We present a system for performing visual search over billions of aerial and satellite images. The purpose of visual search is to find images that are visually similar to a query image. We define visual similarity using 512 abstract visual features generated by a convolutional neural network that has been trained on aerial and satellite imagery. The features are converted to binary values to reduce data and compute requirements. We employ a hash-based search using Bigtable, a scalable database service from Google Cloud. Searching the continental United States at 1-meter pixel resolution, corresponding to approximately 2 billion images, takes approximately 0.1 seconds. This system enables real-time visual search over the surface of the earth, and an interactive demo is available at https://search.descarteslabs.com.
@article{arxiv.2002.02624,
title = {Visual search over billions of aerial and satellite images},
author = {Ryan Keisler and Samuel W. Skillman and Sunny Gonnabathula and Justin Poehnelt and Xander Rudelis and Michael S. Warren},
journal= {arXiv preprint arXiv:2002.02624},
year = {2020}
}