Unless you're an oddly fortuitous agent in a Hollywood thriller, trawling through surveillance footage for a single moment of interest is going to take some time. Nest has today released a software update for its security cameras that might let you cut right to the chase, automatically packaging highlights together so you can more quickly get to the bottom of a potential home invasion.
Nest calls the new feature Sightline and it uses algorithms that scan surveillance footage for irregular motion and sound, before packaging such suspect moments into events. These then appear in a timeline on the updated Nest app as an image, allowing users to quickly skip to the parts where it seems something is not quite right.
UPGRADE TO NEW ATLAS PLUS
More than 1,200 New Atlas Plus subscribers directly support our journalism, and get access to our premium ad-free site and email newsletter. Join them for just US$19 a year.UPGRADE
This works alongside Nest's person alerts feature. The company says its cameras can tell the difference between a tree swaying in the breeze or an actual person entering the frame, even with different degrees of certainty. So the camera will ping your phone to tell you it has definitely spotted a person, but will also alert you even if it simply suspects there is an intruder on the premises.
This technology isn't entirely new, with certain action cameras offering similar functionality. TomTom's Bandit, for example, makes edits easier by tagging highlights in the clips that denote things like an elevated heart rate or maximum speed, and the Graava camera released last year works in much the same way.
If you're the owner of a Nest Dropcam, Nest Cam Indoor, or the Nest Cam Outdoor that became available today, you can update the app to have access to a free three-hour Sightline history. For anything beyond that, you'll need a Nest Aware subscription. A 10-day Sightline history will cost US$10 a month or $100 a year, while a 30-day history will set you back $30 a month or $300 a year.
Source: NestView gallery - 2 images