> 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-models-support/default-models/people-vehicles-high.md).

# People and Vehicles (High)

Input and output format for the default People and Vehicles Detection (High Accuracy) demo model.

This AI model is based on YOLOX (Medium), a convolutional detector, trained to detect people and vehicles in a given image. It is the most reliable of the three variants: it gives few false detections, so alerts can be trusted, but it can miss small or distant objects. It is also the largest and needs the most computing power. Use it on devices with a GPU that serve a few important cameras, when reliable detections matter more than frame rate.

The other variants of this model are: [Low](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-models-support/default-models/people-vehicles-low.md), [Medium](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-models-support/default-models/people-vehicles-medium.md). They share the same classes and output format and differ in model family, input resolution, accuracy and speed.

## Detected Classes

* Person
* Bicycle
* Car
* Motorcycle
* Bus
* Train
* Truck

## Input

The input tensor dimension for this model is 640 wide by 640 high.

This model accepts the following extra input information:

* Sensitivity threshold: detection confidence threshold.

## Output

Each detected object is identified using a bounding box represented by a vector: \[x1, y1, x2, y2, score, class]. The object bounding boxes contain the following information:

* Position and size coordinates, to be used as a rectangular bounding box.
* A confidence score, which helps retain only the most confident and accurate detections while suppressing weaker or redundant ones.
* Class, a textual string of the main category the detected object belongs to.

The following image shows an example of this model's output:

<figure><img src="https://2982163321-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FKGfC0TFSmuMDjbpLErO3%2Fuploads%2Fgit-blob-f0daa51b4fb5060b7de635d9014ac12aa1d78082%2Fmodel-vehicle-detection.png?alt=media" alt="Camera view with bounding boxes labeling cars, motorcycles, and people in traffic"><figcaption><p>Example people and vehicles detection output in the desktop client</p></figcaption></figure>

## Postprocessors

This model's detections can be combined with any of the built-in postprocessors, for example:

* [Loitering Detection](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/postprocessors/loitering-detection.md): detect when an object stays in frame longer than a configured time threshold.
* [Left Behind Object Detection](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/postprocessors/left-behind-object-detection.md): detect objects left behind or removed compared to a reference frame.
* [Line Crossing Detection](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/postprocessors/line-crossing-detection.md): detect or count objects that cross a defined line, and generate an event.
* [Object Counting](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/postprocessors/object-counting.md): count bounding boxes per class and generate a counting event.

See [Postprocessors](https://nx.docs.scailable.net/ai-manager-v6.1.4/ai-manager-plugin/configure-the-plugin/postprocessors.md) for the full list and configuration details.
