Overview

Intel iGPU OpenVINO Object Detection

About Advantech Container Catalog

Advantech Container Catalog is a comprehensive collection of ready-to-use, containerized software packages designed to accelerate the development and deployment of Edge AI applications. By offering pre-integrated solutions optimized for embedded hardware, it simplifies the challenges often faced with software and hardware compatibility, especially in GPU/NPU-accelerated environments.

Key benefits of the Container Catalog include:

Feature / Benefit	Description
Accelerated Edge AI Development	Ready-to-use containerized solutions for fast prototyping and deployment
Hardware Compatibility Solved	Eliminates embedded hardware and AI software package incompatibility
GPU/NPU Access Ready	Supports passthrough for efficient hardware acceleration
Model Conversion & Optimization	Built-in AI model quantization and format conversion support
Optimized for CV & LLM Applications	Pre-optimized containers for computer vision and large language models
Scalable Device Management	Supports large-scale IoT deployments via EdgeSync, Kubernetes, etc.
Lower Entry Barrier for Developers	High-level language (Python, C#, etc.) support enables easier development
Developer Accessibility	Junior engineers can build embedded AI applications more easily
Increased Customer Stickiness	Simplified tools lead to higher adoption and retention
Open Ecosystem	3rd-party developers can integrate new apps to expand the platform

Container Overview

Intel iGPU OpenVINO Object Detection is a Retinopathy detection demo Container on Intel 12&13th Gen CPU and iGPU.

Using the integrated GPU (iGPU) in Intel 12th and 13th Gen Core processors, developers can efficiently run AI workloads like diabetic retinopathy detection directly on compact edge systems. These iGPUs support Intel® OpenVINO™ Toolkit, enabling optimized inference for deep learning models without requiring a discrete GPU. With improved parallel computing performance and low power consumption, the Intel iGPU is well-suited for AI-powered medical imaging applications where space, energy efficiency, and cost are critical. By leveraging Intel’s platform, healthcare developers can deploy accurate and responsive diabetic retinopathy detection models in clinics or point-of-care devices, making AI-assisted diagnostics more accessible and scalable.

Key Features

AI Application Demo: Retinopathy detection
Hardware Acceleration: Optimized access to CPU, iGPU.
Complete AI Framework Stack: OpenVINO
Industrial Vision Support: Accelerated OpenCV
Edge AI Capabilities: Support for computer vision

Host Device Prerequisites

Hardware Specifications

Component	Specification
Target Hardware	ARK-3534
CPU	12th&13th Gen Intel® i3/i5/i7/i9
iGPU	Intel UHD Graphics 770
Memory	16 ~ 64 GB shared CPU memory

Prerequisite Software on Host OS

Component	Version	Description
intel gpu driver	24.26.30049.6

Container Environment Overview

Software Components

Component	Version	Description
OpenVINO Runtime	2023.1.0.12185	OpenVINO Runtime provides AI framework run Model inference, and deploy applications
OpenCV	4.7.0	Computer vision library
YOLO	X	YOLOX Computer Vision Model for Retinopathy detection
Retinopathy detection	1.0.0	Retinopathy detection AI Demo

Quick Start Guide

Refer to Advantech Container Catalog Github: ACC-L3-01-Qualocmm-AI-enabled-Container and Intel Gen 12th~13th Edge AI Container for more quick start guide details.

Run on CPU

sudo docker run -it --privileged=true --ipc host --device /dev/dri:/dev/dri --device-cgroup-rule='c 189:* rmw' -v /tmp/.X11-unix:/tmp/.X11-unix -v /dev/bus/usb:/dev/bus/usb -u root --env DISPLAY=:0  --rm eiot/eas-intel-1213-retinopathy-demo:ubuntu22.04-1.0.0 /bin/bash -c  "~/omz_demos_build/intel64/Release/object_detection_demo -i /opt/intel/openvino/Eye/object_detection/video/output_4288_2848_FPS=1.mp4 -m /opt/intel/openvino/Eye/object_detection/model-test/last_epoch_ckpt-opset-10.xml -at yolox -output_resolution 1280x720 -t 0.9 -labels "/opt/intel/openvino_2023.0.1.11005/Eye/Eye.labels"" -loop -d CPU