xView: Objects in Context in Overhead Imagery

Abstract

We introduce a new large-scale dataset for the advancement of object detection techniques and overhead object detection research. This satellite imagery dataset enables research progress pertaining to four key computer vision frontiers. We utilize a novel process for geospatial category detection and bounding box annotation with three stages of quality control. Our data is collected from WorldView-3 satellites at 0.3m ground sample distance, providing higher resolution imagery than most public satellite imagery datasets. We compare xView to other object detection datasets in both natural and overhead imagery domains and then provide a baseline analysis using the Single Shot MultiBox Detector. xView is one of the largest and most diverse publicly available object-detection datasets to date, with over 1 million objects across 60 classes in over 1,400 km^2 of imagery.

Initial submission

References in corpus (5)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks
• Matching Networks for One Shot Learning
• Rich feature hierarchies for accurate object detection and semantic segmentation
• Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale
• Zoom Out-and-In Network with Map Attention Decision for Region Proposal and Object Detection

Cited by in corpus (32)

• Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges
• Object Detection in 20 Years: A Survey
• SpaceNet: A Remote Sensing Dataset and Challenge Series
• iSAID: A Large-scale Dataset for Instance Segmentation in Aerial Images
• Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
• SpaceNet MVOI: a Multi-View Overhead Imagery Dataset
• Semi-Supervised Semantic Segmentation in Earth Observation: The MiniFrance Suite, Dataset Analysis and Multi-task Network Study
• Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion
• Benchmark Dataset for Automatic Damaged Building Detection from Post-Hurricane Remotely Sensed Imagery
• Reduced Focal Loss: 1st Place Solution to xView object detection in Satellite Imagery
• Efficient Poverty Mapping using Deep Reinforcement Learning
• A Comparison of Super-Resolution and Nearest Neighbors Interpolation Applied to Object Detection on Satellite Data
• Multi-Cue Vehicle Detection for Semantic Video Compression In Georegistered Aerial Videos
• FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery
• RarePlanes: Synthetic Data Takes Flight
• Accelerating Deep Learning Applications in Space
• Remote Sensor Design for Visual Recognition with Convolutional Neural Networks
• SustainBench: Benchmarks for Monitoring the Sustainable Development Goals with Machine Learning
• On Creating Benchmark Dataset for Aerial Image Interpretation: Reviews, Guidances and Million-AID
• Measuring economic activity from space: a case study using flying airplanes and COVID-19
• Overhead MNIST: A Benchmark Satellite Dataset
• Discoverability in Satellite Imagery: A Good Sentence is Worth a Thousand Pictures
• Land Cover Mapping in Limited Labels Scenario: A Survey
• Disaster mapping from satellites: damage detection with crowdsourced point labels
• Transfer Learning for Aided Target Recognition: Comparing Deep Learning to other Machine Learning Approaches
• Seeing poverty from space, how much can it be tuned?
• cofga: A Dataset for Fine Grained Classification of Objects from Aerial Imagery
• Deep Learning for Recognizing Mobile Targets in Satellite Imagery
• Joint-SRVDNet: Joint Super Resolution and Vehicle Detection Network
• Buildings Classification using Very High Resolution Satellite Imagery
• SIMPL: Generating Synthetic Overhead Imagery to Address Zero-shot and Few-Shot Detection Problems
• Deep Built-Structure Counting in Satellite Imagery Using Attention Based Re-Weighting