Current Product Don't Have Test Firmware
Note: pls, use PC chrome/edge browser, if can't connect, refresh the webpage.
1. Click connect button
2. After connected successfully, pick a firmware
3. Click the burn button
4. After burning successfully, Unplug the device and restart.
UnitV2
Quick Start
- Built-in recognition function use 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 launched by M5Stack, using Sigmstar SSD202D (integrated dual-core Cortex-A7 1.2GHz processor) control core, integrated 128MB-DDR3 memory, 512MB NAND Flash, and 1080P camera. With embedded Linux operating system and rich software and hardware resources and development tools integrated, UnitV2 is committed to bringing users a simple and efficient AI development experience out of the box.
Product Features
- Sigmstar SSD202D
- Dual Cortex-A7 1.2GHz Processor
- 128MB DDR3
- 512MB NAND Flash
- GC2145 1080P Colored Sensor
- Microphone
- Wi-Fi 2.4GHz
Include
- 1 x M5Stack UnitV2
- 1 x 16g TF Card
- 1 x USB-C Cable (50cm)
- 1 x Stand
- 1 x Back Brick
Applications
- AI recognition function development
- Industrial visual identification sorting
- 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 | / |
Specification
| Resources | Parameter |
|---|---|
| Sigmstar SSD202D | Dual Cortex-A7 1.2GHz Processor |
| Flash | 512MB NAND |
| RAM | 128MB-DDR3 |
| Camera | GC2145 1080P Colored Sensor |
| Lens | FOV 68° , DOF= 60cm- ∞ |
| Power Input | 5V @ 500mA |
| Peripherals | TypeC x1, UART x1, TFCard x1, Button x1, Microphone x1, Fan x1 |
| Indicator light | Red, White |
| Wi-Fi | 150Mbps 2.4GHz 802.11 b/g/n |
| Operating Temperature | 0°C to 60°C |
| Net weight | 18g |
| Product Size | 48*18.5*24mm |
| Package Size | 157*38*38mm |
| Case Material | Plastic ( PC ) |
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
Schematic
Related Link
Out Of The Box AI Recognition Function
UnitV2 integrates not only the basic AI recognition service developed by M5Stack, but also has built-in multiple recognition functions (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. With highly free connectable style, 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, which is convenient to call.
Development Efficiency Improvement
UnitV2's factory 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).
Learn
Video
UnitV2 Built-in functions out of the box
UnitV2 Applications
FAQ
HARDWARE RELATED
Q1: How do I remove the speaker floor noise when the M5Core is on or running?
Execute the following statement in Setup() of the Arduino program
Q2: How does M5Core2 stack modules?
When M5Core2 is stacked with other M5 modules, you need to remove the battery base of Core2, which does not support module stacking.
Q3: A timeout error is displayed when uploading the program to the device
Reason and solution: The power supply current of the port is insufficient, which can cause the device to not enter the download mode normally. You can try to connect a capacitor (>0.1uF) between the RST pin and the GND pin, or when uploading the program, set the G0 Short-circuit to GND, so that G0 can be set to a low level state normally
Q4: How to solve the phenomenon of automatic signal triggering of M5Core button A
Add the header file #include <driver/adc.h> and the function adc_power_acquire(); in the Arduino program
Q5: M5 device battery life
The battery life of the controller is affected by various factors such as battery capacity, operating status, and load, so there is no fixed value. Reducing the load and adopting a sleep strategy can effectively increase the battery life.
Q6: Can multiple modules with batteries be stacked at the same time?
Support multiple stacks, the total capacity of the batteries in parallel increases, and the voltage remains unchanged. However, since the discharge of each battery is not balanced during use, there is a voltage difference between the batteries, which may cause the battery to charge backwards. .(will lose part of the battery capacity)
Q7: M5 master supports WiFi connection to 5G frequency band
ESP32 module currently does not support WiFi in 5G band, only 2.4G.
Q8: The RS485 device cannot communicate normally/data is garbled. Packet loss, etc.
Confirm whether the TX/RX pin on the TTL side of the pin is correct, try to add two 120Ω terminal resistors at the beginning and end of the device line to reduce signal reflection interference
Q9: The difference between different masters and camera products
Click the link below to view the product comparison table
Q10: M5 camera image blur, how to adjust the focal length
Rotate the lens to adjust the focal length within a certain range
Q11: The control RGB LED pin of FACE II BOTTOM conflicts with the I2S DOUT pin of CORE2
FACE II BOTTOM NOT CORE2 COMPATIBLE
SOFTWARE RELATED
Q1: How to read the programmed firmware?
Use esptool to read the flash content of esp32 and export the bin file. Refer to the detailed operation
Q2: Several solutions for esp32 board download failure in Arduino IDE board management
Restart the Arduino IDE, the computer uses the mobile AP mobile network to download.
Q3: Arduino SPIFFS file upload operation
Refer to the Github link below, use arduino-esp32fs-plugin for file upload
Q4: When M5Burner burns firmware, an error pop-up window or exception occurs
Check if the COM of the corresponding device is selected and if the M5Burner is the latest version
Q5: Does the M5 master device support multi-language display (Chinese, English, Japanese, Russian, etc.)?
UIFlow users can switch the Label font to Unicode, Arduino users can use the Chinese font library provided in the M5GFX driver library
Q6: The program cannot load the SD card normally
Confirm whether the SD card format is FAT32, and no partitions exist.
Q7: How to use Bluetooth, HTTP, SD, WebServer, FreeRTOS and other features in Arduino IDE
You can refer to the following link for other ESP32 users to share the case program
Q8: How to download programs for STAMP C3U
STAMP C3U enters program download mode operation: 1. Long press the center button (G9) of STAMP C3U when the power is off. 2. Connect to the computer, after the port is successfully identified, program burning.
Q9: How STAMP C3U defines UART0 output mode
By default, USB CDC is not enabled, the serial port output started by C3U will be output through the default pins (G20, G21) of UART0. If you want to output through USB, please use the IDE to output Its USB CDC option is enabled. (Arduino users can enable it through Tools->USB CDC on Boot-Enabled. For IDF users, please refer to the ESP IDF official documentation.)
Q10: Unable to connect to UIFlow Desktop IDE
Refer to the UIFlow documentation of the corresponding device to check whether the device has entered the USB programming mode.
Q11: NBIoT devices cannot connect to the network normally
Make sure that the NBIoT used is not locked. Frequent device replacement or after activating the IoT card, using traffic in different places may cause the card to be locked. If the above situation occurs, please contact the IoT card supplier. If you are using the IoT card matching M5, please contact M5 after-sales through e-commerce or email. (provide the ICCID of the IoT card)
COMMON
Q1: Consultation for after-sales problems of products
Describe the problems encountered in detail. Screenshots of the programs involved or files can be added as attachments and sent to M5Stack's official after-sales email
Q2: Code Resources, Cases, User Communication
M5Stack related resource links: Official Github