Microsoft has added a new feature in Azure Media Analytics – a suite of tools for handling media at scale – that automatically blurs the faces of individuals.
Azure Media Redactor offers scalable facial redaction in the cloud, obscuring selected individuals’ faces while leaving others on show – ideal for video being used in public safety and news media scenarios where members of the public must remain anonymous.
The service – which is available as a free public preview for a limited time – works by detecting faces in every frame of video and tracking the facial object both forwards and backwards in time, so that the same individual can be blurred at all times.
“The use of body worn cameras in policing and public spaces is becoming increasing commonplace, which places a larger burden on these departments when videos are requested for disclosure through Freedom of Information or Public Records acts,” said Richard Li, a program manager in the Azure Media Services team. “A video with multiple faces can take hours to manually redact just a few minutes of footage. This service can reduce the labour-intensive task of manual redaction to just a few simple touch ups.”
Although the tool is designed to be as accurate as possible, Microsoft warns that automated redaction is not yet 100%. As such, users can still modify the final output.
“In addition to a fully automatic mode, there is a two pass workflow which allows the selection/de-selection of found faces via a list of IDs, and to make arbitrary per frame adjustments using a metadata file in JSON format,” said Li. “This workflow is split into ‘Analyse’ and ‘Redact’ modes, as well as a single pass ‘Combined’ mode that runs both in one job.”
In the last year in particular, Microsoft has made remarkable progress establishing its Azure cloud as a reliable platform for media service providers. It recently streamed 2.71 billion minutes of live Olympic coverage with zero downtime – a new record for live event coverage.
Share this story