Google Cloud Video Intelligence API scans video, identifies objects & events

Got a big video library and want to find all your segments about baseball? Want to quickly flag when different things appear within a particular video? Google’s got a new cloud-based tool for you.

Called the Cloud Video Intelligence API, the toolset can do the activities described above and more. Here are two examples:

New Google Cloud Video Intelligence API can break down video into what's happening #GoogleNext17 https://t.co/dGCVeGRCox pic.twitter.com/w6XPW75fEz

— Danny Sullivan (@dannysullivan) March 8, 2017

Have big video library? Google's new Video Intelligence API can scan & find all video segments on, say, baseball #GoogleNext17 pic.twitter.com/yTRWvnJxan

— Danny Sullivan (@dannysullivan) March 8, 2017

Google says the new API is the first-of-its-kind. From its blog post on the news:

Cloud Video Intelligence API (now in Private Beta) uses powerful deep-learning models, built using frameworks like TensorFlow and applied on large-scale media platforms like YouTube.

The API is the first of its kind, enabling developers to easily search and discover video content by providing information about entities (nouns such as “dog,” “flower” or “human” or verbs such as “run,” “swim” or “fly”) inside video content.

It can even provide contextual understanding of when those entities appear; for example, searching for “Tiger” would find all precise shots containing tigers across a video collection in Google Cloud Storage.

As noted in quote, the API is in “private beta” for those who sign-up and use the Google Cloud Platform console. You can learn more here.

The announcement came during the opening keynote of the Google Cloud event “Next” that started today. You can watch the livestream here and our own live blog is below: