Deep Learning and the Analysis of Satellite Imagery

Boris Babenko of Orbital Insight talks about Deep Learning and the Analysis of Satellite Imagery.

Orbital Insight is a Geospatial Big Data company leveraging the rapidly growing availability of satellite, UAV, and other geospatial data sources, to understand and characterize socio-economic trends at global, regional, and hyper-local scales. In this talk Boris discusses the satellite imagery domain, how it’s evolving, and the various advantages and challenges of working with such imagery. He also covers several examples of computer vision modules Orbital Insight has built using deep learning, and some lessons learned.

Finally, Boris talks about practical considerations of rapidly prototyping and productizing computer vision / deep learning models.

Boris Babenko received a PhD in computer science at UC San Diego, where he studied weakly supervised learning and its applications to object detection, recognition and tracking. After graduate school Boris dabbled in entrepreneurship, co-founding Anchovi Labs to offer computer vision and crowdsourcing as a service. The startup was acquired by Dropbox, where Boris spent the subsequent two and a half years working on the photos team and building the company’s first computer vision enabled product feature. Boris is now a Computer Vision Engineer at Orbital Insight where he works on deep learning and other computer vision technologies to help understand the Earth at scale.