Dives into performance specifics and the APLS metric score for each of the winning participants in the SpaceNet 5 challenge.
Part 2 of a blog series discussing how lessons from computer vision applications in geo will impact bio image analysis.
Announcing the SpaceNet 6 Challenge, which pushes into a newfrontier and an under-explored modality of data: Synthetic Aperture Radar.
Explores how lessons from computer vision applications in geo will impact bio image analysis.
Outlines the approaches of the SpaceNet 5 challenge winners, and discusses one key feature of SpaceNet 5: geographic diversity.
Explores RarePlanes, the new dataset for object detection and instance segmentation of aircraft and their attributes in satellite imagery.
Discusses results from the SpaceNet 5 Challenge, which sought to identify road networks and optimal travel times directly from satellite imagery.
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.
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.
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.
When it comes to the relationship between geospatial neural network performance and the amount of training data, do geographic differences matter?
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?