GROVE VISON AI V2

Introduction

Recently the seeed studio launches the Grove Vision AI Module V2. This device is an MCU-based vison AI module powered by Arm Cortex-M55 & Ethos-U55. It supports TensorFlow and and PyTorch framerwork and is compatible with Arduino IDE. The module’s ability to process visual data at the edge eliminates the need for cloud processing, ensuring faster responses and lower energy consumption. This article explores the features, applications, and step-by-step integration of Grove Vision AI V2 to unlock its full potential. With the SenseCraft AI algorithm, trained ML models can be deployed to the sensor without the need for coding.

Key Features of Grove Vision AI V2

• Powerful AI Processing Capabilities: Utilizes WiseEye2 HX6538 processor with a dual-core Arm Cortex-M55 and integrated Arm Ethos-U55 neural network unit.
• 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, ESP dev board, easy for further development.
• Fully Open Source: All codes, design files, and schematics available for modification and use.

Applications and Use Cases

• Object Detection and Recognition: Enables devices to detect and classify objects, useful in security and automation.
• Facial Recognition and Access Control: Perfect for building smart locks, attendance systems, and facial access control solutions.
• Smart Agriculture: Can monitor plant health by detecting pests, measuring leaf conditions, or automating irrigation based on visual feedback.
• Industrial Automation: Detects defects, ensures quality control, and monitors assembly lines.
• Traffic Monitoring: Tracks vehicles, pedestrians, and road conditions, useful in urban planning and smart city initiatives.

Hardware Overview

The recommended camera to be used with this device is the OV5647-62 FOV Camera Module for Raspberry Pi.

Video below demonstrate how to connect the camera.

In the next article, we will explore how to get started and build a simple project.