The Pixy CMUcam5 is a remarkably fast image sensor that can be taught to find objects of various shapes, sizes and colors. With the ability to track hundreds of objects simultaneously, Pixy can be used in robotics, home automation, color coding and more, while only providing you with the information you really want. Pixy is really a fast and easy-to-use vision system, equipped with a dedicated NXP LPC4330 processor that allows you to handle large amounts of data from your image sensor and process it quickly, while generating what it detects 50 times per second.
Pixy processes Image sensor images and only send useful information to your microcontroller, making it at 50 frames per second. This means that each Pixy CMUcam5 processes a complete picture frame of 640x400 every 1/50 of a second (20 milliseconds). The information is available through one of several interfaces: UART series, SPI, I2C, USB or digital / analog output. So your Arduino, Raspberry Pi, BeagleBone or another microcontroller can easily talk to Pixy and still have enough CPU available for other tasks you need them to do
Pixy uses a color-based filtering algorithm to detect objects. Color-based filtering methods are popular because they are fast, efficient and relatively solid. Pixy calculates the hue and saturation of each RGB pixel of the image sensor and uses them as primary filtering parameters. The tone of an object remains unchanged with changes in lighting and exposure. Changes in lighting and exposure can have a frustrating effect on color filtering algorithms, causing them to break. Pixy's filtering algorithm is robust when it comes to lighting and exposure changes.
https://docs.pixycam.com/wiki/doku.php?id=wiki:v2:pixy_regular_quick_start
NXP processor LPC4330, 204 MHz, dual core
RAM memory: 264Kb
Consumption: 140mA
Omnivision OV9715, 1/4 ", 1280x800 image sensor • Viewing angle: 75 degrees horizontal, 47 degrees vertical
Recognition single image - Press the button and Pixy will learn to recognize an object
Simplification of programming: Receive only the objects you want to detect
Use your favorite controller: Available libraries for Arduino, Raspberry Pi and BeagleBone Black.
Ports communication: SPI, I2C, UART, USB or analog / digital output
The software works on Windows, MacOS and Linux
Dimensions (without IDC cable, without screws): 50 mm x 54 mm x 2 mm
Height of the chamber: 25 mm
Front two holes: 19mm
A after two holes: 47mm
Weight (without IDC cable, without screws): 25.5 g