XNOR.ai

XNOR.ai is a company focused in highly-efficient AI processing at the edge, focused at running complex deep learning algorithms locally, on a wide range of devices.

Person Detection Demo

The Person Detection Demo uses USB cameras as video input to which it runs the XNOR.ai inference engine to get person detection coordinates.

Supported Modules

The following Computer on Modules are supported:

• Apalis iMX8

Supported Displays

• HDMI video output

While you can use a wide variety of displays, additional configuration may be required for a specific setup.

A section in the end of this guide provide instructions about display and touch screen configuration.

How to Get Started

You can get the source-code as well as setup instructions from the XNOR.ai sample repository in Toradex Github.

Next Steps

For more information about how to get started with XNOR.ai on Toradex modules get in touch with XNOR.ai.

Display and Touchscreen Configuration

Note: This demo application does not have touch screen interactivity. Only the HDMI output is supported.

Displays and Monitors used in Embedded Systems are available in a myriad of configuration possibilities - resistive, capacitive or without touch, single or multi touch, different resolution, density of pixels, pin-out and clock frequency are some examples.

To make things easy for you, Toradex provides specific instructions on how to use its display offerings as well as comprehensive information about how to interface your custom display or monitor to Toradex modules. Please refer to the table below:

Licensing Information

For more information about licensing get in touch with XNOR.ai.

This sample uses the Boot2Qt image available in Qt for Device Creation from The Qt Company. If you want to use it for commercial purposes, make sure to comply to The Qt Company licensing.