Daniel Hogan – Medium

Published in The DownLinQ

·Feb 8, 2021

A Closer Look at the SpaceNet Change and Object Tracking (SCOT) Metric

Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence applied research for geospatial applications, specifically foundational mapping (i.e., building footprint & road network detection). …

Geospatial

7 min read

A Closer Look at the SpaceNet Change and Object Tracking (SCOT) Metric

Geospatial

7 min read

Published in The DownLinQ

·Sep 25, 2020

Deploying the SpaceNet 7 Baseline on AWS

Adapted by Daniel Hogan from a post by Adam Van Etten and Nick Weir Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence applied research for geospatial applications, specifically foundational mapping (i.e., building footprint & road network detection). …

Computer Vision

6 min read

Deploying the SpaceNet 7 Baseline on AWS

Computer Vision

6 min read

Published in The DownLinQ

·Aug 13, 2020

The SpaceNet Change and Object Tracking (SCOT) Metric

Daniel Hogan and Adam Van Etten Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence applied research for geospatial applications, specifically foundational mapping (i.e. building footprint and road network detection). SpaceNet is solely managed by co-founder, In-Q-Tel CosmiQ Works, in collaboration with co-founder and co-chair…

Open Source

8 min read

The SpaceNet Change and Object Tracking (SCOT) Metric

Open Source

8 min read

Published in The DownLinQ

·Jul 16, 2020

Introducing the Solaris Multimodal Preprocessing Library

Within the latest release of Solaris, available now, is a new resource for geospatial deep learning: the Solaris Multimodal Preprocessing Library. This library eases the work of imagery preprocessing, i.e., undertaking data cleaning and image analysis to get the data to a final form for deep learning. …

Open Source

3 min read

Introducing the Solaris Multimodal Preprocessing Library

Open Source

3 min read

Published in The DownLinQ

·Mar 5, 2020

The SpaceNet 6 Baseline

Deep Learning

5 min read

Deep Learning

5 min read

Published in The DownLinQ

·Feb 13, 2020

SAR 201: An Introduction to Synthetic Aperture Radar, Part 2

By Daniel Hogan (In-Q-Tel CosmiQ Works) and Jason Brown (Capella Space) with the CosmiQ Works and Capella teams. Preface: SpaceNet LLC is a nonprofit organization dedicated to accelerating open source, artificial intelligence applied research for geospatial applications, specifically foundational mapping (i.e. building footprint & road network detection). SpaceNet is run…

Remote Sensing

8 min read

SAR 201: An Introduction to Synthetic Aperture Radar, Part 2

Remote Sensing

8 min read

Published in The DownLinQ

·Feb 5, 2020

SAR 101: An Introduction to Synthetic Aperture Radar

Remote Sensing

9 min read

SAR 101: An Introduction to Synthetic Aperture Radar

Remote Sensing

9 min read

Published in The DownLinQ

·Oct 16, 2019

Robustness of Limited Training Data: Part 5

Deep learning models for interpreting satellite imagery show increasing performance as the amount of training data is increased. We’ve looked at the details of how this plays out, but our previous studies of this topic have suffered from a weakness: they’ve all used just one model architecture, meaning the layout…

Machine Learning

5 min read

Robustness of Limited Training Data: Part 5

Machine Learning

5 min read

Published in The DownLinQ

·Sep 25, 2019

Robustness of Limited Training Data: Part 4

When it comes to the relationship between geospatial neural network performance and the amount of training data, do geographic differences matter? In a previous post, we examined this question by training the same building footprint model using various amounts of data from four different cities: Las Vegas, Paris, Shanghai, and…

Machine Learning

7 min read

Robustness of Limited Training Data: Part 4

Machine Learning

7 min read

Published in The DownLinQ

·Sep 17, 2019

Robustness of Limited Training Data: Part 3

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? We’ve seen that performance rises rapidly with training data quantity when data…

Machine Learning

8 min read

Robustness of Limited Training Data: Part 3

Machine Learning

8 min read