Google unveils cloud-based 'Video Intelligence Application' to recognize objects in video

US tech giant Google has launched a cloud-based Video Intelligence Application Programming Interface (API) that helps locate the exact frame from a large video database.

"The API is the first-of-its-kind, enabling developers to easily search and discover video content by providing information about entities, for example, dog, flower or human inside video content," said Chief Scientist Google Cloud (Artificial Intelligence and Machine Learning) Fei Fei Li at Cloud Next conference here.

The Silicon Valley company also made public Cloud Machine Learning Engine, that provides option for organisations that want to train and deploy their own models into production in the cloud.

On Video Intelligence API, Li said that 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.

The API quickly annotates videos stored in Google Cloud Storage with video, shot and frame-level context, she said.

Citing example of usage, she said, "Media organisations are sitting on years of archived content, with very little metadata on what is in their content. Organisations can now useo content. Video Intelligence API to understand key entities and identify when and where they appear in their video.

This level of metadata enables organisations to find new ways to re-purpose their existing video and create new monetisation opportunities."
Video Intelligence API joins the growing family of machine learning APIs that are designed to make it easy for any developer to integrate machine learning into their applications, she added.