Stefan Habenschuss studied and lectured computer science and computational neuroscience at the University of Technology in Graz. He worked on artificial neural networks and their relation to biological neural networks as research scientist, publishing papers in high-ranking journals in computational neuroscience and machine learning. He continued his career as a software engineer at the video game company Bongfish, working on the MMOG "World of Tanks", and Microsoft's Flight Simulator 2020. He is now heading the Machine Learning team at Blackshark.ai, with the mission to recreate our planet in digital 3D, visually and semantically. His research interests include object and attribute detection, fusion of 2D and 3D geospatial data, and advancing the state-of-the-art in human-in-the-loop machine learning.
blackshark.ai provides powerful insights into the world by extracting information from satellite imagery fully automatically. A scalable artificial intelligence builds the core of the blackshark platform, detecting features with incredible precision and speed. A novel machine learning approach was developed to train a neural network for new features rapidly, enabling blackshark to serve various use cases in many different industries.
Input sources supported:
- satellite imagery
- 2D photographs (aerial, street level, ...)
- point clouds (photogrammetry or lidar)
- HD map data
- OSM
- & more
Examples for feature detection:
- buildings (footprint, height, type, roof, orientation, facade)
- vegetation
- streets
- land classification
- flood detection
- & more