Pixy2 Camera - Image Recognition for Arduino & Raspberry Pi

Check out the Pixy2, a smart camera with image recognition capabilities!

The Pixy2 is a low cost yet powerful camera that is capable of object recognition, line tracking, and simple barcode reading. The device is the latest iteration of the Pixy Cam, a project built by Charmed Labs in conjunction with the Robotics Institute at Carnegie Mellon University.

With a variety of interfaces and lots of code libraries and samples, the Pixy2 can be used with an Arduino, Raspberry Pi, Beaglebone Black, or just about any computer, microcomputer, or microcontroller.

In this video, I will show you how the Pixy2 works, how to hook it up, and how to train it using software called PixyMon which runs on Windows, Linux, and Mac OS X. I’ll then show you how to easily hook up your Pixy2 to an Arduino and run code to detect an object, lines, intersections, and simple barcodes.

Thanks to its onboard processor the coding for Pixy2 is very simple. It provides a very easy method of adding vision to your next Arduino or Raspberry Pi project.

Here is the table of contents for this video:

00:00 - Introduction
02:18 - Pixy2 Introduction
05:53 - Pixy2 Unboxing
08:02 - Using PixyMon
14:01 - Color Signature Training
20:32 - Arduino Hookup
21:48 - CCC Hello World Demo
27:44 - Line Tracking Intro
29:24 - Line Hello World Demo

As always there is a detailed article on the DroneBot Workshop website.

[벼락부자-en]

I am Korean.
I can't speak English.
But I am still listening and listening hard.
Thank you very much.

[tly]

you are a high school teacher that I've never had. Thank you!

[swapshots]

I just tore apart my Blade 350QX which has no6 been able to bind since I crashed it. I have decided to build another, which led me to you, which led me to Arduino. My first kits should be in mailbox tomorrow and you will be in my daily routine. Thankyou for your concise content.!

[MrJos]

I love the way you explain each introduction it makes me more confident in learning arduino.

[MysticDreamer]

This is a great device for robotics! Thanks for making a video on it. I'll definitely be getting some of these for my robots. I especially like the barcode feature as those can be used to make certain the robot knows which room it's in for certain, etc. Thanks Bill.

[joeritchey]

Great video! We’ll explained!! Also, I love the fight that you’re having with keeping your hands from moving around. Please keep the videos coming.

[johnroe]

Another brilliant vid. I think you are an amazing teacher. Wish i had teachers like you when I was at school and college 60 years ago.

[Ninjamstrboy]

Awesome content! Please do a video on your workshop! It looks super organized and well stocked.

[DavidFernandez-bgmv]

This man is a legend, I would like him to be my teacher. plz never stop your videos!!

[infinytower]

You are one huge treasure trove on the YouTube planet! Thanks a lot for providing invaluable learning tools!

[rickrose]

This tutorial is awesome. Your tutorials just keep getting better and better, & I'm learning a lot.

[realhusky]

Thank you for taking the time to put together really clear and easy to understand content!

[fabiolsmineiro]

I was thinking about buying this camera, so, i decided watch some videos about, after watching this video i ordered in Amazon. Thanks for this video.

[tohcp]

I always support you . very good detail guide and impressive all presentation and essential info share . I had follow you more than 7 years..if I not wrong

[Reach]

After watching this, I decided that the Pixy2 is mature enough now for my needs.

[davethenerd]

I'm getting into this stuff because I recently went to Disney World and "made" a BB "robot" at the Galaxy's Edge Droid Depot. This thing has zero autonomy and the interactive features are explored in a matter of minutes. Hopefully, I can use what I'm learning here to come up with some worthwhile mods. I'd love to see you rip one apart and experiment with it!

[mechanicpond]

Could you please make a video of your workshop...the kinds of storage options you use and how your workbench and equipment is arranged. It looks super neat.

[featherbrain]

No-one told me that they had brought out version 2! Not nit-picking but when you say "object recognition" at 1:14, the Pixy2 doesn't detect objects any more than the original PixyCMUcam5 did. It recognises only colours, not shapes. The user software would have to process the coordinates to determine shape. The line-following seems to be the biggest advance. I wonder if the detection stability has been improved, but I would have to buy one (which I may) to find out. I have several of the old type which I play with occasionally and seeing this may inspire me to do some more!

[DIYDaveT]

Great video, perfectly understandable even at 1.75x playback speed.  This is amazing tech, probably military grade from 10 years ago.  In other words, bleeding edge to Amazon commodity in a decade.  Just amazing.

[AngryRamboShow]

Was hoping you'd be back in the workshop soon! Always a pleasant show!