Google Home will soon get better at recognizing you with clothing and sounds
Google Home is getting an update that will allow smart home cameras to identify people by clothing color and body shape, as well as recognize specific sounds like dog barks or footsteps.
Google has announced new features for Google Home that will enhance facial recognition in smart home cameras. Starting June 23rd, the company is expanding its facial recognition system so that people tagged in the Familiar Faces library can continue to be identified even when their faces are not clearly visible. This will be achieved using additional non-biometric signals such as body size and clothing color.
Additionally, the Familiar Faces library will begin automatically updating with the most recent images of everyone in the household, reducing inaccurate notifications from outdated examples. Google also says that its AI-generated video event descriptions can now identify specific sounds—like dogs barking, alarms, or footsteps—and include them in notes, even if the audio comes from an off-camera source.
These updates could help address quirks noted by The Verge's Jennifer Pattison Tuohy while testing Google's updated smart home system last year, such as event logs with detailed descriptions of people who were not there and events that did not happen.
A new update to the Google Home app (version 4.20) also adds "System Health alerts" if your Nest thermostat detects issues with your HVAC system, which appears to be a Gemini-connected update to the existing Google Nest System Health Monitoring, along with improved support for Matter switches.
