Features

The OpenMV camera is a small, low-power, low-cost circuit board that helps you easily complete machine vision applications. You can program using the high-level language Python script (specifically MicroPython) instead of C/C++. The advanced data structures of Python make it easy for you to handle complex outputs in machine vision algorithms. However, you still have full control over the OpenMV. You can easily use external terminals to trigger shooting or execute algorithms, and you can also use the results of the algorithms to control IO pins.

• RT1062-ARM Cortex M7 processor, 600MHz main frequency, external 32MB SDRAM + built-in 1MB SRAM, external 16MB Flash. All I/O pins output 3.3V and are 3.3V tolerant. This processor has the following I/O interfaces:
• • High-speed USB-C (480Mbs) interface, connected to the computer. When the OpenMV camera is inserted, your computer will appear as a virtual COM port and a 'U disk'.
  • • 1.5A current limit.
    • With EMI filtering and TVS protection.
  • μSD card slot with 25MB/s read and write, allowing your OpenMV camera to record video and easily extract machine vision material from the SD card.
  • • With EMI filtering and TVS protection.
• An SPI bus up to 60Mb/s, allowing you to easily transfer image stream data to an LCD expansion board or other controllers.
• An I2C bus (up to 1Mb/s), CAN bus (up to 1Mb/s), and an asynchronous serial bus (TX/RX, up to 20Mb/s) for connecting other controllers or sensors.
• A 12-bit ADC (3.3V tolerant).
• Three I/O pins for servo control.
• One I/O pin for frame sync/trigger (or servo control).
• An onboard RTC that keeps running when the system is in low power mode (system power consumption in low power mode is less than 30uA).
• • One I/O pin for low power wake-up.
  • Another pin for the device power button, supporting ON/OFF.
• All IO ports can be used for interrupts (the board has 14 I/O pins).
• • With EMI filtering and TVS protection.
• A user-controllable/dimmable RGB tricolor LED.
• Another RGB LED for charging, USB power, and VIN power indicators.
• 32M external 16-bit SDRAM, 160 MHz clock, up to 320 MB/s bandwidth.
• 16M external QuadSpi Flash, 133 MHz clock, 4-bit SDR mode up to 66 MB/s bandwidth.
• A 12-bit X/Y/Z accelerometer (2/4/8g) located below the camera module center.
• Onboard WiFi (a/b/g/n – 11/54/65 Mb/s) and Bluetooth (v5.1- BR/EDR/BLE) module with chip antenna.
• • Optional U.FL antenna replacement.
• Onboard 10/100 Mb/s Ethernet.
• • Requires an external PoE-supported Ethernet socket expansion board.
• Strong encryption authentication security element support provided by SE050C1HQ1.
• Detachable camera module system, allowing the OpenMV Cam RT1062 to connect with different sensor modules:
• • The OpenMV Cam RT1062 is configured with the OV5640 sensor by default, processing 2592×1944 (5MP) images. At QVGA (320×240) and below resolutions, most simple algorithms can run at 40FPS. Your OpenMV camera has a 2.8mm focal length lens on a standard M12 lens base. If you want to use more special lenses, you can easily install them.
  • For professional machine vision applications, you can purchase our global shutter camera module mt9V034.
  • For infrared thermal imaging machine vision applications, you can purchase our FLIR Lepton infrared thermal imaging module.
• 3.7V lithium-ion battery interface, supporting battery charging via USB. You can purchase our 3.7V-1000MAH lithium-ion battery.
• • 100mA fast charging current.
  • With TVS protection.
• An ARM 10Pin JTAG interface compatible with SEGGER J-Link devices for debugging and programming.
• • With EMI filtering and TVS protection.
• External 5V VIN with reverse power protection.
• • With TVS protection.

