Pixy 2 CMUcam5 Image Sensor

Pixy 2 CMUcam5 Image Sensor

The Sensor of Image Charmed Labs Pixy 2 CMUcam5 is smaller, faster and more capable than the original Pixy. Like its predecessor, Pixy2 can learn to detect objects, just by pressing a button. In addition, Pixy2 has new algorithms that detect and track lines for use with line following robots. The new algorithms can also detect intersections and "traffic signs". Traffic signs can tell your robot what to do, such as turning left, turning right, slowing down, etc.

If you want your robot to perform a task like picking up an object, chasing a ball, locating a charging station, etc., and you want a single sensor to help carry out all these tasks, vision is your trump card. Sensors from Vision (Image) are useful because they are very flexible. With the right algorithm, a Sensor of Image can detect just about anything. But there are two disadvantages with Image Sensors: They produce a lot of data, tens of megabytes per second, and processing that amount of data can tax many processors. And if the processor can keep up with the data, much of its processing power will not be available for other tasks.

The Pixy2 solves these problems by pairing a powerful processor with the Image Sensor. Pixy2 processes images from the Image Sensor and sends only useful information (eg Purple Dinosaur detected at x=54, y=103) to your microcontroller. Information is available through one of several interfaces: Serial UART, SPI, I2C, USB or Digital/Analog Output. So your Arduino or other microcontroller can easily communicate with Pixy2 and still have plenty of CPU available for other tasks.

60 Frames per Second

What does "60 Frames Per Second" mean? It means that Pixy2 is fast. Pixy2 renders an entire frame every 1/60th of a second (16.7 milliseconds). This means you get a complete update of the positions of all detected objects every 16.7ms. At this rate, it is possible to track the path of the falling/rolling ball.

Purple Dinosaurs (And Other Stuff)

Pixy2 uses a color-based filtering algorithm to detect objects called the Color Connected Components (CCC) algorithm. Color-based filtering methods are popular because they are fast, efficient, and relatively robust. Most of us are familiar with RGB (Red, Green and Blue) to represent colors. Pixy2 calculates the Color (Hue) and Saturation of each Image Sensor's RGB pixel and uses them as primary filtering parameters. The hue of an object remains largely unchanged with changes in lighting and exposure. Changes in lighting and exposure can have a frustrating effect on the color filtering algorithms, causing them to break. Pixy2's filtering algorithm is robust when it comes to lighting and exposure changes.

Seven Possibilities

Pixy2's CCC algorithm remembers up to 7 different color possibilities, which means that if you have 7 different objects with unique colors, 's color filtering algorithm Pixy2 you will have no problem identifying them.

PixyMon Lets You See What Pixy Sees

PixyMon is an application that runs on Windows, MacOs and Linux. It lets you see what Pixy sees. It also lets you configure your Pixy, set the output port and manage the colors. PixyMon communicates with Pixy via a standard MiniUSB Cable.

Controller Support

The Pixy can easily connect to many different controllers because it supports various interface options (Serial UART, SPI, I2C, USB or Digital/Analog Output), but the Pixy< /strong> started with Arduinos. In recent times support for Arduino Due, Raspberry Pi and BeagleBone Black has been added.

Features:

• New Features Added to Pixy2:

• Pixy2 Detects Lines, Intersections and Small Barcodes, Intended for Line Following Robots;
• Improved Frame Rate - 60 Frames per Second;
• Tracking Algorithms Added to Detection Based on Color Objects;
• Improved and Simplified Libraries for Arduino, Raspberry Pi and Other Controllers;
• Integrated Light Source.

• Pixy Features:

• Small, Fast, Easy to Use, Low Cost and Readily Available Vision System;
• Learn to Detect Objects;
• Connects to Arduino with Cable Included. 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 Through One of Several Interfaces: SPI, I2C, UART, USB or Analog/Digital Output;
• The Setup Utility Runs on Windows, MacOS and Linux;
• All Software/Firmware is Licensed by GNU Open Source;
• All Hardware Documentation, Including Schematics, Bill of Materials, PCB, Etc, is Provided.

Specifications:

• Lens Type: Standard M12;
• Processor: NXP LPC4330, 204MHz, Dual Core;
• Image Sensor: Aptina MT9M114, 1296x976 Resolution with Integrated Image Stream Processor;
• Lens Field of View: 60 Degrees Horizontal, 40 Degrees Vertical;
• Power Consumption: 140mA Typical;
• Power Input: USB Input (5V) or Non-Regulated Input ( 6V to 10V);
• RAM: 264 KBytes;
• Flash: 2 MBytes;
• Available Data Outputs: Serial UART, SPI, I2C, USB, Digital, Analog;
• Dimensions: 1.5"x1.65"x0.6";
• Weight: 10 Grams;
• Integrated Light Source, Approximately 20 Lumens.

Includes:

• 1x Pixy 2 CMUcam5 Image Sensor.