The OpenMV Cam is a small, low power, microcontroller board which allows you to easily implement applications using machine vision in the real-world. You program the OpenMV Cam in high level Python scripts (courtesy of the MicroPython Operating System) instead of C/C++. This makes it easier to deal with the complex outputs of machine vision algorithms and working with high level data structures. But, you still have total control over your OpenMV Cam and its I/O pins in Python. You can easily trigger taking pictures and video on external events or execute machine vision algorithms to figure out how to control your I/O pins.
The OpenMV Cam features:
- The STM32H743VI ARM Cortex M7 processor running at 480 MHz with 1MB SRAM and 2MB of flash. All I/O pins output 3.3V and are 5V tolerant. The processor has the following I/O interfaces:
- A full speed USB (12Mbs) interface to your computer. Your OpenMV Cam will appear as a Virtual COM Port and a USB Flash Drive when plugged in.
- A μSD Card socket capable of 100Mbs reads/writes which allows your OpenMV Cam to take pictures and easily pull machine vision assets off of the μSD card.
- A SPI bus that can run up to 80Mbs allowing you to easily stream image data off the system to either the LCD Shield, the WiFi Shield, or another microcontroller.
- An I2C Bus (up to 1Mb/s), CAN Bus (up to 1Mb/s), and an Asynchronous Serial Bus (TX/RX, up to 7.5Mb/s) for interfacing with other microcontrollers and sensors.
- A 12-bit ADC and a 12-bit DAC.
- Three I/O pins for servo control.
- Interrupts and PWM on all I/O pins (there are 10 I/O pins on the board).
- And, an RGB LED and two high power 850nm IR LEDs.
- A removable camera module system allowing the OpenMV Cam H7 to interface with different sensors:
- The OpenMV Cam H7 comes with a MT9M114 image sensor is capable of taking 640x480 8-bit Grayscale images or 640x480 8-bit BAYER images at 40 FPS when the resolution is above 320x240 and 80 FPS when it is below. Most simple algorithms will run between 40-80 FPS on QVGA (320x240) resolutions and below. Your image sensor comes with a 2.1mm lens on a standard M12 lens mount. If you want to use more specialized lenses with your image sensor you can easily buy and attach them yourself.
- For professional machine vision applications you can buy our Global Shutter Camera Module.
- For thermal machine vision applications OpenMV offers the FLIR Lepton Adapter Module.
- A LiPo battery connector compatible with 3.7V LiPo batteries commonly sold online for hobbyist robotic applications.
For more information about the OpenMV Cam please see our documentation.
The OpenMV Cam comes built-in with an RPC (Remote Python/Procedure Call) library which makes it easy to connect the OpenMV Cam to your computer, a SBC (single board computer) like the RaspberryPi or Beaglebone, or a microcontroller like the Arduino or ESP8266/32. The RPC Interface Library works over:
- Async Serial (UART) - at up 7.5 Mb/s.
- I2C Bus - at up to 1 Mb/s.
- SPI Bus - at up to 80 Mb/s.
- CAN Bus - at up to 1 Mb/s.
- USB Virtual COM Port (VCP) - at up to 12 Mb/s.
- WiFi using the WiFi Shield - at up to 12 Mb/s.
With the RPC Library you can easily get image processing results, stream RAW or JPG image data, or have the OpenMV Cam control another Microcontroller for lower-level hardware control like driving motors.
OpenMV provides the following libraries for interfacing your OpenMV Cam to other systems below:
The OpenMV Cam can be used for the following things currently (more in the future):
- TensorFlow Lite for Microcontrollers Support
- TensorFlow Lite support lets you run custom image classification and segmentation models on board your OpenMV Cam. With TensorFlow Lite support you can easily classify complex regions of interest in view and control I/O pins based on what you see. See the TensorFlow module for more information.
- The OpenMV Cam features Edge Impulse integration for easy training of TensorFlow Lite Models in the cloud. Using OpenMV IDE and Edge Impulse you can easily train a Model in 15 minutes! Here's a video showing how it works.
- Frame Differencing
- You can use Frame Differencing on your OpenMV Cam to detect motion in a scene by looking at what's changed. Frame Differencing allows you to use your OpenMV Cam for security applications. Checkout the video of the feature here.
- Color Tracking
- You can use your OpenMV Cam to detect up to 16 colors at a time in an image (realistically you'd never want to find more than 4) and each color can have any number of distinct blobs. Your OpenMV Cam will then tell you the position, size, centroid, and orientation of each blob. Using color tracking your OpenMV Cam can be programmed to do things like tracking the sun, line following, target tracking, and much, much, more. Video demo here.
