GOOGLE has announced the AIY Vision Kit, a do-it-yourself system that allows Raspberry Pi users to make use of the company’s AI tools.
“It’s our first project that features on-device neural network acceleration, providing powerful computer vision without a cloud connection,” Google said in a blog post.
The kit includes a cardboard outer shell, a new VisionBonnet circuit board, an RGB arcade-style button, a piezo speaker, a macro/wide lens kit, a tripod mounting nut and other connecting components. You’ll need to add a Raspberry Pi Zero W, a Raspberry Pi Camera, an SD card and a power supply for the kit to work, though.
The AIY Vision Kit also packs some computer vision software of which buyers can pair with their own Raspberry Pi computer and camera. Google said the provided software includes three TensorFlow-based neural network models for different vision applications.
“One based on MobileNets can recognise a thousand common objects, a second can recognize faces and their expressions and the third is a person, cat and dog detector,” the firm explained.
“We’ve also included a tool to compile models for Vision Kit, so you can train and retrain models with TensorFlow on your workstation or any cloud service.”
These features, Google said, could allow Raspberry Pi users to explore a plethora of creative builds that use computer vision, such as identifying plant and animal species, or seeing when your pet is at the back door, etc.
The kit release comes follows the launch Google’s AIY Projects, which was released in May to help makers experiment with and learn about AI. As part of this project, the firm released AIY Voice Kit, a system that Raspberry Pi users could buy to show what was possible with voice recognition in maker projects.
Google’s AIY Vision Kit will cost $44.99 (£33) when it ships through Micro Center on 31 December. µ
Source : Inquirer