Edge Insights for Vision

Download PDF
ID 772621
Date 10/24/2022
Public
Document Table of Contents
Document Table of Contents x
Edge Insights for Vision How it Works Get Started Guide using Linux* Release Notes Documentation Archive
Get Started Guide using Linux* x
Linux* Requirements Install Edge Insights for Vision Introduction to the Edge Software Command Line Interface (CLI) Linux* Troubleshooting Linux* Tutorials
Linux* Tutorials x
Single and Multi-Object Detection with Hardware Acceleration on Linux* Multi-Camera Detection of Social Distancing on Linux*
Single and Multi-Object Detection with Hardware Acceleration on Linux* x
Single and Multi-Object Detection on CPU on Linux* Single and Multi-Object Detection on GPU on Linux* Single and Multi-Object Detection on Intel® Vision Accelerator on Linux*
Edge Insights for Vision
How it Works
Get Started Guide using Linux*
Release Notes
Documentation Archive

How it Works

Edge Insights for Vision is a set of pre-validated modules, implemented as a containerized architecture or a stand-alone runtime, for deploying computer vision and deep learning workloads at the edge. The package features third-party modules for orchestration and cloud support, and the Intel® Distribution of OpenVINO™ toolkit for computer vision and deep learning apps optimized for Intel® architecture.

This section provides an overview of the modules and services featured with Edge Insights for Vision.

Modules and Services

The Intel® Distribution of OpenVINO™ toolkit (OpenVINO™)

Edge Insights for Vision includes the Intel® Distribution of OpenVINO™ toolkit so you can develop and optimize AI and computer vision applications. OpenVINO™ maximizes performance and extends workloads across Intel hardware, including accelerators.

Edge Insights for Vision supports the following OpenVINO™ packages to optimize inferencing on your edge IoT device:

  • Intel® Distribution of OpenVINO™ toolkit in a Container builds Docker* images for the OpenVINO™ toolkit.
  • Intel® Distribution of OpenVINO™ toolkit Runtime installs the toolkit runtime packages distributed through the APT repository. It does not run in a container.

Refer to the Release Notes for the supported version of Intel® Distribution of OpenVINO™ toolkit.

Container Engines and Orchestration

Edge Insights for Vision features Docker* and Rancher k3s* for automated container management.

  • Docker* is a container framework widely used in enterprise environments. It allows applications and their dependencies to be packaged together and run as a self-contained unit.

  • Rancher k3s* is a lightweight Kubernetes* distribution that provides automated container management for IoT and edge computing.
    NOTE:
    It is observed that Rancher k3s features may not work for PRC users.

Cloud Edge Connectors

Edge Insights for Vision features Amazon Web Services (AWS)* Greengrass Prerequisites and to connect edge devices with the cloud and each other.

Amazon Web Services (AWS)* Greengrass Prerequisites

AWS* Greengrass Prerequisites installs the following packages to enable local data collection, analysis, and communication for your AWS-connected edge devices:

  • AWS* IoT Greengrass Core.
  • AWS* IoT Device SDK.
  • AWS* IoT Greengrass SDK.

Intel Tools

  • Intel® Edge Software Configurator is a software tool that enables you to configure and optimize* Edge Software Hub Packages and custom applications, creating and managing Containers and Virtual Machines for edge computing with the same flexibility you would have in cloud computing operations.
Level Two Title