- Marker Tracking
- You can use your OpenMV Cam to detect groups of colors instead of independent colors. This allows you to create color makers (2 or more color tags) which can be put on objects allowing your OpenMV Cam to understand what the tagged objects are. Video demo here.
- Face Detection
- You can detect Faces with your OpenMV Cam (or any generic object). Your OpenMV Cam can process Haar Cascades to do generic object detection and comes with a built-in Frontal Face Cascade and Eye Haar Cascade to detect faces and eyes. Video demo here.
- Eye Tracking
- You can use Eye Tracking with your OpenMV Cam to detect someone's gaze. You can then, for example, use that to control a robot. Eye Tracking detects where the pupil is looking versus detecting if there's an eye in the image.
- Person Detection
- You can detect if there's a person in the field of view using our built-in person detector TensorFlow Lite model. Video demo here.
- Optical Flow
- You can use Optical Flow to detect translation of what your OpenMV Cam is looking at. For example, you can use Optical Flow on a quad-copter to determine how stable it is in the air. See the video of the feature here.
- QR Code Detection/Decoding
- You can use the OpenMV Cam to read QR Codes in it's field of view. With QR Code Detection/Decoding you can make smart robots which can read labels in the environment. You can see our video on this feature here.
- Data Matrix Detection/Decoding
- The OpenMV Cam H7 can also detect and decode data matrix 2D barcodes too. You can see our video on this feature here.
- Linear Barcode Decoding
- The OpenMV Cam H7 can also decode 1D linear bar codes. In particular, it can decode EAN2, EAN5, EAN8, UPCE, ISBN10, UPCA, EAN13, ISBN13, I25, DATABAR, DARABAR_EXP, CODABAR, CODE39, CODE93, and CODE128 barcodes. You can see our video on this feature here.
- AprilTag Tracking
- Even better than QR Codes above, the OpenMV Cam H7 can also track AprilTags at 160x120 at up to about 12 FPS. AprilTags are rotation, scale, shear, and lighting invariant state-of-the-art fidicual markers. We have a video on this feature here.
- Line Detection
- Infinite line detection can be done speedily on your OpenMV Cam at near max FPS. And, you can also find non-infinite length line segments too. You can see our video of this feature here. Additionally, we support running linear regressions on the image for use in line following applications like this DIY Robocar.
- Circle Detection
- You can use the OpenMV Cam H7 to easily detect circles in the image. See for yourself in this video.
- Rectangle Detection
- The OpenMV Cam H7 can also detect rectangles using our AprilTag library's quad detector code. Checkout the video here.
- Template Matching
- You can use template matching with your OpenMV Cam to detect when a translated pre-saved image is in view. For example, template matching can be used to find fiducials on a PCB or read known digits on a display.
- Image Capture
- You can use the OpenMV Cam to capture up to 640x480 Grayscale/RGB565 BMP/JPG/PPM/PGM images. You directly control how images are captured in your Python script. Best of all, you can preform machine vision functions and/or draw on frames before saving them.
- Video Recording
- You can use the OpenMV Cam to record up to 640x480 Grayscale/RGB565 MJPEG video or GIF images (or RAW video). You directly control how each frame of video is recorded in your Python script and have total control on how video recording starts and finishes. And, like capturing images, you can preform machine vision functions and/or draw on video frames before saving them.
Finally, all the above features can be mixed and matched in your own custom application along with I/O pin control to talk to the real world.
Schematic & Datasheets
||ARM® 32-bit Cortex®-M7 CPU
w/ Double Precision FPU
480 MHz (1027 DMIPS)
Core Mark Score: 2400
(compare w/ Raspberry Pi 2: 2340)
512KB Frame Buffer/Stack
256KB DMA Buffers
128KB Embedded Flash Drive
|Supported Image Formats
JPEG (and BAYER)
|Maximum Supported Resolutions
Grayscale: 640x480 and under
RGB565: 320x240 and under
Grayscale JPEG: 640x480 and under
RGB565 JPEG: 640x480 and under
||Focal Length: 2.1mm
HFOV = 60.7°, VFOV = 47.5°
IR Cut Filter: 650nm (removable)
||All pins are 5V tolerant with 3.3V output. All pins can sink or source up to 25mA. P6 is not 5V tolerant in ADC or DAC mode. Up to 120mA may be sinked or sourced in total between all pins. VIN may be between 3.6V and 5V. Do not draw more than 250mA from your OpenMV Cam's 3.3V rail.
|Idle - No μSD Card
||110mA @ 3.3V
|Idle - μSD Card
||110mA @ 3.3V
|Active - No μSD Card
||160mA @ 3.3V
|Active - μSD Card
||170mA @ 3.3V
||-40°C to 125°C
||-20°C to 70°C
|Country of Origin