEE, s. 2403-2412, 2019 IEEE International Conference on Big Data, Los Angeles, USA, 09/12/2019.

APA

Oehmcke, S., Thrysøe, C., Borgstad, A., Vaz Salles, M. A., Brandt, M. S., & Gieseke, F. C. (2019). Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. I Proceedings of the IEEE International Conference on Big Data, Big Data 2019: Special Session on Intelligent Data Mining (s. 2403-2412). [9006251,] IEEE.

Vancouver

Oehmcke S, Thrysøe C, Borgstad A, Vaz Salles MA, Brandt MS, Gieseke FC. Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. I Proceedings of the IEEE International Conference on Big Data, Big Data 2019: Special Session on Intelligent Data Mining. IEEE. 2019. s. 2403-2412. 9006251,

Author

Oehmcke, Stefan ; Thrysøe, Christoffer ; Borgstad, Andreas ; Vaz Salles, Marcos Antonio ; Brandt, Martin Stefan ; Gieseke, Fabian Cristian. / Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data. Proceedings of the IEEE International Conference on Big Data, Big Data 2019: Special Session on Intelligent Data Mining. IEEE, 2019. s. 2403-2412

Bibtex

@inproceedings{8fe11d2642e443c9a06cbc37d7fa0d64,
title = "Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data",
abstract = "Massive amounts of satellite data have been gathered over time, holding the potential to unveil a spatiotemporal chronicle of the surface of Earth. These data allow scientists to investigate various important issues, such as land use changes, on a global scale. However, not all land-use phenomena are equally visible on satellite imagery. In particular, the creation of an inventory of the planet's road infrastructure remains a challenge, despite being crucial to analyze urbanization patterns and their impact. Towards this end, this work advances data-driven approaches for the automatic identification of roads based on open satellite data. Given the typical resolutions of these historical satellite data, we observe that there is inherent variation in the visibility of different road types. Based on this observation, we propose two deep learning frameworks that extend state-of-the-art deep learning methods by formalizing road detection as an ordinal classification task. In contrast to related schemes, one of the two models also resorts to satellite time series data that are potentially affected by missing data and cloud occlusion. Taking these time series data into account eliminates the need to manually curate datasets of high-quality image tiles, substantially simplifying the application of such models on a global scale. We evaluate our approaches on a dataset that is based on Sentinel~2 satellite imagery and OpenStreetMap vector data. Our results indicate that the proposed models can successfully identify large and medium-sized roads. We also discuss opportunities and challenges related to the detection of roads and other infrastructure on a global scale.",
author = "Stefan Oehmcke and Christoffer Thrys{\o}e and Andreas Borgstad and {Vaz Salles}, {Marcos Antonio} and Brandt, {Martin Stefan} and Gieseke, {Fabian Cristian}",
year = "2019",
language = "English",
pages = "2403--2412",
booktitle = "Proceedings of the IEEE International Conference on Big Data, Big Data 2019",
publisher = "IEEE",
note = "2019 IEEE International Conference on Big Data ; Conference date: 09-12-2019 Through 12-12-2019",

}

RIS

TY - GEN

T1 - Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data

AU - Oehmcke, Stefan

AU - Thrysøe, Christoffer

AU - Borgstad, Andreas

AU - Vaz Salles, Marcos Antonio

AU - Brandt, Martin Stefan

AU - Gieseke, Fabian Cristian

PY - 2019

Y1 - 2019

N2 - Massive amounts of satellite data have been gathered over time, holding the potential to unveil a spatiotemporal chronicle of the surface of Earth. These data allow scientists to investigate various important issues, such as land use changes, on a global scale. However, not all land-use phenomena are equally visible on satellite imagery. In particular, the creation of an inventory of the planet's road infrastructure remains a challenge, despite being crucial to analyze urbanization patterns and their impact. Towards this end, this work advances data-driven approaches for the automatic identification of roads based on open satellite data. Given the typical resolutions of these historical satellite data, we observe that there is inherent variation in the visibility of different road types. Based on this observation, we propose two deep learning frameworks that extend state-of-the-art deep learning methods by formalizing road detection as an ordinal classification task. In contrast to related schemes, one of the two models also resorts to satellite time series data that are potentially affected by missing data and cloud occlusion. Taking these time series data into account eliminates the need to manually curate datasets of high-quality image tiles, substantially simplifying the application of such models on a global scale. We evaluate our approaches on a dataset that is based on Sentinel~2 satellite imagery and OpenStreetMap vector data. Our results indicate that the proposed models can successfully identify large and medium-sized roads. We also discuss opportunities and challenges related to the detection of roads and other infrastructure on a global scale.

AB - Massive amounts of satellite data have been gathered over time, holding the potential to unveil a spatiotemporal chronicle of the surface of Earth. These data allow scientists to investigate various important issues, such as land use changes, on a global scale. However, not all land-use phenomena are equally visible on satellite imagery. In particular, the creation of an inventory of the planet's road infrastructure remains a challenge, despite being crucial to analyze urbanization patterns and their impact. Towards this end, this work advances data-driven approaches for the automatic identification of roads based on open satellite data. Given the typical resolutions of these historical satellite data, we observe that there is inherent variation in the visibility of different road types. Based on this observation, we propose two deep learning frameworks that extend state-of-the-art deep learning methods by formalizing road detection as an ordinal classification task. In contrast to related schemes, one of the two models also resorts to satellite time series data that are potentially affected by missing data and cloud occlusion. Taking these time series data into account eliminates the need to manually curate datasets of high-quality image tiles, substantially simplifying the application of such models on a global scale. We evaluate our approaches on a dataset that is based on Sentinel~2 satellite imagery and OpenStreetMap vector data. Our results indicate that the proposed models can successfully identify large and medium-sized roads. We also discuss opportunities and challenges related to the detection of roads and other infrastructure on a global scale.

M3 - Article in proceedings

SP - 2403

EP - 2412

BT - Proceedings of the IEEE International Conference on Big Data, Big Data 2019

PB - IEEE

T2 - 2019 IEEE International Conference on Big Data

Y2 - 9 December 2019 through 12 December 2019

ER -

ID: 231760061