UnitV2

SKU:U078-D

Description

UnitV2 is a high-efficiency AI recognition module launched by M5Stack, featuring the Sigmstar SSD202D (integrated dual-core Cortex-A7 1.2GHz processor) as the control core, integrated with 128MB DDR3 memory, 512MB NAND Flash, and a 1080P camera. It comes with an embedded Linux operating system, rich software and hardware resources, and development tools, aiming to provide users with a plug-and-play, simple, and efficient AI development experience.

Note

Precautions

It is recommended to use the original M5 data cable when connecting to a computer, otherwise, it may cause a crash. Loose data cables may also cause crashes.
It is recommended to use Edge and Chrome browsers, as Firefox may cause freezing or unstable video playback.

Features

Sigmstar SSD202D
Dual-core Cortex-A7 1.2GHz processor
128MB DDR3
512MB NAND Flash
GC2145 1080P Colored Sensor
Built-in microphone
Wi-Fi 2.4GHz

Includes

1 x UnitV2
1 x 16GB microSD card
1 x USB Type-C cable (50cm)
1 x Stand
1 x Back clip

Applications

AI recognition function development
Industrial visual recognition and classification
Machine vision learning

Specifications

Specification	Parameters
Sigmstar SSD202D	Dual Cortex-A7 1.2GHz Processor
Flash	512MB NAND
RAM	128MB-DDR3
Camera	GC2145 1080P Colored Sensor
Lens	FOV 68°, DOF= 60cm- ∞
Input Voltage	5V @ 500mA
Hardware Peripherals	Type-C x1, UART x1, TFCard x1, Button x1, Microphone x1, Fan x1
Indicators	Red, White
Wi-Fi	150Mbps 2.4GHz 802.11 b/g/n
Operating Temperature	0 ~ 60°C

Schematics

Model Size

Softwares

Quick Start

UnitV2 integrates a basic AI recognition service developed by M5Stack, with built-in multiple recognition functions (such as face recognition, object tracking, etc.), which can quickly help users build AI recognition applications.
All functions! Plug and play! UnitV2 has a built-in wired network card. When you connect it to a PC via the Type-C interface, it will automatically establish a network connection with UnitV2. It can also be connected and debugged via Wi-Fi, offering high flexibility.
UART serial output, all recognition content is automatically output in JSON format, making it easy to call.
Built-in Recognition Function Tutorial
V-Training Online AI Model Training Service
Jupyter Notebook Development Tutorial/Example
SSH Connection & WIFI Configuration
Firmware Update Tutorial

SDK

UnitV2Framework

USB Driver

Driver Name	Download Link
SR9900_Windows	Download
SR9900_MacOS	Download

For Windows10

Extract the driver package to the desktop path -> Go to Device Manager and select the currently unrecognized device (named USB 10/100 LAN or containing SR9900) -> Right-click and select custom update -> Select the path where the package was extracted -> Click confirm and wait for the update to complete.

For MacOS

Extract the driver package -> Double-click to open the SR9900_v1.x.pkg file -> Follow the prompts to install. (The package includes a detailed PDF guide for driver installation.)
After installation, if the network card does not work properly, you can open the terminal and use the following commands to re-enable the network card.

sudo ifconfig en10 down
sudo ifconfig en10 up

Other

Object Detection using M5Stack UnitV2 and Edge Impulse

Use the latest Linux AI smart camera UnitV2 from M5Stack to build a simulated industrial application scenario for defective product screening.

Video

UnitV2 Built-in Functions Unboxing and Usage

UnitV2 Application Scenarios

Product Comparison

Specification	UnitV2	UnitV2-M12	UnitV2-USB
Lens Configuration	Standard focal length (FOV 68°)	Standard focal length (FOV 85°) + Wide-angle focal length (FOV 150°)	No lens, USB-A universal interface, supports connection to various UVC cameras
CMOS	GC2145	GC2053	/

To compare information on the UnitV series products, you can visit the Product Selection Table, check the target products, and get the comparison results. The selection table covers key information such as core parameters and functional features, and supports comparison of multiple products simultaneously.