Automated identification of astronauts on board the International Space Station: A case study in space archaeology

We develop and apply a deep learning-based computer vision pipeline to automatically identify crew members in archival photographic imagery taken on-board the International Space Station. Our approach is able to quickly tag thousands of images from public and private photo repositories without human supervision with high degrees of accuracy, including photographs where crew faces are partially obscured. Using the results of our pipeline, we carry out a large-scale network analysis of the crew, using the imagery data to provide novel insights into the social interactions among crew during their missions.

Automated summary

We have developed and applied a deep learning-based computer vision pipeline to identify crew members in archival photos taken on the International Space Station. Our approach can accurately tag a large number of images from public and private repositories, even when crew faces are partially obscured. Using the results of our pipeline, we conducted a network analysis of the crew, providing novel insights into their social interactions during missions.