Why we designed Miniature Embedded Machine Vision Module? This is a no frills, fully assembled, and simple to use open source machine vision module designed for applications such as mobile robotic projects. Just power it up with +5V supply, connect to your favorite single-board computer via UART port, send commands to activate the module and it will start to capture and analyze image at 20 frames-per-second.

Design specifications and application
The module contains a CMOS VGA camera, supporting QQVGA and QVGA resolutions. An ARM Cortex-M7 micro-controller (Microchip/Atmel SAMS70 series) provides around 20 frames-per-second video capture and processing speed. Image processing algorithms such as color object detection, line detection, obstacle detection can be performed with this system. The module is fully assembled and comes pre-programmed with a standard executable file but we also share the sample source codes in C so that user can developed their own algorithm to run on the module (A programmer compatible with Atmel Studio is needed).

How to use it?

The module supports two UART ports and one SPI port.

The main UART port (57600 bps) is for interfacing with external controller (such as Arduino or your own robotic controller). Basically the user sends a command to execute a certain image processing algorithm to the module and after processing each image frame the module will report back the result to the external controller, for example the x-y coordinate of the brightest pixel or the average coordinate of pixels that match a color.

Another UART port (115200 bps) is for real-time image dump so that the user can see the image captured by the camera using a free Windows PC software provided (Note that a USB-to-serial converter or HC-05 Bluetooth module, not provided, is needed for this).

The SPI port is currently not supported in current stable release of the firmware, we are currently working on a beta version that can use the SPI port to stream the image to an external TFT LCD display (also not provided), such as this https://www.adafruit.com/product/1480

A demonstration of the machine vision module on a two-wheels robotic platform is shown below.