Edge Insights for Vision
Deploy computer vision and deep learning workloads at the edge with prevalidated software components.
Overview
Software Architecture
Edge Insights for Vision is a set of pre-validated modules, implemented as a containerized architecture or a stand-alone runtime. The package features third-party modules for orchestration and cloud support, and the Intel® Distribution of OpenVINO™ toolkit for deploying computer vision and deep learning workloads at the edge.
Featured Components
Intel® Distribution of OpenVINO™ Toolkit
Develop and optimize AI and computer vision applications. The Intel® Distribution of OpenVINO™ toolkit maximizes performance and extends workloads across Intel® hardware, including accelerators.
Integrate workloads with an open-source framework that provides data and communications interoperability between devices and applications at the IoT edge.
Recommended for Intel® Xeon® processors and 6th to 8th generation Intel® Core™ processors.
Supports hardware acceleration on CPU, iGPU, VPU, and the Intel® Neural Compute Stick 2.
Use Cases and Reference Implementations
Reference Implementation
Social Distancing Detection for Retail Settings
Create an end-to-end pipeline to detect social distancing, a COVID-19 preventive measure. Apply deep learning models from the Intel® Distribution of OpenVINO™ toolkit to measure the distance between people based on input from multiple camera feeds.
Reference Implementation
Intelligent Traffic Management
Monitor traffic intersections via IP cameras to optimize traffic flow. Detect vehicles and pedestrians, record vehicle types and counts, calculate velocity and acceleration, and more.
Reference Implementation
Driver Management
Use computer vision, deep learning, and edge networking to develop a solution for managing driver behavior and alertness. Provide real-time alerts to the driver and fleet manager, plus long-term analytics about drivers, vehicles, and routes.
Reference Implementation
Automated Checkout
Use computer vision to detect products that are removed from a cooler or cabinet without the mechanical pusher or robotic arms.
Reference Implementation
Real-Time Sensor Fusion for Loss Prevention
Combine data from point-of-sale systems, scales, cameras, and RFID readers to prevent loss at checkout.
Use Case
Connect Edge Devices to Microsoft Azure* IoT
Simplify Azure IoT Edge* deployments. Install a web-based application that provides an Out of Box Experience to securely connect your Intel device to Azure* IoT Hub and Azure* IoT Central. Create resources and enable configuration and monitoring of edge AI and use case deployments.
You are responsible for payment of all third-party charges, including payment for use of Microsoft Azure* services.
Use Case
Amazon Web Services (AWS)* Cloud to Edge Pipeline
Single-click deployment of a ready-to-use cloud to edge inferencing pipeline that uses AWS IoT Greengrass and OpenVINO™ toolkit on the edge, and AWS IoT in the cloud. Includes sample AWS IoT Greengrass Lambda for image classification and object detection.
You are responsible for payment of all third-party charges, including payment for use of Amazon Web Services (AWS).
Documentation
Understand the components, services, architecture, and data flow in Edge Insights for Vision.
Instructions for installing the software and validating the installation.
Step-by-step examples to familiarize you with the software's core functionality.
Hardware Qualification
Original device and equipment manufacturers (ODMs and OEMs) can learn how to include devices in our recommended hardware program or the Edge Software Hub.