xView: Objects in Context in Overhead Imagery

TL;DR

The paper introduces xView, a large-scale, high-resolution satellite imagery dataset with over 1 million objects across 60 classes, designed to advance overhead object detection research.

Contribution

It presents a new geospatial annotation process and a comprehensive dataset that surpasses existing datasets in size and diversity for overhead imagery object detection.

Findings

xView is one of the largest overhead object detection datasets available.

The dataset includes high-resolution imagery from WorldView-3 satellites.

Baseline analysis with SSD demonstrates its utility for research.

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.