April Virtual Meetup: Scaling a POC to an Enterprise using Azure Custom Vision

Azure Custom Vision Service is a service for building custom image classifiers, and for making them better over time. This service enables you to identify your own objects and things in images by taking a pre-built image recognition model supplied by Azure, then customise it for your needs by supplying a set of images to update and improve it.

This month we will be broadcasting live on YouTube and Twitter.

YouTube is our primary channel but feel free to catch us on Twitter at https://twitter.com/AzureSydneyUG .

Our schedule for the evening currently looks like this:

5:30 - 5:35pm - Event Kick Off with BYOD (Bring Your Own Drink)!
5:35 - 5:55pm - What's new in Azure - Sam Alavi (Telstra Purple)
6:00 - 7:00pm - Scaling a POC to an Enterprise using Azure Custom Vision (Bruno Capuano)

Main Session: Scaling a POC to an Enterprise using Azure Custom Vision

It all started with a DIY project to use Computer Vision for security cameras at home. A custom Machine Learning model is the core component used to analyze pictures to detect people, animals and more in a house environment. The AI processing is performed at the edge, in dedicated hardware and the collected information is stored in the cloud.
The same idea can be applied to several CCTV scenarios, like parking lots, train stations, malls and more. However, moving this into enterprise scale brings a set of challenges, which are going to be described and explained in this session.

In this new version of the session, we will start from scratch and create a complete “Parking Garage Open Space Tracker” solution with live devices and live cars (small ones, of course)

Let’s code this.

About Bruno:

Bruno Capuano is Regional Innovation Lead at Avanade Canada and has been a Microsoft MVP for the past 12 years. He is an active Microsoft Technologies Community participant, a writer and a frequent speaker at local and international technology conferences.