Dipti Pai joins Scott Hanselman to show how to run containerized and VM workloads to get quick, actionable insights at the edge—where data is created—using purpose-built hardware-as-a-service with Azure Stack Edge.

Related links:

AI chipmaker Hailo announced today the launch of its M.2 and Mini PCIe high-performance AI acceleration modules for empowering edge devices.

Integrating the Hailo-8TM processor, the modules can be plugged into a variety of edge devices to provide superior AI capabilities for smart cities, smart retail, industry 4.0, smart homes and other fields.

The plug-in solutions come at a time when industries are increasingly utilizing edge devices that are both high-performing and cost-effective. For example, fanless AI edge boxes are in high demand as they allow many cameras or sensors to be connected to a single intelligent processing device in outdoor deployment. Hailo’s modules – with their high-performing Hailo-8 AI processor delivering 26 Tera-Operations Per Second (TOPS) and high-power efficiency of 3 TOPS/W – can be plugged into any existing edge device with the appropriate M.2 or Mini PCIe sockets, delivering unprecedented performance while reducing latency and improving privacy, the company said.

Building Vision AI applications has never been that simple with Azure IoT Central and IoT Edge.

Today, you can use various technologies to create Video Analytics solutions end to end, but assembling all these technologies from video acquisition, analytics at the edge to managing the cameras and gateways is not trivial.

The Azure IoT Central team just released a new App Template and IoT Edge modules that will help you do all this in a matter a hours.

Check out this demo heavy episode of the IoT Show with Nandakishor Basavanthappa, PM in the Azure IoT Central team.

Learn more reading the bog post at https://aka.ms/iotshow/VisionAIInIoTCentral

Get started today

  • You can use the new Video Analytics for Object & Motion Detection template to build and deploy your live video analytics solution.
  • You can build Video Analytics solution within hours by leveraging Azure IoT Central, Live Video Analytics, and Intel.
  • You can learn more about Live Video Analytics on IoT Edge here and try out some of the other video analytics scenarios via the quickstarts and tutorials here. These show you how you can leverage open source AI models such as those in the Open Model Zoo repository or YOLOv3, or custom models that you have built, to analyze live video.
  • You can learn more about the OpenVINO™ Inference server by Intel® in Azure marketplace and its underlying technologies here. You can access developer kits to learn how to accelerate edge workloads using Intel®-based accelerators CPUs, iGPUs, VPUs and FPGAs. You can select from a wide range of AI Models from Open Model Zoo

With the adoption of IoT, connected applications and systems are moving to the cloud.

The number of end-devices and data generated on the cloud is also increasing. Edge devices like sensors, mobile devices, wearables, robots, and many other connected devices in IoT ecosystem generate a huge amount of decentralized data.

Due to lack of reliable connectivity, delays and difficulties in processing this huge data on cloud, there is a challenge in analyzing and extracting important insights from this data. To deal with this challenge, enterprises are leveraging edge analytics along with cloud computing.

This combination brings stability in the IoT network by bringing the computational power near to the source of data and reducing the delays in analytics, resulting in real-time insights and resolutions for the problems of various industries. In other terms, when data cannot be taken to the algorithm, edge analytics brings algorithms to the data and provide important insights.

Cassie Condon joined Scott Hanselman at Ignite 2019 to talk about the new investments, capabilities, and form factors for the Azure Stack portfolio that ensure our edge infrastructure fits seamlessly in our customers’ solutions.

Azure Stack is now a portfolio of products consisting of Azure Stack HCI, Azure Stack Hub (previously Azure Stack), and Azure Stack Edge (previously Azure Data Box Edge).

A rugged series is also available for sites with harsh environments, including a battery-powered form-factor that can be carried in a backpack.

The versatility of these Azure Stack Edge form-factors and cloud-managed capabilities brings cloud intelligence and compute to retail stores, factory floors, hospitals, field operations, disaster zones, and rescue operations.     

Related Links:

Do you need AI video smarts on the edge?

Then, SolidRun, a developer and manufacturer of high-performance edge computing hardware, and application-specific integrated circuit (ASIC) chip manufacturer Gyrfalcon Technology has a server for you:

The Arm-based, Linux-powered Janux GS31 AI inference server.

What’s an AI inference server you ask? Once you’ve trained a neural network with machine learning to recognize, say, cars and spaces, it’s learned lessons can be built into an application. That program can then infer things about new data based on its training. So, for example, an AI-empowered traffic cop might infer when someone’s speeding or has run a red light.

ExplainingComputers explores Edge computing definitions and concepts.

This non-technical video focuses on edge computing and cloud computing, as well as edge computing and the deployment of vision recognition and other AI applications.

Also introduced are mesh networks, SBC (single board computer) edge hardware, and fog computing.

Azure Data Box Edge is as a server class target for Azure IoT Edge.

Sometimes people want to run more heavy-weight workloads via IoT Edge than fit on traditional gateways. Data Box Edge offers a server-class machine to do so.

During this episode of the IoT Show, get introduced the device capabilities and show a short demo of how simple it is to setup and configure from the Cloud.

Learn more HERE