Google is significantly enhancing its smart home artificial intelligence, enabling it to identify individuals based on their clothing and to recognize specific sounds captured by cameras.
An upcoming update for Google Home is set to notably reduce instances of smart home cameras misidentifying residents, particularly when their faces are obscured or turned away. Effective June 23rd, Google will expand its existing facial recognition capabilities. Individuals previously tagged in the "Familiar Faces" library will continue to be identified even without clear facial visibility, leveraging "additional non-biometric signals such as body size and clothing color."
Furthermore, the "Familiar Faces" library will now automatically refresh with the most current images of household members, aiming to minimize inaccurate notifications caused by outdated visual data.
Google further states that its AI-generated video event descriptions will now be capable of identifying and including "specific sounds — such as dogs barking, alarms, or footsteps" in event notes, even if the audio source is off-camera. These comprehensive updates are poised to rectify several anomalies previously observed by The Verge's Jennifer Pattison Tuohy during her review of Google’s updated smart home system last year, which included event logs detailing non-existent individuals or occurrences.
Concurrently, version 4.20 of the Google Home app introduces new "System Health alerts." These alerts will notify users if their Nest thermostat detects potential issues with their HVAC system, appearing to be an evolution of the existing Google Nest System Health Monitoring, possibly integrated with Gemini. Additionally, this update brings enhanced support for Matter switches.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.