Carpet detection

This tutorial will walk you through how to use Acconeer’s A121 sensor to determine whether a device is operating on a floor or on a textile carpet. The concept can be integrated in many different devices such as vacuum cleaners or robots to optimize the unit’s performance and operation.

The material provided will guide you through the end-to-end process of collecting data, model development and real-time deployment.

The first part of this tutorial is implemented in a Jupyter notebook. Here you will get more familiar with the overall concepts, feature extraction, compiling and training the classification model and more. Once all the steps are completed and the model ready to go, it can be executed in real-time through a provided script.

If you have not already python installed on your computer, follow the steps in the links below to get up and running with VS Code.

• Download and install Python
• Install VS Code and set it up for python by following this tutorial
• Follow this guide to get started with Jupyter notebooks in VS Code

All the required scripts and pre-recorded data can be downloaded from Acconeer’s Innovation Lab GitHub.

Lastly, you will also need to install Acconeer’s Exploration Tool. To do this, follow the instructions found here.

The following components from Acconeer are required for this tutorial and are available at Digi-Key.

• Acconeer’s XE121 Evaluation Kit
• Acconeer’s XS121 Satellite sensor

You also need a Raspberry Pi, a power bank, and a device to mount the components on. More information on how to get up and running with the hardware can be found in the Jupyter notebook.

If you try this, or work on something else, we’d love to hear about your project! Please get in touch with us on innovation@acconeer.com.