The SpaceNet Multi-Temporal Urban Development Challenge

Adam Van Etten, Daniel Hogan
Proceedings of the NeurIPS 2020 Competition and Demonstration Track, PMLR 133:216-232, 2021.

Abstract

Building footprints provide a useful proxy for a great many humanitarian applications. For example, building footprints are useful for high fidelity population estimates, and quantifying population statistics is fundamental to  1/4 of the United Nations Sustainable Development Goals Indicators. In this paper we (the SpaceNet Partners) discuss efforts to develop techniques for precise building footprint localization, tracking, and change detection via the SpaceNet Multi-Temporal Urban Development Challenge (also known as SpaceNet 7). In this NeurIPS 2020 competition, participants were asked identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas. The competition centered around a brand new open source dataset of Planet Labs satellite imagery mosaics at 4m resolution, which includes 24 images (one per month) covering  100 unique geographies. Tracking individual buildings at this resolution is quite challenging, yet the winning participants demonstrated impressive performance with the newly developed SpaceNet Change and Object Tracking (SCOT) metric. This paper details the top-5 winning approaches, as well as analysis of results that yielded a handful of interesting anecdotes such as decreasing performance with latitude.

Cite this Paper


BibTeX
@InProceedings{pmlr-v133-etten21a, title = {The SpaceNet Multi-Temporal Urban Development Challenge}, author = {Etten, Adam Van and Hogan, Daniel}, booktitle = {Proceedings of the NeurIPS 2020 Competition and Demonstration Track}, pages = {216--232}, year = {2021}, editor = {Escalante, Hugo Jair and Hofmann, Katja}, volume = {133}, series = {Proceedings of Machine Learning Research}, month = {06--12 Dec}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v133/etten21a/etten21a.pdf}, url = {https://proceedings.mlr.press/v133/etten21a.html}, abstract = {Building footprints provide a useful proxy for a great many humanitarian applications. For example, building footprints are useful for high fidelity population estimates, and quantifying population statistics is fundamental to  1/4 of the United Nations Sustainable Development Goals Indicators. In this paper we (the SpaceNet Partners) discuss efforts to develop techniques for precise building footprint localization, tracking, and change detection via the SpaceNet Multi-Temporal Urban Development Challenge (also known as SpaceNet 7). In this NeurIPS 2020 competition, participants were asked identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas. The competition centered around a brand new open source dataset of Planet Labs satellite imagery mosaics at 4m resolution, which includes 24 images (one per month) covering  100 unique geographies. Tracking individual buildings at this resolution is quite challenging, yet the winning participants demonstrated impressive performance with the newly developed SpaceNet Change and Object Tracking (SCOT) metric. This paper details the top-5 winning approaches, as well as analysis of results that yielded a handful of interesting anecdotes such as decreasing performance with latitude.} }
Endnote
%0 Conference Paper %T The SpaceNet Multi-Temporal Urban Development Challenge %A Adam Van Etten %A Daniel Hogan %B Proceedings of the NeurIPS 2020 Competition and Demonstration Track %C Proceedings of Machine Learning Research %D 2021 %E Hugo Jair Escalante %E Katja Hofmann %F pmlr-v133-etten21a %I PMLR %P 216--232 %U https://proceedings.mlr.press/v133/etten21a.html %V 133 %X Building footprints provide a useful proxy for a great many humanitarian applications. For example, building footprints are useful for high fidelity population estimates, and quantifying population statistics is fundamental to  1/4 of the United Nations Sustainable Development Goals Indicators. In this paper we (the SpaceNet Partners) discuss efforts to develop techniques for precise building footprint localization, tracking, and change detection via the SpaceNet Multi-Temporal Urban Development Challenge (also known as SpaceNet 7). In this NeurIPS 2020 competition, participants were asked identify and track buildings in satellite imagery time series collected over rapidly urbanizing areas. The competition centered around a brand new open source dataset of Planet Labs satellite imagery mosaics at 4m resolution, which includes 24 images (one per month) covering  100 unique geographies. Tracking individual buildings at this resolution is quite challenging, yet the winning participants demonstrated impressive performance with the newly developed SpaceNet Change and Object Tracking (SCOT) metric. This paper details the top-5 winning approaches, as well as analysis of results that yielded a handful of interesting anecdotes such as decreasing performance with latitude.
APA
Etten, A.V. & Hogan, D.. (2021). The SpaceNet Multi-Temporal Urban Development Challenge. Proceedings of the NeurIPS 2020 Competition and Demonstration Track, in Proceedings of Machine Learning Research 133:216-232 Available from https://proceedings.mlr.press/v133/etten21a.html.

Related Material