Skip to main content

User Manual 2.0

Install​

NOTE
  • Not Using (sudo su or sudo) to install
  • An active Internet connection is required
  • Don't apt upgrade before installation
$ tar zxvf Edge_AI_SDK-installer-<version>.tar.gz
$ ./Edge_AI_SDK-installer.run

EAS-installer-run-s1.png

  • License Agreement
    EAS Install s2.png

  • System Information (by target platform)
    EAS-Install s1.png

  • Select AI Accelerator SDK
    EAS-Install s2-update.png

Activation​

  • User Information
    Please fill in the required information one by one, especially a correct email.
    The following activation will need an available email. Then press the Next button to proceed.

    EAS-Activataion-S1.png

  • License Agreement
    Please review EULA and then press the Activation button if the content is agreed.

    EAS-Activataion-S2.png

  • Activation Code
    If internet is available, a dialog will pop up to ask you to enter a token for activation.

    EAS-Activataion-S3.png

Uninstall​

cd /opt/Advantech/EdgeAISuite
./unInstall.sh

Quick Guide

Edge AI SDK caters to users who are comfortable with the machine learning (ML) experience.
It can quickly evaluate computing performance for the CPU or GPU, and provides runtime results inferenced with ML.

Double click the icon (in the red box) on the Desktop to start the Edge AI SDK App.

Step1.png

Quick Guide Video​

EdgeAISDK OperationVideo.jpg

How to Quickly Start AI Inferences​

Step 1. Go to the Quick Start page.
EAS-QS-2.png

Step 2. Choose one application you want to activate and then confirm inference info.
(1. Object detection, 2. Face detection, 3. Person detection, 4. Pose estimation)
EAS-QS-3.png

Step 3. Choose your video source which could be video clips or the USB Camera.

  • Video (Note: .MP4 only)
    EAS-QS-4.png

  • USB Camera
    EAS-QS-5.png

Step 4. Choose one of the acceleration chipsets to execute selected inference application.
Note: The available accelerator chipsets depend on your AI system and accelerator card.
EAS-QS-6.png

Step 5. Another window will pop up to show the AI inference.
Objection Detect.png

Object Detection​

Object Detection is a computer vision task in which the goal is to detect and locate objects of interest in an image or video.
The task involves identifying the position and boundaries of objects, and classifying them into different categories.

Objection Detect.png

Person Detection​

Person Detection is based on object detection systems that can classify detected objects as human.
It is used in many different sectors: security, insurance, nursing, health, and production.
Technologies offer opportunities that can significantly increase customer satisfaction.

Person Detect.png

Face Detection​

Facial Detection is the task of making a positive identification of a face in a photo or video image against a pre-existing database of faces.
It begins with detection - distinguishing human faces from other objects in the image - and then works on identification of those detected faces.

Face Detect.png

Pose Estimation​

Pose Estimation is a computer vision task where the goal is to detect the position and orientation of a person or an object.
Usually, this is done by predicting the location of specific keypoints like hands, head, elbows, etc.

Pose Detect.png

Monitor AI System Performance​

Go to the System Monitoring page.
This page shows payload and temperature for each chipset.
EAS-System-Info.png

Evaluate the AI Performance​

Go to the System Monitoring page. Click the Run button to evaluate each chipset performance.
Wait for a few seconds to get FPS results.
EAS-Benchmark.png