Have you Ever wanted your microcontroller to sense images without eating up all your processor speed? Or wish that you had an image sensor that wasn’t limited to RGB – but could sense hue and saturation as well? Or just want a kickstarted, open source camera sensor with a cool name? Enter the Pixy 1.0 – an image sensor for your microcontroller that you can teach what to look for.
The Pixy 1.0 Smart Vision Sensor-Object Tracking Camera is an image sensor with a powerful processor that you can program to only send the information you’re looking for so your microcontroller isn’t overwhelmed by data. The Pixy CMUCam also exports its information in a variety of useful ways – UART serial, SPI, I2C, digital out, or analog out – so your microcontroller can communicate easily while still doing other tasks. It’s so unobtrusive that you can even hook up multiple Pixy CMUCams to one microcontroller!
The Pixy 1.0 also uses hue and saturation as its primary means of image detection – rather than the normal RGB. This means that lighting or exposure won’t affect the Pixy CMUCam’s detection of an item – which is a frustrating problem with many image sensors. It’s also a vast improvement over previous versions of the Pixy CMUCam, adding increased flexibility when it comes to lighting and exposure changes.
It can also remember seven different color signatures, find hundreds of objects at the same time, and is super fast – processing at 50 frames a second. Finally, the Pixy CMUCam is also teachable so you can set it up to only send you images that you’ve specifically told it to look for. It’s easy and fast and has an open source application called PixyMon.
Image sensors are used because they are so flexible. With the right algorithm, an image sensor can sense or detect practically anything. But there are two drawbacks with image sensors: 1) they output lots of data, dozens of megabytes per second, and 2) processing this amount of data can overwhelm many processors. And if the processor can keep up with the data, much of its processing power won’t be available for other tasks.
Pixy addresses these problems by pairing a powerful dedicated processor with the image sensor. Pixy processes images from the image sensor and only sends the useful information (e.g. purple dinosaur detected at x=54, y=103) to your microcontroller. And it does this at the frame rate (50 Hz). The information is available through one of several interfaces: UART serial, SPI, I2C, digital out, or analog out. So your Arduino or other microcontrollers can talk easily with Pixy and still have plenty of CPU available for other tasks.
It’s possible to hook up multiple Pixies to your microcontroller — for example, a robot with 4 Pixies and 360 degrees of sense. Or use Pixy without a microcontroller and use the digital or analog outputs to trigger events, switches, servos, etc.
- Small, fast, easy-to-use, low-cost, readily-available vision system
- Learns to detect objects that you teach it
- Outputs what it detects 50 times per second
- Connects to Arduino with an included cable. Also works with Raspberry Pi, BeagleBone, and similar controllers
- All libraries for Arduino, Raspberry Pi, etc. are provided
- C/C++ and Python are supported
- Communicates via one of several interfaces: SPI, I2C, UART, USB or analog/digital output
- Configuration utility runs on Windows, MacOS, and Linux
- All software/firmware is open-source GNU-licensed
1 x Pixy 1.0 Smart Vision Sensor-Object Tracking Camera
1 x Connecting IDC Cable
1 x Mounting Accessories