Overview
Reference architecture that integrates video decode and analytic capabilities in a single box. Configure your application end-to-end with flexible AI capacity and reference video analytics pipeline for fast development.
Intel® Video AI Box can be a standalone device connected to cameras to enable edge analytics in real time. In addition, it can be connected to the network and serve as a discrete AI service on the network to run offline deep learning analytics on-demand.
Select Configure & Download to download the package and the software listed below.
Prerequisites
- Programming Language: Python, C , C++
- Available Software: Intel® Distribution of OpenVINO™ toolkit 2022.2.0, Intel® Deep Learning Streamer (Intel® DL Streamer) 2022.2.0
Recommended Hardware
The below hardware is recommended for use with this package. See the Recommended Hardware page for other suggestions.
- ASRock* NUC BOX-1165G7
- Uzel* US-M5520
- Portwell* PCOM-B656VGL
- AAEON* PICO-TGU4-SEMI
- AOPEN* DEX5750
- DFI* EC70A-TGU
- NexAIoT* NISE 70-T01
- Vecow* SPC-7000 Series
- Lex System* SKY 3 3I110HW
- GIGAIPC* QBiX-Pro TGLA1115G4EH-A1
- GIGAIPC* QBiX-Lite-TGLA1135G7-A1
- ADLINK* AMP-300
- ADLINK* AMP-500
- ASRock* iBOX-1100 Series
- DSIPC* BU11D
- TinyGo* AI-5033
- TinyGo* AI-7702
- Seavo* SV-U1170
- Seavo* SV-U1150
Target System Requirements
- 11th and 12th Generation Intel® Core™ processors and Celeron® processors
- Operating System:
- Ubuntu* 20.04.5 with Kernel Version 5.17.15
- At least 128GB disk space
- At least 8GB (4GB x2) memory with 8GB swap space
- Direct Internet Access
NOTE: If Kernel version is less than 5.17.15, then Kernel will be upgraded to 5.17.15 for 11th and 12th Generation Intel® Core™ processors and Celeron® processors during the installation of the package.
Prerequisites:
- sudo access to system. Current user must have the permissions to execute sudo command;
- Secure boot must be disabled in BIOS, otherwise user will not be able to login to the new 5.17.15 kernel.
How It Works
Intel® Video AI Box forms the base to create a full video analytics pipeline for lightweight edge devices. This package is optimized for 11th and 12th Generation Intel® Core™ processors and Celeron® processors, which come with integrated graphics capable of offering AI computing accelerations with both performance and efficiency.
Pick the software modules required for your solution and download the installation scripts accordingly.
Package Content
Two configurations are available. The recommended configuration contains the following packages:
- Intel® Distribution of OpenVINO™ toolkit 2022.2.0 (native and containerized)
- Intel® Deep Learning Streamer Pipeline Framework 2022.2.0 (native and containerized)
- OpenVINO™ Integration with TensorFlow* Version 2.2.0
- Database for metadata: SQLite DB, InfluxDB
- Containerization technology: Docker Community Edition and Docker Compose
- Cloud connectors: Amazon Web Services Greengrass Prerequisite and Azure IoT PnP Bridge
- Container: openvino/ubuntu20 dev:2022.2.0 and intel/dlstreamer:2022.2.0-ubuntu20-gpu815-dpcpp-devel
The development configuration also includes the AI Box Test Module for Intel® Edge Software Device Qualification (ESDQ).
Deployment Package
The deployment package has the same key software available as the deployment package, but the preselected modules are mainly run-time libraries. The objective is to minimize the installation footprint of the package, so that it is suitable for being deployed to the edge devices where memory and storage could be constrained resources.

As depicted in Figure 2, the integrated GPU (iGPU) is the primary target platform where AI workloads are deployed. The CSP connectors are the interface for the Edge AI Box to leverage cloud services to create edge-to-cloud functions such as telemetry, device onboarding, and manageability. Furthermore, we also have a number of reference implementations, such as Smart Video AI Workload, as a quick demo tool for developers to evaluate the performance of the Edge AI Box hardware.

Get Started
Prerequisites
- Root password must be set for the system.
- For 12th Generation Intel® Core™ Processors or Celeron® processors (products formerly Alder Lake) to work with GPU accelerators, complete the steps below:
- sudo vim /etc/default/grub
- Append “i915.force_probe=*” to the end of GRUB_CMDLINE_LINUX_DEFAULT:
- GRUB_CMDLINE_LINUX_DEFAULT="quiet splash i915.force_probe=*"
- sudo update-grub
- sudo reboot
NOTE: These steps are also required for Smart Video AI Workload reference implementation.
Install the Package
Select Configure & Download to download the package and then follow the steps below to install it.
- Open a new terminal, go to the downloaded folder and unzip the downloaded package:
unzip edge_ai_box_for_video_analytics.zip
- Go to the edge_ai_box_for_video_analytics/ directory:
cd edge_ai_box_for_video_analytics
- Change permission of the executable edgesoftware file:
chmod 755 edgesoftware
- Run the command below to install the package:
./edgesoftware install
- During the installation, you will be prompted for the Product Key. The Product Key is contained in the email you received from Intel confirming your download.
- When the installation is complete, you see the message “Installation of package complete” and the installation status for each module.
-
NOTE: Kernel will be upgraded to 5.17.15 for 11th and 12th Generation Intel® Core™ processors and Celeron® processors, so rebooting the system after installation is mandatory to work with iGPU.
Build a Solution Based on the Package
Use the Single and Multi-object Detection with Hardware Acceleration tutorial application.
In addition, explore the demos located in the OpenVINO™ integration with TensorFlow* examples directory.
To connect an IoT Plug and Play bridge sample running on Linux to Azure* IoT Hub, go through the sample with previously installed azure_cli, Azure IoT explorer and cloned repository.
Summary and Next Steps
With this application you successfully created a full video analytics pipeline for lightweight edge devices.
Learn More
To continue learning, see the following guides and software resources:
Troubleshooting
If installation of OpenVINO™ toolkit TensorFlow Bridge component fails while running python tests for CPU, then do the following:
- Uninstall Python package of ‘keras’ and retry the installation.
$ pip3 uninstall keras
- Or reboot the system once and install it again.
Support Forum
If you're unable to resolve your issues, contact the Support Forum.