We take cryptocurrency — so the coins you hold can buy real hardware.Pay in crypto, spend it on real hardware. Free insured shipping worldwide over $399. Plain, unbranded boxes, sent from Germany.Free insured shipping over $399. Your rate is locked for 30 minutes once checkout opens.Rate locked 30 minutes. Every item sealed, serial-checked and covered by a 24-month warranty.Sealed, 24-month warranty.

Saved items Sign in

Seeed Studio

Seeed Studio Pixy2 CMUcam5 Smart Vision Sensor

SKU CH-6J57-8717M

A 60 frames-per-second smart vision sensor that learns objects, tracks lines, reads barcodes and connects to Arduino or Raspberry Pi via multiple interfaces

  • TypeSensors
  • Processes 60 frames per second for real-time object tracking
  • Remembers seven colour signatures to identify hundreds of objects simultaneously
  • Teaches new objects with a single button press
  • Detects lines, intersections and barcodes without a host computer
  • Connects via SPI, I2C, UART, USB or analog/digital output

Vision sensor for robotics

The Pixy2 CMUcam5 is a compact smart vision sensor designed for makers and students building autonomous robots or computer-vision projects. It processes images on board at 60 frames per second and can track hundreds of objects or follow lines without burdening the host microcontroller. The sensor learns up to seven colour signatures with a single button press and reports only the data you request. It suits hobbyists who need fast, self-contained object detection for Arduino or Raspberry Pi platforms.

Multi-interface connectivity

The board exposes SPI, I2C, UART, USB and analog or digital outputs so you can wire it directly to almost any microcontroller or single-board computer. A configuration utility runs on Windows, macOS and Linux for firmware updates and parameter tuning. All firmware and hardware documentation are open source under a GNU licence, allowing full customisation of detection algorithms. Builders who require wireless streaming or built-in display outputs will need additional hardware.

On-board processing thermals

Because image processing runs on the integrated microprocessor, the sensor handles detection, line tracking and barcode reading internally while drawing power from the host USB or logic supply. No external cooling is required for typical indoor robotics use. The compact form factor fits tight chassis spaces, though users planning continuous high-frame-rate operation in sealed enclosures should verify thermal margins themselves.

Highlights

  • Processes 60 frames per second for real-time object tracking
  • Remembers seven colour signatures to identify hundreds of objects simultaneously
  • Teaches new objects with a single button press
  • Detects lines, intersections and barcodes without a host computer
  • Connects via SPI, I2C, UART, USB or analog/digital output

Specifications

TypeSensors

Questions about this item

Which communication interfaces does the Pixy2 CMUcam5 support for sending object data to a microcontroller?

It can output data over SPI, I2C, UART, USB, or analog and digital pins, so you can connect it directly to Arduino, Raspberry Pi, or other boards.

What physical connections and mounting options does the Pixy2 CMUcam5 require to fit into a project?

It uses a standard 10-pin IDC header for power and data, includes mounting holes on the PCB, and is smaller than the original Pixy for tighter spaces.

How is the Pixy2 CMUcam5 taught to recognise a new object, and what is the common mistake to avoid?

Hold the object in view and press the top button until the LED changes colour; the mistake is releasing the button too early before the colour signature is saved.

Also in this aisle

People compared these

Same shelf, same checkout — eight coins and a 30-minute rate lock.