For more information, please visit: https://singtown.com/openmv/

Applications

Currently, the OpenMV camera can be used for the following tasks (more in the future):

• Neural Network Object Detection
• • You can use OpenMV to train neural networks for object detection, training any target you want to detect. For example, different numbers, different fruits, different markers, different parts, or any specific irregular targets can be trained to identify the number, coordinates, and object type name of specific targets.
  • You can detect traffic signs in our actual roads based on our video tutorials, such as no honking, no parking, speed limit 80, etc. /learn/50918
• Neural Network Classification
• • You can use OpenMV to train neural networks for object detection, training any target you want to detect. For example, different numbers, different fruits, different markers, different parts, or any specific irregular targets can be trained to identify the number, coordinates, and object type name of specific targets.
  • It can classify whether a person is wearing a mask based on our video tutorial./learn/50872
• TensorFlow Lite for Microcontrollers
• • TensorFlow Lite support allows you to run custom image classification and segmentation models on the OpenMV Cam. With TensorFlow Lite, you can easily classify complex areas in the picture and control the 1/0 pins based on what you see.
• Frame Differencing Algorithm
• • You can use the frame differencing algorithm on the OpenMV Cam to see the movement in the scene. The frame differencing algorithm can be used for security applications.
• Color Tracking
• • You can use OpenMV to detect up to 16 colors in the image simultaneously (you will never want to find more than 4 colors), and each color can have any number of different color blocks. OpenMV will tell you the position, size, center, and direction of each color block. With color tracking, your OpenMV Cam can be programmed to track the sun, line tracking, target tracking, and more. Video demonstration: /learn/49993
• Marker Tracking
• • You can use the OpenMV Cam to detect groups of colors instead of individual colors. This allows you to place color tags (tags with 2 or more colors) on objects, and OpenMV will get the content of the tag object.
• Face Detection
• • You can use the OpenMV Cam (or any general object) to detect faces. Your OpenMV camera can process Haar templates for general object detection and comes with built-in Frontal Face templates and Eye Haar templates to detect faces and eyes. /learn/50013
• Eye Tracking
• • You can use eye tracking to detect someone's gaze direction. You can use it to control robots. Eye tracking detects the position of the pupil while detecting whether there are eyes in the image.
• Person Detection
• • You can use the built-in person detector (TensorFlow Lite model) to detect whether there are people in the field of view.
• Optical Flow
• • You can use optical flow to detect the scene in front of your OpenMV camera. For example, you can use optical flow on a quadcopter to control stability in the air.
• QR Code Detection/Decoding
• • You can use the OpenMV Cam to read QR codes in its field of view. With QR code detection/decoding, you can enable smart robots to read tags in the environment.
• Data Matrix Detection/Decoding
• • The OpenMV Cam can also detect and decode Data Matrix (2D barcodes). You can watch our video here.
• Linear Barcode Decoding
• • The OpenMV Cam can also handle 1D barcodes. It can decode EAN2, EAN5, EAN8, UPCE, ISBN10, UPCA, EAN13, ISBN13, I25, DATABAR, DATABAR_EXP, CODABAR, CODE39, CODE93, and CODE128. Watch our video here: /learn/50017
• AprilTag Tracking
• • Even better than the QR code above, the OpenMV Cam can also track AprilTags. AprilTags are state-of-the-art fiducial markers that are rotation-invariant, scale-invariant, shear-invariant, and illumination-invariant. Watch our video here: /learn/49590
• Line Detection
• • The OpenMV Cam can quickly complete infinite-length line detection at almost full frame rate. It can also find non-infinite-length line segments. Watch our video here: /learn/50009
• Circle Detection
• • You can easily detect circles in the image using OpenMV.
• Rectangle Detection
• • OpenMV can also detect rectangles, using the square detection code from the AprilTag library.
• Template Matching
• • You can use OpenMV template matching to detect whether there are template-like images in the field of view. For example, template matching can be used to find marks on PCBs or read known numbers on displays.
• Image Capture
• • You can use OpenMV to capture RGB565/grayscale BMP/JPG/PPM/PGM images. You can directly control how to capture images in Python scripts. Most importantly, using machine vision algorithms, you can draw lines, draw characters, and then save them.
• Video Recording
• • You can use the OpenMV camera to record RGB565/grayscale MJPEG videos or GIF images (or RAW videos). You can directly control how each video frame is recorded in Python scripts and have full control over the start and end of video recording. Moreover, like capturing images, you can use machine vision algorithms to draw lines, draw characters, and then save them.

Finally, all the above functions can be mixed with IO pin control to match your custom applications and interact with the real world.