Google offers Raspberry Pi owners this new AI vision kit to spot cats, people, emotions

Google's Vision Kit lets you build your own computer-vision system for $45, but you'll need your own Raspberry Pi.
Written by Liam Tung, Contributing Writer

Google has developed the VisionBonnet for high performance on-device computer vision.


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 lets you turn Raspberry Pi equipment into an image-recognition device. The kit is powered by Google's TensorFlow machine-learning models and will soon gain an accompanying Android app for controlling the device.

According to Google, Vision Kit features "on-device neural network acceleration", allowing a Raspberry Pi-based box to do computer vision without processing in the cloud. The AIY Voice Kit relies on the cloud for natural-language processing.

As with the AIY Voice Kit, makers will need to provide their own Raspberry Pi Zero W, a Raspberry Pi camera, a 4GB SD card, and power supply. The Vision Kit itself includes the VisionBonnet accessory board, cables, the cardboard box and frame, lens equipment, and a privacy LED to tell others when the camera is on.

The VisionBonnet board was developed by Google and is powered by Intel's Movidius MA2450 vision processing chip. This chip is the secret sauce of the Vision Kit.


Vision Kit components include the cardboard outer shell, VisionBonnet circuit board, an RGB arcade-style button, a piezo speaker, and a macro/wide lens kit.


Kai Yick, a member of the AIY Projects team, told the official Raspberry Pi magazine MagPi that the chip is 60 times faster at performing computer vision than if it were to rely on a Raspberry Pi 3. The VisionBonnet is connected to the Raspberry Pi Zero W by a cable supplied in the kit.

Vision Kit makers can use several neural-network programs, the first being one that can detect when people, cats, and dogs are in view, according to AIY Projects. Another neural network will detect happiness, sadness, and other sentiments. A further program, based on MobileNets, can detect 1,000 different objects such as a chair, orange, or cup.

Google hopes developers will build on these neural networks and apply them to new tasks, such as making the cat/dog/person detector recognize rabbits. To help achieve this goal, it's provided a tool to compile models for retraining models with TensorFlow.

Google suggests the Vision Kit box can be used to identify various plants and animal species, see when the dog is at the backdoor, or when the car has left the driveway, analyze your guests' emotions, or even set up a custom home-security system.

The Vision Kit is available from electronics seller Micro Center for $44.99 and will be available on December 31.

However, fans will probably want to pre-order the kit. The first batch of AIY Voice Kit sold out pretty quickly and it took several months before more become available. The same is likely to happen this time given that the initial run of Vision Kits consists of just 2,000 units.

Previous and related coverage

Raspberry Pi: This Google kit will turn your Pi into a voice-controlled digital assistant

The Google Assistant voice interaction kit will allow Pi fans to add voice control to their projects.

Raspberry Pi: Google plans more AI projects to follow DIY voice recognition kit

Google says its next maker projects will add eyes, ears, voice and a sense of balance.

Read more on computer vision

Editorial standards