Seeed Studio
Grove Vision AI v2 Kit - with Raspberry Pi OV5647 Camera Module and Seeed Studio XIAO
A high-performance, MCU-based smart vision module powered by the Himax WiseEye2 HX6538 processor, featuring a dual-core Arm Cortex-M55 with an integrated Arm...
Get notified when back in stock
A high-performance, MCU-based smart vision module powered by the Himax WiseEye2 HX6538 processor, featuring a dual-core Arm Cortex-M55 with an integrated Arm Ethos-U55 neural processing unit. With Arm Helium technology optimised for vector data processing, it delivers strong ML and DSP performance at just 0.35 W — ideal for battery-powered vision AI applications.
Deploy off-the-shelf or custom AI models via the SenseCraft AI platform with no-code/low-code workflows. Supports popular frameworks including TensorFlow and PyTorch, with pre-built support for MobileNet V1/V2, EfficientNet-Lite, and YOLO v5/v8. This kit includes a Raspberry Pi OV5647 camera module and Seeed Studio XIAO for a complete development setup.
Key Features
- WiseEye2 HX6538 Processor – Dual-core Arm Cortex-M55 + Arm Ethos-U55 NPU
- 33 ms Inference Time – Fast on-device AI processing
- 30 FPS Frame Rate – Real-time vision capture and analysis
- 0.35 W Power Consumption – Suitable for battery-powered deployments
- Standard CSI Interface – Compatible with all Raspberry Pi cameras
- On-Board PDM Microphone – For sound-based AI applications
- SD Card Slot – Store images, video, and inference results
- Multiple Interfaces – I2C, UART, SPI, USB Type-C, and Grove connector
- SenseCraft AI Platform – No-code model deployment with instant visualisation
- Fully Open Source – All code, design files, and schematics available
Ideal For
- Edge AI and computer vision prototyping
- Object detection and image classification projects
- Smart home integration (e.g. Home Assistant)
- Battery-powered IoT vision applications
- Sound recognition and audio AI projects
Compatibility
- Seeed Studio XIAO series
- Arduino, Raspberry Pi, BeagleBoard, ESP-based boards
- Arduino IDE, MicroPython, CircuitPython, PlatformIO
- TensorFlow, PyTorch, MobileNet, EfficientNet, YOLO v5/v8
Package Contents
- 1× Grove Vision AI V2 Module
- 1× Raspberry Pi OV5647 Camera Module
- 1× Seeed Studio XIAO
Resources
Jargon buster
Plain-language definitions for the technical terms used above.
- CircuitPython
- A beginner-friendly version of Python designed to run directly on microcontroller boards. If a product supports CircuitPython, you can often program it by copying code files onto the board rather than setting up a more complex toolchain.
- DSP
- Digital signal processing means using software or hardware to analyse or modify signals such as audio, vibration, or sensor readings. A board suited to DSP is useful when a project needs fast maths for filtering, synthesis, or real-time signal analysis.
- fps
- fps means frames per second, or how many video images are captured or displayed each second. A higher fps generally gives smoother motion, which helps when the camera or the scene being viewed is moving.
- Grove
- Grove is a standardised 4-pin plug-in connector system for sensors and modules that avoids soldering and jumper wires, with different cable types carrying I2C, UART, analogue or digital signals. When a product is Grove-compatible it can be quicker to connect supported modules, provided the connector type, signal and voltage all match.
- I2C
- I2C is a two-wire communication bus used by many sensors and small modules. It matters because several I2C devices can share the same two wires, but each device needs a compatible address and your controller must support I2C.
- IDE
- Short for Integrated Development Environment, a program used to write, run and manage code. It matters because some learners prefer a traditional coding workspace instead of a guided notebook-style lesson.
- IoT
- Short for Internet of Things, meaning physical devices that connect to networks or the internet to send data or be controlled remotely. It matters if you want projects such as connected sensors, remote controls or classroom data-logging activities.
- MicroPython
- A version of the Python programming language made to run on microcontrollers. It matters because it lets beginners write readable code to control LEDs, sensors, motors and displays without needing to start with lower-level languages.
- MobileNet
- MobileNet is a type of image-recognition machine-learning model designed to run efficiently on smaller computers and mobile devices. It matters for maker AI projects because it can recognise objects or images without needing a powerful desktop computer.
- SPI
- A fast serial communication bus often used for displays, memory cards, and sensors. It matters because SPI devices need specific pins for clock and data, plus a separate chip-select line for each device.
- UART
- UART is a simple asynchronous serial interface that sends data over separate transmit and receive wires, usually labelled TX and RX, with both ends set to the same baud rate. It is a common way for microcontrollers and other serial devices to exchange data.
- USB Type-C
- USB Type-C is a small, reversible USB connector used for power, data and sometimes video on many modern devices. The connector itself does not guarantee a particular speed or voltage, so check the supported USB version, data rate and whether it carries more than 5V via USB Power Delivery.
Find this product in
STEM & Education
HX6538 datasheet
Datasheet · 1.4 MB · Click any page to view full size