M5Stack M5StickV K210 AI Camera Development Board with MPU6886 (Gyro + Acc + Base + USB-C Cable)

M5Stick-V RISC-V AI camera

Note: M5StickV does not support the microphone function. This function will be added to the new wifi version M5StickV+. If you need it, you can pay attention to it~

 The M5Stick-V is an AIOT (AI + IOT) camera with Kendrye K210, an edge computing system-on-a-chip (SoC) with dual-core 64-bit RISC-V CPU and state-of-the-art neural network processor.

The M5stickV AI camera has machine vision capabilities, supports multiple visual recognition capabilities (such as real-time acquisition of the size and coordinates of the detected target • real-time acquisition of the type of target being detected), and enables convolutional neural networks with low power consumption. Calculations, so M5StickV would be a good zero-threshold machine vision embedded solution that supports the MicroPython development environment, which makes your code more streamlined when you use the M5stick-V for project development.  

Equipped with the OmniVision OV7740 image sensor and OmniPixel®3-HS technology, it offers the best low light sensitivity compared to best-in-class, ideal for machine vision projects.

Product Features:

• Dual Core 64-bit RISC-V RV64IMAFDC (RV64GC) CPU / 400Mhz (Normal)
• Double precision FPU
• 8MiB 64bit on-chip SRAM
• Neural Network Processor (KPU) / 0.8Tops
• Programmable IO Array (FPIOA)
• Dual hardware 512-point 16-bit complex FFT
• SPI, I2C, UART, I2S, RTC, PWM, Timer Support
• AES, SHA256 accelerator
• Direct Memory Access Controller (DMAC)
• Support for Micropython
• Firmware encryption support
• Onboard hardware resources:
  • Flash: 16M.
  • TFT: ST7789. 135*240 IPS 1.14 SPI
  • Camera: OV7740
  • PCM: MAX98357
  • Power Management IC: AXP192
  • Button: Front and side.
  • Lithium battery: 200mAh.
  • Indicator light: RGBW .
  • External storage: TF card/Micro SD
  • Motion sensor: MPU6886.
  • Interface: CONNEXT.

contain

• M5Stick-V
• Tpye-C USB

Functional description

1.1 KENDRYTE K210

The Kendryte K210 is a system-on-chip (SoC) with integrated machine vision capabilities. Using TSMC's ultra-low-power 28nm advanced process with dual-core 64-bit processors for better power performance, stability and reliability. The program strives for zero threshold development and can be deployed in the user's products in the shortest time, giving the product artificial intelligence. 

• Machine vision
• Better low power vision processing speed and accuracy
• Convolutional artificial neural network hardware accelerator KPU, high performance convolution artificial neural network operation
• TSMC 28nm advanced process, temperature range -40 ° C to 125 ° C, stable and reliable
• Support firmware encryption, it is difficult to crack using common methods
• Unique programmable IO array for more flexible product design
• Low voltage, lower power consumption compared to systems with the same processing power
• 3.3V/1.8V dual voltage support, no level shifting, cost saving

1.1.1 CPU

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

• Number of cores: Dual-core processor
• Processor bit width: 64-bit CPU 400MHz
• Nominal frequency: 400MHz
• Instruction Set Extension: IMAFDC
• Floating Point Processing Unit (FPU): Double precision
• Platform Interrupt Management: PLIC
• Local interrupt management: CLINT
• Instruction cache: 32KiB x 2
• Data cache: 32KiB x 2
• On-chip SRAM: 8MiB

1.2 OV7740

• Support output format: RAW RGB and YUV
• Support image size: VGA, QVGA, CIF or other smaller sizes
• Support sunspot elimination
• Support for internal and external frame synchronization
• Standard SCCB serial interface
• Digital Video Port (DVP) Parallel Output Interface
• Embedded One Time Programmable (OTP) Memory
• On-chip phase-locked loop (PLL)
• Embedded 1.5 V Regulator for the Core

1.2.1 Specifications

• Array size: 656 x 488
• Power: - Core: 1.5VDC ± 5% - Analog: 3.3V ± 5% - I / O: 1.7 ~ 3.47V
• Temperature range: - Operation: -30 ° C to 70 ° C - Stable image: 0 ° C to 50 ° C
• Output format: - 8/10-bit raw RGB data - 8-bit YUV
• Lens size: 1/5"
• Input clock frequency: 6~27 MHz
• Maximum image transfer rate: VGA (640x480): 60 fps - QVGA (320 x 240): 120 fp
• Sensitivity: 6800 mV / (Lux-sec)
• Maximum exposure interval: 502 x tROW
• Pixel size: 4.2μm × 4.2μm
• Image area: 2755.2μm × 2049.6μm
• Package/die size: - CSP3: 4185μm × 4345 μm-COB: 4200μm × 4360μm

1.3 MAX98357

• Single supply operation (2.5V to 5.5V)
• 3.2W output power: 4Ω, 5V
• 2.4mA quiescent current
• 92% efficiency (RL = 8Ω, POUT = 1W)
• 22.8μVRMS output noise (AV = 15dB)
• 0.01% THD+N at 1kHz
• No MCLK required
• 8kHz to 96kHz sampling rate
• Support left channel, right channel, and (left channel/2 + right channel/2) output
• Proven edge rate control allows Class D amplifier output to be filtered
• 77dB PSRR at 1kHz
• Low RF sensitivity to suppress TDMA noise from GSM emissions
• Click sound suppression circuit

1.4 AXP192

• Operating voltage: 2.9V - 6.3V (AMR: -0.3V~15V)
• Configurable intelligent power selection system
• Current and voltage limits for adaptive USB or AC adapter inputs
• Internal ideal diode resistance is less than 100mΩ

1.5 MPU6886

1.5.1 Gyro function

The three-axis MEMS gyroscope in the MPU-6886 has several functions:

• Digital output X, Y, and Z-axis angular rate sensors (gyro) with user programmable full-scale range of ±250 dps, ±500 dps, ±1000 dps, and ±2000 dps, integrated 16-bit ADC
• Digitally programmable low pass filter
• Low power gyroscope operation
• Factory calibration sensitivity scale factor
• Lens size: 1/5"
• Self test

1.5.2 Accelerometer function

The three-axis MEMS accelerometer in the MPU-6886 includes several functions:

• Digital output X, Y and Z-axis accelerometers with programmable full-scale range of ±2g, ±4g, ±8g and ±16g, integrated 16-bit ADC
• User programmable interrupt
• Wake-up interrupt, low-power operation for the application processor
• Self test

What can I do with the application / M5Stick-V?

• Facial recognition/detection
• Object detection/classification
• Get the size and coordinates of the target in real time
• Get the detected target type in real time
• Shape recognition
• Video/audio recording/display
• Game simulator