Google Can Now Recognize Objects Inside Videos Using Machine Learning

Google is leagues ahead of other companies when it comes to search and with a new machine learning tool, the search giant is looking to widen that lead even further.

Google unveiled the latest weapon in its arsenal of search tools yesterday at its Cloud Next conference in San Francisco. It comes in the form of a Video Intelligence API which will allow developers to work on applications that can automatically extract entities from a video.

“In simple words, Google’s computer vision is capable of recognizing objects inside video or a group of videos as well.”

google machine learning

For example, you can search for simple nouns like “dog,” “flower” or “human” or verbs such as “run,” “swim” or “fly”, and it will quickly pull up a list of results relevant to your query.

Currently, the API is limited to only developers, large media organizations and consumer technology companies, who want to build their media catalogs or find easy ways to manage crowd-sourced content.

Google’s image search tools have been around for quite some time. Anyone can upload their photos to Google’s cloud-based Google Photos and search for objects or texts inside images, but this is the first time they have unveiled something for searching inside videos.

Source via Google

Image via Telegraph