SpaceNet: A Remote Sensing Dataset and Challenge Series
arXiv:1807.01232
Abstract
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.
10 pages, 5 figures, 2 tables, 5 appendices
References in corpus (4)
Cited by in corpus (48)
- LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
- Enabling Country-Scale Land Cover Mapping with Meter-Resolution Satellite Imagery
- SpaceNet MVOI: a Multi-View Overhead Imagery Dataset
- RNGDet: Road Network Graph Detection by Transformer in Aerial Images
- DAugNet: Unsupervised, Multi-source, Multi-target, and Life-long Domain Adaptation for Semantic Segmentation of Satellite Images
- DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image Classification
- City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times
- Panoptic Segmentation Meets Remote Sensing
- There Are No Data Like More Data- Datasets for Deep Learning in Earth Observation
- Road Extraction with Satellite Images and Partial Road Maps
- Measuring Human and Economic Activity from Satellite Imagery to Support City-Scale Decision-Making during COVID-19 Pandemic
- Collaborative Dynamic 3D Scene Graphs for Automated Driving
- 3D Instance Segmentation of MVS Buildings
- Image-Conditioned Graph Generation for Road Network Extraction
- A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentation
- Road Network Reconstruction from Satellite Images with Machine Learning Supported by Topological Methods
- FOOL: Addressing the Downlink Bottleneck in Satellite Computing with Neural Feature Compression
- Panoptic Perception: A Novel Task and Fine-grained Dataset for Universal Remote Sensing Image Interpretation
- SpaceNet 6: Multi-Sensor All Weather Mapping Dataset
- Road Network and Travel Time Extraction from Multiple Look Angles with SpaceNet Data
- Improving Community Resiliency and Emergency Response With Artificial Intelligence
- RarePlanes: Synthetic Data Takes Flight
- The SpaceNet Multi-Temporal Urban Development Challenge
- City-scale Road Extraction from Satellite Imagery
- Remote Sensor Design for Visual Recognition with Convolutional Neural Networks
- Sat2Graph: Road Graph Extraction through Graph-Tensor Encoding
- SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
- Randomized Histogram Matching: A Simple Augmentation for Unsupervised Domain Adaptation in Overhead Imagery
- Updating Street Maps using Changes Detected in Satellite Imagery
- Topo-boundary: A Benchmark Dataset on Topological Road-boundary Detection Using Aerial Images for Autonomous Driving
- Topological Map Extraction from Overhead Images
- Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction
- Vectorizing World Buildings: Planar Graph Reconstruction by Primitive Detection and Relationship Inference
- Channel Tiling for Improved Performance and Accuracy of Optical Neural Network Accelerators
- Revisiting Classical Bagging with Modern Transfer Learning for On-the-fly Disaster Damage Detector
- Overhead MNIST: A Benchmark Satellite Dataset
- Robust Deep Learning with Active Noise Cancellation for Spatial Computing
- Resource-Constrained Simultaneous Detection and Labeling of Objects in High-Resolution Satellite Images
- Object-Based Augmentation Improves Quality of Remote Sensing Semantic Segmentation
- MultiNet: Segmenting Flooded Buildings via Fusion of Multiresolution, Multisensor, and Multitemporal Satellite Imagery
- Map Generation from Large Scale Incomplete and Inaccurate Data Labels
- Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate
- Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning
- PAIRS AutoGeo: an Automated Machine Learning Framework for Massive Geospatial Data
- Compressed learning based onboard semantic compression for remote sensing platforms
- Learning to Detect Fortified Areas
- Towards Reliable Evaluation of Road Network Reconstructions
- Towards Sustainable Census Independent Population Estimation in Mozambique