Latest in Autonomous

Image credit:

Google's latest object recognition tech can spot everything in your living room

3 Shares
Share
Tweet
Share
Save

Sponsored Links

Automatic object recognition in images is currently tricky. Even if a computer has the help of smart algorithms and human assistants, it may not catch everything in a given scene. Google might change that soon, though; it just detailed a new detection system that can easily spot lots of objects in a scene, even if they're partly obscured. The key is a neural network that can rapidly refine the criteria it's looking for without requiring a lot of extra computing power. The result is a far deeper scanning system that can both identify more objects and make better guesses -- it can spot tons of items in a living room, including (according to Google's odd example) a flying cat. The technology is still young, but the internet giant sees its recognition breakthrough helping everything from image searches through to self-driving cars. Don't be surprised if it gets much easier to look for things online using only vaguest of terms.

All products recommended by Engadget are selected by our editorial team, independent of our parent company. Some of our stories include affiliate links. If you buy something through one of these links, we may earn an affiliate commission.
Comment
Comments
Share
3 Shares
Share
Tweet
Share
Save

Popular on Engadget

The 2019 Engadget Holiday Gift Guide

The 2019 Engadget Holiday Gift Guide

View
The Morning After: Google Stadia's launch game line-up gets a big boost

The Morning After: Google Stadia's launch game line-up gets a big boost

View
Canadian court issues first ever ISP order to block a piracy website

Canadian court issues first ever ISP order to block a piracy website

View
Google Stadia will have 10 more games at launch

Google Stadia will have 10 more games at launch

View
Stanford's new tech-laden hospital includes pill-picking robots

Stanford's new tech-laden hospital includes pill-picking robots

View

From around the web

Page 1Page 1ear iconeye iconFill 23text filevr