CMUcam Pixy Explained

What is Pixy?

Pixy is a fully open source embedded camera that has a dual core ARM processor, USB/I2C/UART/SPI communication, and built-in computer vision algorithms. Pixy, also known as the CMUcam5, is the 5th revision of the CMUcam, started by Anthony Rowe of Carnegie Mellon University. Pixy was developed jointly by Carnegie Mellon and Charmed Labs, starting in 2012.

Why is Pixy useful?

The main feature of Pixy is its color trainer and tracker. It's capable of creating a statiscial model of an object's color, which then allows the camera to report the location of all objects in view that matches that color model. Then using one of the many communication mediums you can interface with the camera and receive location data for tracked objects at up to 50 times per second. This simplicity makes the camera extremely easy to use and perfect for just about any tracking application.

Additionally, everything about Pixy is open source, which means you can view and modify all of the source files (both hardware and software) as much as you'd like. This also means you can benefit from other people's changes/additions to the project, so Pixy's featuers won't just stop at those that it's shipped with, but they'll expand as more people contribute to the project.

How do you use Pixy?

We designed Pixy to be very easy to use out of the box. Simply place a colored object in front of the camera, hold down the push-button, and let go when the color of the LED matches that of the colored object. Doing this will create a statistical model of the object's color, and the camera will start reporting all positions of objects in view that match this color model.

This is just one feature of Pixy, and since it is open source, you can create just about anything on the hardware that drives Pixy. The 204MHz dual core NXP LPC4330 processor is very capable and can be used to accomplish much more than what we're using it for.

As we release more information on Pixy, I'll add it to this page. So check back soon!


Check back here for links to tutorials and additional information.