Eta Compute is a California-based technology company involved in providing AI edge vision, sensing solutions. They create energy-efficient AI endpoint solutions that enable sensing devices to make autonomous decisions in energy-constrained environments.
The company has released Low Power AI Vision Board for easy evaluation of their technology which is based on Low Power ARM-Cortex-M3 MCU which consumes only ~5uA/Mhz.
I am aware of only one more microcontroller which could compete with it from a low power consumption point of view, which is Ambiq Micro Apollo 4, it consumes 4uA/Mhz.
ECM3532 AI Vision Board
- Small size (1.5 x1.5 Inch) board with sensors
- ECM3532 NSP
- Himax HM0360 Camera
- Texas Instruments OPT3001 Ambient Light Sensor
- TDK ICS-41350 MEMs Microphones
- TDK ICM-42688-P 6-Axis Motion Sensor (Accel/Gyro)
- Battery socket for CR2032
- Onboard Bluetooth using ABOV Semiconductor A31R118
- 6-Pin UART Interface for programming
- Extension for other types of RF
Read more details on board.
Eta Compute provides a Neural Network API with support for CNN, RNN, LSTM, GRU, etc., various sensors, as well as a Software Development Kit that includes support for popular machine learning training frameworks such as TensorFlow.
The board is also compatible with Edge Impulse TinyML development pipeline.
Eta Compute ECM3532 NSP
- ECM3532 Neural Sensor Processor
- Ultra-low-power 32-bit Arm® Cortex®-M3, NXP CoolFlux 16-bit DSP
- 512kB Flash and 256kB + 96kB SRAM
- 8x PWM
- 2x UART ( Upto 460,800 Baud)
- 3x SPI (Slave), 3x SPI (Master)
- 3x I2C
- Mono, Stereo I2S
- 2x ADC (12 bit)
- Temperature sensor
Download datasheet from Eta Compute website.
ECM3532 is ideal for IoT applications that are battery operated or powered by energy
harvesting such as:
- Low power embedded vision
- Wearable and hearable devices
- Asset tracking, asset monitoring
- Gesture, image, and voice-based user interfaces
- IoT sensor nodes for security and building, retail / inventory management
How to buy ECM3532 AI Vision Board?
One can buy Eta Compute’s AI Vision Board from Digikey at 130$ or from their website as well.
I hope you found this post interesting.
If you like the post, please share it with others. Any suggestions or comments, let me know here.
Read my other articles on embedded systems design.
Happy learning to you!