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, this AI camera is committed to bringing users a simple and efficient AI development experience out of the box.
- Sigmstar SSD202D
- Dual Cortex-A7 1.2GHz Processor
- 128MB DDR3
- 512MB NAND Flash
- GC2145 1080P Colored Sensor
- Wi-Fi 2.4GHz
- 1 x M5Stack UnitV2
- 1 x 16g TF Card
- 1 x USB-C Cable (50cm)
- 1 x Stand
- 1 x Back Brick
- AI recognition function development
- Industrial visual identification sorting
- Machine vision learning
UNIT-V2 series comparison
|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
|Dual Cortex-A7 1.2GHz Processor
|GC2145 1080P Colored Sensor
|FOV 68° , DOF= 60cm- ∞
|5V @ 500mA
|TypeC x1, UART x1, TFCard x1, Button x1, Microphone x1, Fan x1
|150Mbps 2.4GHz 802.11 b/g/n
|0°C to 60°C
|Plastic ( PC )
LEARN AND DOCUMENTS
I bought this to test edge ml applications. But it comes with limitations.
I have not found a path to upload my own library to be used for my own python script without involving a third party . Library training appears to be Locked to either an online m5 stack or another vender. Most likely ok for an enthusiast learning ml or wanting to play around in general.
The standalone AI Camera for Edge Computing (SSD202D) TinyML.
M5Stack UnitV2 - The standalone AI Camera for Edge Computing (SSD202D) TinyML
Everything worked without problems. But I found the documentation a bit confusing especially for a Linux user