Blackshark's Orca Workflow Manager - FF
by Blackshark.ai GmbH
Blackshark's Multi Class Detection Containerized Pipeline
Blackshark.ai’s Orca - geospatial analytics service - detects objects and extracts insights about planet-wide infrastructure from satellite imagery. This pre-trained and ready to use containerized artificial intelligence service can easily be integrated in analytics pipelines, providing fast and precise insights using vectorized building footprints, detected buildings heights, roof types and roof colors.
The containerized, convolutional neural networks contained in the Orca AI services provide very fast, global-scale, accurate insights based on satellite or aerial imagery data sets. As desired, input data sets are conveniently provided via Azure as well - or you can provide your own data if you prefer. Simply register to your Azure account, choose the right kind of geospatial imagery, select what kind of insights you want extracted and start the process. Bing! - you will be notified when the results are ready to consume.
The current machine learning algorithms are optimized for orthographic satellite imagery with a resolution between 40 and 60cm and the containers are export either georeferenced pixel masks or regularized vectors of building footprints, building height, or vegetation coverage.
Whenever fresh input data is available the Orca service can be started again and will extract fast and precise insights. These fast, georeferenced object and change detection capabilities enable applications such as efficient 3D mapping services, city planning, smart city apps, logistic planning, risk analysis, telecom signal propagation planning or disaster relief planning.
