U.S. Department of Homeland Security (DHS) Science and Technology Directorate (S&T) officials have assessed the 2020 Privacy Technology Demonstration results.
The endeavor sought to advance efforts to protect the privacy of individuals appearing in photos and videos. Five privacy systems participated in the event as a means of demonstrating the ability to detect and blur faces in an S&T-created video.
“In recent years, we’ve observed tremendous improvement in face recognition technologies,” Arun Vemury, director of DHS S&T’s Biometric and Identity Technology Center, said. “The purpose of this research is to nurture the development of privacy enhancing technologies that can be used by organizations that have an interest in operating various types of camera systems, but recognize concerns related to face recognition surveillance.”
The findings are available via S&T’s Maryland Test Facility (MdTF) website that supports DHS to test technologies and evaluate operational processes.
The initiative stems from circumstances, such as large events or in an airport, during which video surveillance is a useful tool for public safety planning for crowd control or deploying the right number of responders.
In recognition of privacy concerns, S&T sought to understand how privacy enhancing technologies could be used to protect individual privacy in such instances.
According to S&T, the 2020 Demo Results Summary shows how each of the five technologies performed concerning barrel distortion, motion blur, pose variation, expression variation, occlusions, clipping, crowding, and masks.