Grove - Vision AI Module with Himax HX6537-A processor, thumb-size AI-powered OV2640 camera sensor, support YOLO v5 and Edge Impulse

The module features a compact AI-powered OV 2640 camera sensor embedded with Edge Machine Learning algorithms and can be easily deployed with simple clicks. It is a small and great assistant for various object detection projects and can be customized based on different needs. Just imagine endowing devices with vision through a tiny sensor.

Key Features

• Fully supported by Edge Impulse : Seamlessly sample raw data from the camera, build models and deploy trained ML models to the module from the studio without any programming
• Compact AI camera sensor: Equipped with OV2640 SOC sensor that supports auto-exposure and auto-white balance to offer good images
• Customizable model: Support the import of up to 3 customized models to realize mainstream ML functions like object detection
• Simple development & deployment: Support Arduino IDE programming and drag-and-drop model implementation
• High compatibility: Perfectly match with XIAO series interface, supports Arduino ecology through Grove connector

Description

Artificial Intelligence camera (AI camera) is the enhanced camera powered by a built-in Edge Machine Learning algorithm, smartly processing with computational photography to perform enhanced object detection in real-time. It has been widely used in smartphones for face recognition, edge devices for wildlife detection, and other Edge Intelligence applications.

This compact camera sensor will be the perfect module for you to get started with the AI-powered camera. It is installed with one pre-trained model that allows you to detect human faces. Furthermore, it has been installed with three ML classification algorithms for model recognition, which allows you to freely develop the models for detecting different objects and directly apply them to your projects.

Launched by Seeed Studio, the IoT hardware enabler, the sensor includes two typical IoT modules: a digital microphone and a 6-axis Inertial Measurement Unit (IMU), for your further usage of edge AI. Edge Impulse has annouced the IMU and Microphone Support for Grove - Vision AI, to get you started, here are two tutorials focused on the Microphone and IMU Sensors:

• Responding to your voice
• Building a continuous motion recognition system

Use YOLOv5 to Build Detect Models of Your Own

YOLO is an abbreviation for the term 'You Only Look Once'. It is an algorithm that detects and recognizes various objects in an image in real-time. Ultralytics YOLOv5 is the version of YOLO based on the PyTorch framework. Based on its repository, Seeed Studio has published a more suitable version that fits in Seeed Studio AIoT hardware/devices. You can use this repository to build detect models of your own. They can not only be implemented on the Grove vision AI module but also on the industrial-level SenseCAP A1101 - LoRaWAN Vision AI Sensor.

Meanwhile, we have provided a specific tutorial to show you how to train the AI model for specific applications and then deploy it onto the devices.

Transmit Your Data to the SenseCAP Cloud 

Same as the SenseCAP industrial-level sensors, the base-level Grove Vision AI Module can be connected to the SenseCAP cloud for data transmission. We are proud to introduce the SenseCAP K1100 - The Sensor Prototype Kit with LoRa® and AI that combines Wio Terminal and other classic IoT sensors to achieve this function.

The kit enables you to rapidly digitize the world using LoRa® and AI technology to tackle real-world challenges. With this plug-and-play toolkit, anyone can add AI to their edge devices and unlock the potential of AIoT. After walking through the plain and easy tutorials, you can connect the sensors with the SenseCAP cloud by LoRaWAN® or Wi-Fi within 10 minutes.

Build the Project with a Smaller MCU Board: Seeed Studio XIAO

Around the ports of the Grove Vision AI, there are dual 7-pin headers built to connect the Seeed Studio XIAO series. Seeed Studio XIAO series are all designed as thumb-sized development boards, empowered by popular and powerful chips: SAMD21, nRF52840, RP2040, and ESP32C3. In addition, it is so compact that all SMD components are placed on the same side of the board, so designers can easily integrate XIAO into the boards for rapid production.

Application

• People Detection
• Customized Object Detection
• Smart Doorkeeper
• Fall Detection & Alarm
• Face Recognition

Specification

Hardware Layout

*The camera sensor resolution supports up to 1600*1200, and yet due to the limitation of inference speed, we set the highest display as 192*192.

Part List