M5Stack UnitV AI Camera

UNIT-V is the new AI Camera powered by Kendryte K210. An edge computing system-on-chip(SoC) with dual-core 64bit RISC-V CPU and state-of-art neural network processor. UNIT-V AI Camera features its integration with machine vision capabilities, featuring the unprocessed acceptability to AI Visioning with high energy efficiency and low cost. M5Stack co-oped with Sipeed providing the MicroPython environment makes programming on UNIT-V easier. It supports MicroPython development environment, which makes the program code more concise when you use UNIT-V for project development.

Equipped with an OV2640 (2 megapixels) image sensor, it is an ideal choice for a machine vision project. It is equipped with two programmable keys and an RGB LED indicator on the front for convenient status display. At the bottom, there is a YH2.0-4P interface and a type-C interface compatible with grove, which is convenient to connect with the main controller. Support TF card to expand the memory, related material, and model file call more convenient.

Note:

1. This unit is actually an add-on unit for M5Stack controllers. The controllers are NOT INCLUDED in the package. However, it is compatible with the following controllers:
   • M5Stack Basic ESP32
   • M5Stack Fire ESP32
   • M5Stack ATOM Matrix ESP32
2. If you're interested to get other M5Stack modules and units in your hands for a lot more fun projects, you may get them here.

Features and specifications:

• Dual-Core 64-bit RISC-V RV64IMAFDC (RV64GC) CPU / 400Mhz(Normal)
• Dual Independent Double Precision FPU
• 8MiB 64bit width On-Chip SRAM
• Neural Network Processor(KPU) / 0.8Tops
• Field-Programmable IO Array (FPIOA)
• AES, SHA256 Accelerator
• Direct Memory Access Controller (DMAC)
• Micropython Support
• Firmware encryption support
• Case Material: PC + ABS
• On-board Hardware resources:
  • Flash: 16M
  • Camera: OV2640
  • Button: button * 2
  • Indicator light: WS2812 LED
  • External storage: TF card/Micro SD
  • Interface: YH2.0/compatible with GROVE
• Kendryte K210: Dual-Core 64-bit RISC-V RV64IMAFDC (RV64GC) CPU / 400Mhz(Normal)
• SRAM: 8Mbit
• Flash: 16M
• Input voltage: 5V @ 500mA
• KPU Neural network parameter size: 5.5MiB - 5.9MiB
• Interface: Type C x 1, GROVE(I2C+I/0+UART) x 1
• RGB LED: WS2812 x 1
• Button: 2
• Image Sensor: OV2640
• FOV: 65deg
• External storage: TF Card/Micro SD
• Net weight: 8g
• Gross weight: 45g
• Product dimension: 40mm * 24mm * 13mm
• Package dimension: 70mm * 50mm * 30mm
• Shell material: Plastic ( PC )

About KENDRYTE K210

The Kendryte K210 is a system-on-chip (SoC) that integrates machine vision. Using TSMC’s ultra-low-power 28-nm advanced process with dual-core 64-bit processors for better power efficiency, stability, and reliability. The SoC strives for ”zero thresholds” development and to be deployable in the user’s products in the shortest possible time, giving the product artificial intelligence

• Machine Vision
• Better low power vision processing speed and accuracy
• KPU high-performance Convolutional Neural Network (CNN) hardware accelerator
• Advanced TSMC 28nm process, temperature range -40°C to 125°C
• Firmware encryption support
• Unique programmable IO array maximizes design flexibility
• Low voltage, reduced power consumption compared to other systems with the same processing power
• 3.3V/1.8V dual voltage IO support eliminates the need for level shifters

The chip contains a high-performance, low power RISC-V ISA-based dual core 64-bit CPU with the following features:

• Core Count： Dual-core processor
• Bit Width: 64-bit CPU 400MHz
• Frequency: 400MHz
• ISA extensions: IMAFDC
• FPU: Double Precision
• Platform Interrupts: PLIC
• Local Interrupts: CLINT
• I-Cache: 32KiB x 2
• D-Cache: 32KiB x 2
• On-Chip SRAM: 8MiB

About OV2640

• Output Formats(8-bit):
  • YUV(422/420)/YCbCr422
  • RGB565/555
  • 8-bit compressed data
  • 8-/10-bit Raw RGB data
• Maximum Image Transfer Rate according to specific format
  • UXGA/SXGA: 15fps
  • SVGA: 30fps
  • CIF: 60fps
• Scan Mode: Progressive
• Camera specifications
  • CCD size: 1/4 inch
  • Field of view: 65 degree
  • Maximium Pixel: 2M

SD card test

UNIT-V does not currently recognize all types of MicroSD cards. Some common SD cards have been tested. The test results are as follows.

Applications:

• Face recognition/detection
• Object detection/classification
• Obtaining the size and coordinates of the target in real-time
• Obtaining the type of detected target in real-time
• Shape recognition
• Video recorder

Packing list:

• 1 x UNIT-V
• 1 x 20cm 4P cable
• 1 x USB-C cable

Resources:

• Product description
• K210 datasheet
• Sipeed web page
• Tutorial & quick start
  • V-Function 
  • V-Training 
  • Maixpy
• Example code