I’ll be sharing some experiences and insights around Machine Learning, Computer Vision and IoT. Here are my session details.
How a PoC at home can scale to Enterprise Level using Custom Vision APIs (v2!)
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)
A while ago I wrote about the Artificial Intelligence School of Microsoft, you can find many resources on AI using Microsoft technology in that “virtual school”.
Note: Check my post about AI School And you see because I like this approach.
Hace un tiempo escribí sobre la Artificial Intelligence School de Microsoft, donde es posible encontrar muchos recursos sobre AI utilizando tecnología Microsoft.
Nota: Revisa mi post sobre AI School y veras porque me gustan este enfoque.
It’s been a while since I wrote about Microsoft Flow, and today we have some very interesting news to share, so let’s go for it.
I’ll start with a simple but power feature added a couple of weeks ago: “Save As” on a flow definition. This is very powerful, let me share an scenario: right now when we need to duplicate a flow definition, we need to create the flow from scratch. With the Save As feature we can quickly create duplicates, or even snapshots of our definitions and use them as a “back up” while we are working.
Another interesting topic is the new integration with physical buttons (link). The 2 ones for start area Flic by Shortcut Labs, and Bttn by The Button Corporation. Both need to be connected via Bluetooth to a iOS or Android device. And then, we can identify the buttons and use them as triggers for flow definitions.
Tenía abandonado los posts sobre Microsoft Flow, y ahora que tenemos algunas novedades interesantes, es momento de comentar las mismas.
En primer lugar tenemos una nueva opción de “Save As” para nuestras definiciones de Flow. Esto es INCREÍBLEMENTE ÚTIL, ya que hasta ahora solo podíamos crear desde cero definiciones de Flow cuando queríamos hacer un BackUp o similar.
Otro detalle interesante es la integración con botones reales (link). En este caso con Flic by Shortcut Labs, and Bttn by The Button Corporation. Ambos dispositivos requieren estar conectados via BlueTooth a un smartphone iOS o Android, y a partir de allí los podemos utilizar como trigger para lanzar un Flow.
Today is a special podcast episode, because everyone is on holidays we have to cancel some of the scheduled podcasts. And that’s fine, this is holidays time !!! So I think I try an idea I have on my mind in the past months:
Create a quick podcast where I share my opinions on some of the latest techonology news. In this episode I’ll talk about some of the news in Windows 10 Anniversary Update for some of the devices I wrote and know: Hololens and Windows 10 IoT Core.
Windows 10 Anniversary Update is here and there are lot of news to write about. I’ve already wrote about some of the new Hololens features, and I need to write down also some important topics related to Windows 10 IoT Core and Anniversary Update.
So let’s start with the basis: the main image and news are always focused on Raspberry Pi 3, however the Anniversary Update will also work with the MinnowMax, Raspberry Pi 2, and DragonBoard 410c developer boards. The new Getting Started section is a really nice step by step tutorial to setup the device much faster.
And finally, my selected set of top new features are:
Windows IoT Remote Client – remote into your IoT device to control and view what is displayed on your IoT device from your desktop or phone