Googles new machine learning API recognizes objects in videos

At its Cloud Next conference in San Francisco, Google today announcedthe launch of a new machine learning API for automatically recognizing objects in videos and making them searchable.

The new Video Intelligence API will allow developers to build applications that can automatically extract entities from a video. Until now, most similar image recognitionAPIs available in the cloud only focused on doing this for still images, but with the help of this new API, developers will be able to build applications that let users search and discover information in videos. That means you can search for dog or flower, for example.

Besides extracting metadata, the API allows you to tagscene changes in a video.

Those videos have to be stored in Googles cloud storage service. You can see a demo of how this works here. If you are developer, you can sign up for the private beta here.

As GooglesFei-Fei Li, its chief scientist of AI and Machine Learning at Google Cloud, noted in todays keynote, the world of pixels goes beyond images. Videos have long been a challenge for machine learning researchers. This new service, though, now makes extracting information from these videos as easy as doing the same for images.

In addition, the Cloud Machine Learning Engine, the companys tool for building custom machine learning models using its TensorFlow framework, is nowgenerally available.

As Li noted in todays keynote, the company wants to democratize the machine learning technologies it has developed in-house. The Vision API is another example of this.