Open Source
<-Return to all blogs
Lessons on tree-shaking Lodash with Webpack and Babel
Tree-shaking lodash can reduce the size of your JavaScript bundle, but it requires that a few conditions are met along the way to implementing it.
Introducing TileJSON.io, A Fast and Easy Way to View and Share Raster Tiles
TileJSON.io is an open source project by Azavea. It is an easy way to view and share raster tile sets using slippy map endpoints.
Mapping Africa: Crowdsourced Machine Learning
We leveraged our ability to process raster imagery, our open sources libraries, and our knack for machine learning to map agricultural fields in Africa.
Accuracy is in the Eye of the Beholder
Accuracy in deep learning models is not as cut and dry as many present it to be. We examine several examples where accuracy is more of a judgment call.
Reducing Road Crashes with DRIVER
Over 1.3 million people are killed on the world’s roads every year. More than 30 million suffer life-changing injuries. Based on current trauma levels an estimated 400 million people will be killed or injured between now and 2030. Source: IDB Road crashes are a leading cause of death globally, but these deaths occur mostly in […]
How We Select Projects
As a mission-based organization, how we select the projects we pursue is an ongoing conversation at Azavea. We share our thought process here.
Raster Vision: A New Open Source Framework for Deep Learning on Satellite and Aerial Imagery
Azavea is pleased to announce the release of Raster Vision, a new open source framework for deep learning on satellite and aerial imagery.
Three (Earth) Observations from Sat Summit 2018
Here are our key takeaways from SatSummit and some thoughts to help drive innovation related to earth observation data toward impactful solutions.
Tilegarden: Serverless Tile Rendering with AWS Lambda
This 2018 Azavea Open Source Fellowship project enables serverless Lambda-based raster and vector tile generation from PostGIS data.