Skip to main content
Version: 2.3.1

Installation and Activation

System Requirements​

Supported OS:

  • Windows 10 (64-bit)
  • Ubuntu 20.04 (64-bit)

Hardware Requirements:

Minimum:

  • CPU: 4 x 3GHz with AVX support
  • RAM: 2GB
  • HDD: 6GB

Recommended:

  • CPU: 6 x 3GHz with AVX support
  • RAM: 4GB
  • HDD: 6GB
  • GPU: GTX 1050Ti or equivalents

Specified requirements correspond to 1 video stream in 1080p (Full HD) and 5 persons in the frame at the same time (database size up to 50К faces).

Preparing for Installation​

Windows​

Before installing OMNI Agent on Windows you might need to install Microsoft Visual C++ Redistributable for Visual Studio.

Linux​

If you use Linux, you need to set up the execution permission for the installer before running. To set up the execution permission to the installer, follow the steps below:

  • Go to the directory, where OMNI Agent installer is downloaded to, and click the right button on the installation file.
  • Open Properties, go to the Permission tab, and check Allow execute checkbox

Installation​

To install OMNI Agent to your PC, follow the steps below:

  1. Download OMNI Agent installer from the distribution kit.
  2. Once the downloading is completed, run the OMNI Agent installer and follow the installation wizard's instructions.

Activation​

To activate OMNI Agent, do the following:

  1. After completing the installation, run OMNI Agent, select the on-premise (Self-hosted) version at OMNI Agent web page and click on Next button. The domain for on-premise deployment is specified in the platform.values.yaml of OMNI Platform distribution kit in the field ingress.rules.gateway.host.

img.png

  1. Sign in to OMNI Agent using the email and password of your OMNI Platform account. This data is specified in ./cfg/platform.secrets.json in variables platform-user-secret.default_password and platform-user-secret.default_email.

img.png

  1. Add an IP or USB camera:
    • To use an IP camera, enter the camera URL.
    • To use a USB camera, connect the camera to your PC and select it from the list of connected cameras.

img.png

  1. After the camera is added, you will see the video from the camera and the information about the detected persons (their gender, age, emotions, etc.).

img.png

The detected faces and silhouettes can be highlighted as follows:

face bbox:

  • bbox with red corners: a face is detected but the person’s attention is none;
  • bbox with white corners: both a face and the person’s attention are detected;
  • bbox with corners of + form: image quality is insufficient or head rotation angle is not applicable for proper detection;
  • bbox with green corners: a face is detected and recognized but the person attention is not registered;
  • bbox with orange corners: a face is detected and recognized, and the person's attention is registered.

body bbox:

  • green bounding box: a human silhouette is detected and has an ID;
  • red bounding box: a human silhouette is detected, but an ID is not assigned yet.