Configure the plugin

This page gives instructions on how to configure basic operations of the Nx AI Manager Plugin

circle-info

Nx Witness, Nx Go and Nx Meta will work in the same way for the configuration.

Configure Nx Server

After successful installation of Nx Server and Nx Client, an "Integrations" tab should be visible when opening a camera's settings:

Camera Settings dialog with the Integrations tab selected, showing Nx AI Manager in the list
Camera Settings: Integrations tab

The plugin can be enabled/disabled per device on the Integrations tab:

Camera Settings Integrations tab showing the Nx AI Manager toggle in the off position
Nx AI Manager Integration tab: plugin disabled

Once the plugin is enabled and started (toggle on, then click Apply), the settings panel shows the active AI pipeline and model controls directly in the Integrations tab:

Camera Settings Integrations tab with plugin active, showing AI Pipeline dropdown, Device Active toggle, and Device Overview with active pipeline summary
Plugin active: AI pipeline and model settings

To change a model, use the AI Pipelines dropdown to select from the models available on the server.

When using a custom pipeline managed via the Nx AI Cloud, a Manage Device button is shown instead. Clicking it opens the AI Manager device panel to manage the model pipeline.

Plugin settings showing AI Pipeline set to Custom with Manage Device and Reselect Runtime buttons, and Device Overview showing the active pipeline summary
Manage Device button: available when using a custom cloud pipeline
AI Manager device panel opened from the Manage Device button, showing the current model pipeline on device with pipeline settings
Device model pipeline management: opened via the Manage Device button

For specific settings see the model settings.

Visualizing Bounding Boxes

If a model that outputs compatible bounding boxes is selected and running the Nx AI Manager, bounding boxes can be visualized by visiting the Objects tab on the right pane in the Nx Meta Client:

Camera feed in the Nx Meta Client showing a detected person with face bounding boxes from the AI model
Visible Bounding Boxes in Nx Meta Client
circle-exclamation

Adding Event Rules

The Nx AI Manager plugin can generate several different types of events. Network Optix gives the user control over what these events should do, from sending an email to showing a notification. In this example, we will show a text overlay on the video.

Rules can be added by navigating to the Camera Rules menu:

On the Event Rules window, click the Add button to add a new rule.

From here, several options are available. First, on the left side, select Analytics Event from the When context menu. This is the type of event the Nx AI Manager plugin generates.

Select any, or multiple, camera(s) in the At context menu.

Under the Event Type context menu, you will find a number of event types the Nx AI Manager plugin can generate, from alarms to counting objects. In this example, we will select the Objects Counted type.

On the right side, it can be configured what should be done when one of these events is triggered. Here you could set up an email or notification trigger. In this example, we will select the Show text overlay option in the Do context menu at the source camera

If set up correctly, and a model generating counts is selected and running, we should see an overlay on the camera feed showing us the object counts:

Example of Objects Counted text overlay

Confirming it works

Once the plugin is configured and a model pipeline is active, switch to the Objects tab in the right pane of the Nx Meta Client. Bounding boxes and other model output only appear when the Objects tab is the active tab.

Nx Meta Client with the Objects tab active, showing a detected person with face bounding boxes from the AI model
Objects tab active: bounding boxes are visible on the camera feed
circle-info

If the Objects tab is not visible after enabling the plugin, restart the Nx Client; this refreshes the tab list.

If no detections appear after a few seconds, check the Troubleshooting section.

Last updated