Businesses can now run cloud intelligence directly on IoT devices at the edge managed by Azure IoT Central (https://aka.ms/iotshow/iotedgeiniotcentral).

This new feature helps businesses connect and manage Edge devices, deploy edge software modules, publish insights, and take actions at-scale – all from within IoT Central.

In this episode of the IoT Show, Ranga Vadlamudi, Principal PM in the Azure IoT team joins Olivier to demo how the integration works.

To learn more about IoT Edge devices support in Azure IoT Central, visit https://aka.ms/iotshow/iotedgeiniotcentral

The Vision AI DevKit (https://aka.ms/iotshow/visionaidevkit) is a smart camera device powered by Azure IoT Edge. Equiped with a camera and microphones, it allows developing proof of concept (or even actual) projects implementing advanced image and sound analytics directly on the device.In a previous episode (https://aka.ms/iotshow/185), Mahesh Yadav showed us the unboxing and first time experience with the device.

In this new episode, Mahesh is back to show us how you can train and deploy new AI models on the device in a matter of minutes.

Check out the Vision AI devkit site to learn more and take it for a spin: https://aka.ms/iotshow/visionaidevkit

With Farmbeats, Microsoft is making data-driven agriculture simple and affordable.

Watch this intriguing episode to learn about Farmbeats, (aka.ms/iotshow/farmbeats) a new Azure offering currently in preview and available on Azure Marketplace.

Understand how Farmbeats enables partners to make farmers more efficient by providing visibility into how much water is in the soil, what the soil conditions are, how plants are growing, and more. Learn from Dr. Ranveer Chandra, Chief Scientist, Azure Global, about the amazing solution to the challenge of connecting to farms (leveraging unused TV channels!) developed by Microsoft.

Hear how data is stored in Farmbeats Datahub and analyzed using AI and ML to provide valuable insights like where sensors should be optimally placed. Jeff Hollan, Principal PM Manager, shows how simple it is to use IoT Plug and Play to connect a new sensors, drones, or robots to Farmbeats.

Jeff demonstrates how easy it is for a partner to enable a farmer to view pressure, temperature, and humidity from a sensor on his/her farm using Azure IoT Central.

Learn more aka.ms/iotshow/farmbeats

Try Farmbeats aka.ms/iotshow/farmbeatsonmarketplace

Have you ever tried to transfer 1M of data when your IoT device has only 2K of RAM?

If so, then this IoT show is for you! (aka.ms/iotshow/ulib)

Marcos Perez Mokarzel and Dane Walton, Software Developers on the Azure Device SDK team, appear in this episode to talk about the uStream library, written in the C language.

uStream is an Azure utility library for embedded and constrained devices. It enables developers to expose and use large amounts of data without the need for large amounts of memory.

Marcos gives an overview of the constrained memory use cases that IoT device developers face and Dane steps through how the uStream library solves these issues. Dane presents a system level overview of the uStream library and demos ustream_read(), ustream_clone(), and more .

Azure Maps Mobility Services make the life of an IoT developer easier and they contribute towards a great end user experience.

Watch this episode to see Outi Nyman, Senior Program Manager, Azure Maps, step through the APIs for these services.

Designed to support developers creating smart city applications that move people and things from one place to another, they help create applications that decrease traffic congestion and increase air quality.

The Mobility Service APIs for Azure Maps are brought to life in partnership with Moovit, Inc. Moovit combines information from public transit operators and authorities with live information from its user community to offer a real-time picture of public transit services, including stops, route information, and travel time estimations.

Geofencing has many practical applications. A geofence is a virtual boundary defining an area on a map. Using tools in Azure Maps, Jim demos how to test if a coordinate is inside or outside the Microsoft Redmond campus boundary.

It can be used to send an alert if an expensive piece of machinery leaves a construction site unexpectedly or to send a warning if a worker enters an unsafe location within a factory.

Jim Bennett shows us how to code geofencing applications with Visual Studio, Python, and Azure Maps.

Jim explains why and how to manage a buffer around your geofence boundary. (Hint: GPS is not that accurate!) He also demos how to set a notification using a web hook and an Azure Logic App when a person or item enters or leaves a geofence area.

Next steps:

Step through the tutorial: Set up a geofence by using Azure Maps

Visit Jim’s blog on geofencing: are you where you should be?

Mahesh Yadav, Software Engineer on the Intelligent Edge team, joins the IoT Show to unbox the Microsoft Vision AI DevKit (aka.ms/iotshow/visionaidevkit), a smart camera for the intelligent edge.

The developer kit uses the Qualcomm’s Vision Intelligence 300 Platform which uniquely runs machine learning with hardware acceleration delivering results in milliseconds which is perfect for connected car or connected factory scenarios where you need low latency as well as support offline scenarios.

In this episode, you will see how easy it is to bring up AI on the edge with Azure IoT Edge and Azure Machine Learning.

The DevKit includes a sample AI model that identifies 183 objects including people, laptops, chairs and more. The highlight of the show is a real-time camera demo that asserts that both Mahesh and Olivier really are people.

And it’s always good when an AI affirms your personhood. 😉

Learn how VISEO (https://aka.ms/iotshow/viseo) is analyzing large amounts of data (1 GB to 1 TB) collected from drones and other vehicles flying over 32,000 km of railway tracks in France for Altametris, a subsidiary of SNCF Réseau.

VISEO’s Vincent Thavonekham, Head of Smart Factory, and Igor Leontiev, Chief Cloud Solution Architect, show three demos in this amazing episode. Vincent and Igor demonstrate how VISEO processes 42 billion laser dots and other data collected from 450 km of railroad tracks from Paris to Lyon.

Using VISEO’s custom data model and Azure IoT Edge, data at the edge is now prepared for upload to the Cloud in days instead of weeks. From the Cloud, Altametris analyzes the data to track and maintain its railroad assets remotely reducing expenses and increasing safety.

Watch Paul de Carlo, Microsoft Cloud Developer Advocate, step through his Intelligent Edge Hands-on Lab (https://aka.ms/iotshow/intelligentedge — which is open source and available for you to try)

During this lab, Paul deploys an IoT Edge module to an NVIDIA Jetson Nano development board to allow for detection of objects from the live video stream of a Webcam. In this episode, the webcam is scanning the floor at Microsoft Ignite 2019 and detects people, backpacks, chairs and more, in real time.

The same setup can detect objects in YouTube video streams, RTSP streams, or HoloLens Mixed Reality Capture and stream up to 32 videos simultaneously. Object Detection is accomplished using YOLOv3-tiny with Darknet.

Learn why Paul and Olivier are never going to give you up, never going to let you down during this memorable episode.