In this blog, we discuss various improvements that we have made to the proposed workflow first discussed in our previous blog post focused on edge processing of drone imagery for search-and-rescue.
In this blog post, we explore the application of a foundation model pre-trained on Sentinel-2 imagery, to the downstream task of change detection.
Element 84 has developed near real-time edge processing of drone and aerial imagery for human identification that leverages machine learning and AWS Snowcone edge capabilities during austere operations for search and rescue applications.
We outline recent projects tackling complex challenges through the lens of Machine Learning and discuss how our past experience will shape future work.
Responsible for the data labeling for a machine learning project? Here are some insights we’ve developed while managing data labeling for machine learning.
Today, the availability of satellite imagery still far outpaces our capacity to analyze it, but machine learning and tools like Raster Vision are helping.
In a previous post we showed how the E84 R&D team used RoboSat by Mapbox to prepare training data, train a machine learning model, and run predictions on new satellite imagery. In this example, we’re going to use the same imagery source and label data as a proxy for data produced by our AWS disaster […]