Facilitating the Spread of Knowledge and Innovation in Professional Software Development

Write for InfoQ


Choose your language

InfoQ Homepage News Google Announces Updates to AutoML Vision Edge, AutoML Video, and the Video Intelligence API

Google Announces Updates to AutoML Vision Edge, AutoML Video, and the Video Intelligence API

In a recent blog post, Google announced enhancements to a part of its Vision AI portfolio: AutoML Vision Edge, AutoML Video, and the Video Intelligence API. Each received updates to enhance their capabilities.

Both AutoML Vision Edge and AutoML Video were both introduced earlier this year, in April, as a part of Google’s AI Platform, while the Video Intelligence API introduction dates back a few years prior, with a public beta release in June 2017. All received enhancements provide customers with more features, as both Google product managers Vishy Tirumalashetty and Andrew Schwartz in the blog post state:

We’re constantly inspired by all the ways our customers use Google Cloud AI for image and video understanding—everything from eBay's use of image search to improve their shopping experience to AES leveraging AutoML Vision to accelerate a greener energy future and help make their employees safer.

With AutoML Vision Edge, developers can train, build and deploy ML models at the edge. This began initially with image classification, and now also supports object detection. Developers can now implement both operations on edge devices, including those using ARM, NVIDIA GPUs, or other chipsets. Operating systems support includes Android and iOS. According to the blog post, the object detection is useful for use cases such as identifying pieces of an outfit in a shopping app, detecting defects on a fast-moving conveyor belt, or assessing inventory on a retail shelf.

AutoML Video is a toolset designed to make it easier for users to train video-parsing AI models, and now it can track the movement of multiple items between frames through object detection. With object detection in AutoML Video, developers can create applications for tracking management, robotic navigation, and so on. 


The Video Intelligence API, a part of AutoML Video, offers developers pre-trained machine learning models that automatically recognize a vast number of objects, scenes, and actions in stored and streaming video. This API now has a so-called Video Intelligence Logo Recognition feature, providing detection and recognition of logos from more than a 100,000 popular businesses and organizations in stored and streaming clips, which according to the blog post is useful for brand safety, ad placement, and sports sponsorship use cases.  

Regarding the Video Intelligence API demo, Google developer advocate Sara Robinson stated in a recent blog post that it is easy to analyze videos with just a few lines of code: 

The Video Intelligence API makes it easy to analyze your video content with a single API request.

Next to Google, Microsoft and Amazon offer capabilities through their offerings in the cloud to leverage AI, including logo and object detection. In comparison, Microsoft provides a Custom Vision service in Azure, which offers APIs such as Video Indexer to allow developers to get insights from audio and video files - or Amazon, who provides a service called Rekognition, which gives developers means to add intelligent image and video analysis to their applications. 

Lastly, to learn more about any of these new features, visit Google’s Vision AI website.

Rate this Article