Azavea and CloudFactory: Partners on Quality Training Data and Social Impact
By Joe Morrison on October 8th, 2019
Read about our journey to hiring an outsourced data labeling firm and how we've found a partner in Cloud Factory.
STAC: Creating an Ecosystem of SpatioTemporal Assets
By Niki LaGrone, James Santucci and Aaron Su on October 1st, 2019
STAC is creating an ecosystem of interoperable spatiotemporal assets. Learn how Azavea has contibuted and about future steps for the specification.
Housing & Landlords: Using Open Data to Find Substandard Conditions
By Fay Walker on September 26th, 2019
Using R and QGIS to analyze substandard housing in Philadelphia with open data. We used open data to identify violations, evictions, and illegal rentals.
Is This a Crosswalk?: 5 Takeaways from Training a Data Labeling Team
By Niki LaGrone on September 13th, 2019
We trained remote computer vision workers to provide data labeling for machine learning projects. Here's what we learned.
Putting Native American Voters on the Map: Using Cadastral Data to Geocode Non-Traditional Addresses
By Fay Walker on September 12th, 2019
We used cadastral land survey data to geocode previously unmappable Native American voters in Montana.
Transfer Learning from RGB to Multi-band Imagery
By Adeel Hassan on August 30th, 2019
We used transfer learning to teach a model to take advantage of multi-band imagery without discarding the original RGB pre-training. This resulted in significant performance improvement.