UnitV2-M12
Quick Start
- Built-in recognition function tutorial
- V-Training online AI model training service
- Jupyter Notebook Development Tutorial/Example
- SSH connection & WIFI configuration
- Firmware Update Tutorial
Description
UnitV2 is a high-efficiency AI recognition module from M5Stack, It adopts Sigmstar SSD202D (integrated dual-core Cortex-A7 1.2GHz processor) control core, integrated 128MB-DDR3 memory, 512MB NAND Flash, 1080P camera. Equipped with 1x regular focal length (FOV: 85°) + 1x wide-angle fisheye lens (FOV: 150°) two M12 general specifications lenses, support manual focus adjustment. Embedded Linux operating system, integrated with rich hardware and software resources and development tools brings you a simple and efficient AI development experience right out of the box!
Features
- Sigmstar SSD202D
- Dual-core Cortex-A7 1.2GHz processor
- 128MB DDR3
- 512MB NAND Flash
- GC2053 1080P Colored Sensor
- Equipped with dual lenses: regular focal length (FOV: 85°) + wide-angle fisheye lens (FOV: 150°)
- Built-in microphone
- Wi-Fi 2.4GHz
- Development method:
- Equipped with 12 ways AI image functions: QR code, face detection, line tracking, movement, shape matching, image streaming, classification, color tracking, face recognition, target tracking, shape detection, custom object recognition
- Support web online preview, UIFlow (used as serial port json format)
- Linux system (OpenCV, SSH, JupyterNotebook)
Include
- 1 x M5Stack UnitV2 M12
- 1 x 16g TF Card
- 1 x USB-C cable (50cm)
- 1 x bracket
- 1 x back clip
- 1x regular focal length lens (FOV: 85°)
- 1x wide angle fisheye lens (FOV: 150°)
Applications
- AI recognition function development
- Industrial visual recognition classification
- Machine vision learning
UNIT-V2 series comparison
| Spec | UNIT-V2 | UNIT-V2 M12 | UNIT-V2 USB |
|---|---|---|---|
| Lens equipment | Normal focal length (FOV 68°) | Normal focal length (FOV 85°) + wide-angle focal length (FOV: 150°) | Without lens, USB-A universal interface, can be connected to various UVC cameras |
| CMOS | GC2145 | GC2053 | / |
Specifications
| Specifications | Parameters |
|---|---|
| Sigmstar SSD202D | Dual Cortex-A7 1.2GHz Processor |
| Flash | 512MB NAND |
| RAM | 128MB-DDR3 |
| Camera | GC2053 1080P Colored Sensor |
| Lens | 1x regular focal length (FOV: 85°) + 1x wide-angle fisheye lens (FOV: 150°) |
| Input voltage | 5V @ 500mA |
| Hardware Peripherals | TypeC x1, UART x1, TFCard x1, Button x1, Microphone x1, Built-in active cooling fan x1 |
| Indicator light | Red, White |
| Wi-Fi | 150Mbps 2.4GHz 802.11 b/g/n |
| Ethernet network card | SR9900 |
| Package Size(with lens） | 48 * 24 * 32mm |
Driver Installation
Download the corresponding SR9900 driver according to the operating system used.
Windows10
Extract the driver compressed package to the desktop path -> Enter the device manager and select the currently unrecognized device (named with SR9900) -> Right-click and select Custom Update -> Select the path where the compressed package is decompressed -> Click OK and wait for the update carry out.
MacOS
Unzip the driver package -> double-click to open the SR9900_v1.x.pkg file -> follow the prompts and click Next to install. (The compressed package contains a detailed version of the driver installation tutorial pdf)
- After the installation is complete, if the network card cannot be enabled normally, you can open the terminal and use the command below to re-enable the network card.
sudo ifconfig en10 down
sudo ifconfig en10 up
Schematics
Out Of The Box AI Recognition Function
UnitV2 integrates not only the basic AI recognition developed by M5Stack, but also has built-in multiple recognition (such as face recognition, object tracking and other common functions), which can quickly help users build AI recognition applications.
All features! Plug and play! UnitV2 has a built-in wired network card. When you connect to a PC through the TypeC interface, it will automatically establish a network connection with UnitV2.Flexibly Connectable, it can also be connected and debugged via Wi-Fi.
UART serial port output, all identification content is automatically output in
JSONformat through the serial port for convenient use.
Development Efficiency Improvement
UnitV2's factory setting Linux image integrates a variety of basic peripherals and development tools (such as Jupyter Notebook etc.)
Through SSH access, you can fully control the hardware resources of this camera
Easily build a custom recognition model through M5Stack's V-Training (AI model training service).
Video
UnitV2 Built-in functions out of the box
UnitV2 Applications