• Skip to primary navigation
  • Skip to main content
  • Careers
  • Submit A Business Plan
  • Contact Us

In-Q-Tel

Strategic investor that accelerates the development and delivery of cutting-edge technologies to U.S. government agencies

  • IQT_logo_color_FINAL-web
  • Insights & Access
  • How We Work
  • Portfolio
  • News & Resources
  • Our History
  • IQT Labs
You are here: Home / Archives for IQT Labs / Commercial Space

Commercial Space

The SpaceNet 5 Baseline — Part 3: Extracting Road Speed Vectors from Satellite Imagery

Oct 17, 2019 By christynz

We’re closing in on the final stretch for the SpaceNet 5 Challenge that aims to extract road networks and route travel times directly from satellite imagery. Yet there’s still plenty of time to get involved, as our previous blog showed reasonable road mask predictions after only 10 hours of training.

Filed Under: Blogs (SPACE), Commercial Space

Robustness of Limited Training Data: Part 5

Oct 16, 2019 By christynz

Deep learning models for interpreting satellite imagery show increasing performance as the amount of training data is increased. In this post, we’ll recreate our first analysis with a whole new model architecture, to see what changes and what stays the same.

Filed Under: Blogs (SPACE), Commercial Space

The SpaceNet 5 Baseline — Part 1: Imagery and Label Preparation

Oct 3, 2019 By christynz

In support of SpaceNet 5’s rather complex challenge, this post walks readers through the steps necessary to prepare the data for the first step in our baseline: creating training masks for a deep learning segmentation model.

Filed Under: Blogs (SPACE), Commercial Space

Robustness of Limited Training Data: Part 4

Sep 25, 2019 By christynz

When it comes to the relationship between geospatial neural network performance and the amount of training data, do geographic differences matter?

Filed Under: Blogs (SPACE), Commercial Space

Robustness of Limited Training Data: Part 3

Sep 17, 2019 By christynz

When training a deep neural network to identify building footprints in satellite imagery, having more training data never hurts. But how much does more data help, and when is it worth the cost and difficulty of procuring it?

Filed Under: Blogs (SPACE), Commercial Space

Accelerating your geospatial deep learning pipeline with fine-tuning

Sep 11, 2019 By christynz

Using Solaris, you can fine-tune deep learning models pre-trained on overhead imagery for five minutes and achieve performance comparable to past SpaceNet Challenge prize-winners.

Filed Under: Blogs (SPACE), Commercial Space

  • Go to page 1
  • Go to page 2
  • Go to page 3
  • Interim pages omitted …
  • Go to page 9
  • Go to Next Page »
  • Home
  • Insights & Access
  • How We Work
  • Portfolio
  • News & Resources
  • Our History
  • IQT Labs

Copyright © 2019 · In-Q-Tel, Inc. - All Rights Reserved | Terms of Use | Privacy Policy | Sitemap

We use cookies to analyze the usage of our websites and give you a better experience. You consent to our cookies if you click on “Agree” and continue to use our website. Read our Privacy Policy for more information and to know how to amend your settings.AgreePrivacy Policy