SpaceNet: A Remote Sensing Dataset and Challenge Series
By Adam Van Etten, David Lindenbaum, Todd M. Bacastow. 2018
490 citations recorded by the source corpus.
Foundational mapping remains a challenge in many parts of the world, particularly in dynamic scenarios such as natural disasters when timely updates are critical. Updating maps is currently a highly manual process requiring a large number of human labelers to either create features or rigorously validate automated outputs. We propose that the frequent revisits of earth imaging satellite constellations may accelerate existing efforts to quickly update foundational maps when combined with advanced machine learning techniques. Accordingly, the SpaceNet partners (CosmiQ Works, Radiant Solutions, and NVIDIA), released a large corpus of labeled satellite imagery on Amazon Web Services (AWS) called SpaceNet. The SpaceNet partners also launched a series of public prize competitions to encourage improvement of remote sensing machine learning algorithms. The first two of these competitions focused on automated building footprint extraction, and the most recent challenge focused on road network extraction. In this paper we discuss the SpaceNet imagery, labels, evaluation metrics, prize challenge results to date, and future plans for the SpaceNet challenge series.
Subfields: Epidemiology, Media Technology, Ocean Engineering, Evaluation & Benchmarks, Remote Sensing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Epidemiology
In Media Technology
- Brandon Lucia
- Clifford Broni-Bediako
- Jan Dirk Wegner
- Yasutaka Furukawa
- Junshi Xia
- Fuyang Zhang
- Stefano Ermon
- Bruno Adriano
In Ocean Engineering
- Brandon Lucia
- Clifford Broni-Bediako
- Jan Dirk Wegner
- Yasutaka Furukawa
- Junshi Xia
- Zuoyue Li
- Fuyang Zhang
- Stefano Ermon
In Evaluation & Benchmarks
- Brandon Lucia
- Yasutaka Furukawa
- Fuyang Zhang
- Stefano Ermon
- Nelson Nauata
- Aurélien Lucchi
- Bradley Denby
In Remote Sensing
Citations in the corpus
- SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery (2022, methodology): “Building Segmentation In this section, we evaluate SatMAE on the semantic segmentation down-stream task of the SpaceNet v1 dataset [20].”
- Orbital Edge Computing: Nanosatellite Constellations as a New Class of Computer System (2020, methodology): “The SpaceNet challenge [94] illustrates broad interest in visual computing on space data, and the proposed Amazon ground station network [2] further cements the value of computing on visual and other space sensor data.”
- Topological Map Extraction From Overhead Images (2018, background): “Another large-scale dataset that includes both, building footprints and road networks is SpaceNet [49].”
- OpenEarthMap: A Benchmark Dataset for Global High-Resolution Land Cover Mapping (2022, methodology): “SpaceNet [51] and IEEE GRSS DFC [20], among others, regularly introduce benchmark datasets to the public through competitions that drive research and development.”
- Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction (2019, methodology): “ represented as a 2D planar graph. This section describes our data source and pre-processing steps (See Fig.2). Dataset: Our data source is a set of high-resolution satellite RGB images from SpaceNet [12] corpus, hosted through the Amazon Web Services (AWS) as a part of the SpaceNet Input Corner enu”