101021112 Embedded MCU DSP Evaluation Boards

FYX Original Development Boards Kit Programmers Embedded MCU DSP Evaluation Board 101021112 Vision AI Module V2 

Features

• Versatile AI Model Support: Easily deploy off-the-shelf or your custom AI models

• 
  

• from SenseCraft AI, including Mobilenet V1, V2, Efficientnet-lite, Yolo v5 & v8. TensorFlow and PyTorch frameworks are supported.

• Rich Peripheral Devices: Includes PDM microphone, SD card slot, Type-C, Grove interface, and other peripherals.
• High Compatibility: Compatible with XIAO series, Arduino, Raspberry Pi, ESP32 dev board, easy for further development
• Fully Open Source: All codes, design files, and schematics available for modification and use.

Description

What are the cores?

The Grove - Vision AI V2 is a highly efficient MCU-based smart vision module driven by the Himax WiseEye2 HX6538 processor, featuring a dual-core Arm Cortex-M55 and integrated Arm Ethos-U55 neural network component. It integrates Arm Helium technology, which is finely optimized for vector data processiong, enables a significant uplift in DSP and ML capabilities without compromising on power consumption, which is ideal for battery-powered applications.

To have a quick evaluation of this board's performance, we compared it to Seeed's other MCU-based vision AI boards - Grove Vision AI Module, XIAO ESP32S3 Sense in four areas:

1. Power consumption: This metric indicates whether the board can be used in battery-powered products.

2. Inference time: This metric indicates the processing speed of the MCU and how much latency is involved.

3. Frame rate: This metric evaluates whether the product can capture instant changes, patterns, and movements.

4. Ease of use: We assessed whether this product is user-friendly for vision AI novices and can quickly run mainstream models on the market.

Applications

Earlier MCU-based vision sensors were constrained by limited computing power, typically only supporting simple tasks like face detection. We believe this product surpasses the limits, enabling functionalities that were previously unachievable with traditional MCU-based vision AI sensors, such as:
1. Facial Keypoint Detection: Beyond basic facial recognition, detailed facial keypoint detection is capable of running. It accurately identifies critical features such as eyes, nose, and mouth.
2. Human Pose Estimation: It analyzes key joints and limbs to determine human posture, identifying body parts like arms, legs, torso, and head. This is useful for fitness tracking, posture correction, and motion recognition.
3.Object Detection: It supports powerful models like the Yolo v8n model, which can detect and classify over 80 types of objects.

Specification