Number plates recognised by Arduino and EdgeImpulse

This project, described on Medium, is a tinyML-based number plate recognition system, built using Arduino, OpenMV and EdgeImpulse (supporting machine learning models for embedded devices). For hardware, we’re talking Nicla Vision, a Giga R1 WiFi board and a Giga Display Shield…

Full disclosure – this is for recognising EU and Swiss style plates. That’s what the Edge Impulse model will be able to inference.

The Gadget Master in question, Leonardo Cavagnis, is a firmware engineer at Arduino, so he definitely knows his onions.

As mentioned, the hardware system is made up of three main nodes. The Nicla Vision node looks after image acquisition and number plate recognition, using an ML model created with Edge Impulse.

The captured number plate type data is then transmitted to the Giga R1 WiFi board. As well as handling the data from the Nicla Vision, this supports communication with the Arduino IoT Cloud to manage the remote dashboard and also controls the display on local dashboards.

Finally, the Giga Display Shield, which is the display component connected to the Giga R1 WiFi board, for local visualisation of the dashboard.

On the AI side of things, EdgeImpulse enables developers to create, train, and deploy machine learning models directly onto Arduino, and other Edge hardware, i.e. low-power MCUs. (Note that this is a paid-for service, although there is an Edge Impulse 14-day free Enterprise trial.)

Leonardo also covers the dashboards, both local and remote, involving the Giga Display shield and the Arduino Cloud. When it comes to the GUI, for example, he writes:

“The graphical user interface is managed by the Giga Display Shield, which displays a local dashboard showing the recognized license plate type. The display management is controlled by the Arduino_GigaDisplay_GFX library.”

“The Arduino_GigaDisplay_GFX is a library built on top of the Adafruit_GFX library. It provides functions for drawing individual pixels, lines, rectangles, and other geometrical shapes. Additionally, it supports printing numeric values and strings.”

You can read the full details of the number plates system on this Medium post.

[Via twitter: @arduino]

See also: Arduino Alvik robot system rolls into action