> For the complete documentation index, see [llms.txt](https://nx.docs.scailable.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/plugin-settings/input-masks-and-roi/inclusive-masks.md).

# Inclusive Masks

Limit inference to inside a drawn polygon.

Inclusive input masks ignore objects that are fully outside the drawn mask area. Create these masks on the video frame inside the AI Manager's Model Settings, in the **Input Masks** section.

Select **Inclusive** from the **Mask Type** dropdown:

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-9fc38b213e792fbf668c26edfba4e9fd51d77e90%2Fclient-ai-manager-mask-type-dropdown.png?alt=media" alt="Model Settings panel with the Input Mask Type dropdown open, showing Inclusive and Exclusive options"><figcaption><p>Choosing the Inclusive mask type</p></figcaption></figure>

Click inside the mask's shape field to open the figure editor and draw the mask over the frame:

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-8222dd9bdd4089720e32b860c10c323599a4e47c%2Fclient-inclusive-mask-figure-editor-shape-drawn.png?alt=media" alt="Figure editor dialog with an orange polygon shape drawn over part of a forest camera image, resize handles visible"><figcaption><p>Drawing an inclusive mask shape in the figure editor</p></figcaption></figure>

Click **OK** to save the shape. A thumbnail preview appears in the mask's shape field, with a **Display on video** checkbox to show the mask as an overlay in Live View. Add more masks with the **Add** button.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-33b9fed6fbec6a1910898b12f33dc2b5d6dad343%2Fclient-ai-manager-model-settings-inclusive-mask-preview.png?alt=media" alt="Model Settings panel showing a completed inclusive input mask thumbnail, an orange polygon shape drawn over part of the camera image"><figcaption><p>Input Masks setting with an inclusive input mask</p></figcaption></figure>

Confirm it in Live View: only detections inside the polygon are returned.

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-6fef05039f6ec983cd88a183085d1dc18228750d%2Fclient-live-view-inclusive-input-mask-overlay.png?alt=media" alt="Live View showing an orange inclusive mask polygon over part of the frame, with only the people inside the polygon detected and labeled"><figcaption><p>Inclusive mask overlay in Live View</p></figcaption></figure>

In practice, results overlap the polygon borders slightly because the anchor location for a detected object is the middle of the bottom of the detection box.

{% hint style="info" %}
The center of the bottom of the bounding box is chosen for the anchor location because that is usually a good indication for where a person or object is standing on the ground. In a line-crossing scenario for example, this would make it easier to detect if a person crosses a certain line.
{% endhint %}

{% hint style="warning" %}
Using an input mask and a region of interest at the same time is not supported.
{% endhint %}

Click **Apply** for changes to take effect.