[2002.02624] Visual search over billions of aerial and satellite imagescontact arXivarXiv Twitter

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.

10 mentions: @RyanKeisler@pkmital@secou@mymarkup@secou@XiXiDu@Native_Mode
Date: 2020/02/20 00:51

Referring Tweets

@RyanKeisler Last weekend I dusted off the old arxiv-submission skills to publish "Visual search over billions of aerial and satellite images", t.co/VCRSwEBAJQ . This is basically a deeper dive into the @DescartesLabs GeoVisual Search demo at t.co/Y8vxkq0vGg . t.co/GatZaI2ZBk
@mymarkup ”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.” t.co/whJZAAH57D Testa här: t.co/6uhZL0su2x #preprintwatch
@pkmital Visual search over billions of aerial and satellite images paper: t.co/3khawx6Vrp demo: t.co/ZCmz8U5bi8 cc: @kcimc @golan

Related Entries

Read more [2001.09773] Algorithmic Fairness from a Non-ideal Perspectivecontact arXivarXiv Twitter
0 users, 2 mentions 2020/01/28 20:20
Read more Complete Statistical Theory of Learning (Vladimir Vapnik) | MIT Deep Learning Series - YouTube
0 users, 6 mentions 2020/02/18 14:21
Read more [2007.00808] Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalopen...
0 users, 2 mentions 2020/07/06 08:21
Read more [2007.04131] Pitfalls to Avoid when Interpreting Machine Learning Modelsopen searchopen navigation m...
0 users, 7 mentions 2020/07/09 08:21
Read more PyTorch Recipes — PyTorch Tutorials 1.5.1 documentation
0 users, 2 mentions 2020/07/09 17:21