Introducing AIY Vision Kit

Build Your Own Intelligent Camera with Intel® Movidius™ VPU at the Heart

Earlier this year Google introduced the AIY voice project, which allowed makers to turn a Raspberry Pi into a voice-controlled assistant, using the Google Assistant SDK.

The company has now launched the AIY (AI yourself) Vision Kit that is smart and has a hackable camera system that runs on the Raspberry Pi Zero W. The kit is powered by Google’s TensorFlow machine-learning models and will soon gain an accompanying Android app for controlling the device.

AIY is cheap and simple computer vision system that doesn’t require access to cloud processing, because of the extra processing unit. It suggests several simple uses, including setting up cameras to detect your dog or car.

Contents

The kit includes the following:

• Button harness
• Cardboard subframe
• RGB arcade style pushbutton
• Privacy LED
• Piezo speaker
• Combo macro/wide lens kit
• VisionBonnet
• Camera flex cables
• Cardboard camera form
• Plastic standoffs
• Tripod mounting nut

Intelligence at the Edge: Intel Movidius Myriad Vision Processing Unit (VPU)

The Vision Kit employs a daughter board for the Raspberry Pi Zero W called the VisionBonnet. The VisionBonnet board is at the heart of this project with its Intel Movidius MA2450 chip that is capable of running TensorFlow-based neural network models on-device. These neural networks allow the AIY Vision Kit to run applications such as emotion estimation and recognize over 1000 common objects such as cats, dogs and varieties of plants.

The Intel Movidius Myriad Vision Processing Unit (VPU) makes the algorithms to run locally and at very low power, making them ideal for mobile and robotics applications.

Bundled with the software image are three neural network models:

• A model based on MobileNets that can recognize a thousand common objects.
• A model for face detection capable of not only detecting faces in the image, but also scoring facial expressions on a “joy scale” that ranges from “sad” to “laughing.”
• A model for the important task of discerning between cats, dogs and people.

Build Your Own Intelligent Camera Featuring Intel® Movidius™ VPU

The AIY Vision Kit is completely hackable:

• Want to prototype your own product? The Vision Kit and the Raspberry Pi Zero W can fit into any number of tiny enclosures.
• Want to change the way the camera reacts? Use the Python API to write new software to customize the RGB button colors, piezo element sounds and GPIO pins.
• Want to add more lights, buttons, or servos? Use the 4 GPIO expansion pins to connect your own hardware.

The Vision Kit enables makers to build a similar device, but that’s just the start.

For those of you who have your own models in mind, they have included the original TensorFlow code and a compiler. You can take a new model you have (or train) and run it on the the Intel® Movidius™ MA2450.

Necessary items not included:

• Raspberry Pi Zero W
• Raspberry Pi Camera 2
• Raspberry Pi Zero W compatible power supply
• 16GB micro SD card
• Scotch Tape

Where can you get it?

Pre-order your kit today through Micro Center.

Applications

What could you use the AIY Vision Kit to achieve? Google suggests challenging applications such as playing music when someone enters a room, sending a text when your car leaves the driveway or even recognising different types of food…