Raspberry Pi has joined the world of AI with a new camera that processes visual data with on-device AI models. The $70 Raspberry Pi AI camera was built in collaboration with Sony Semiconductor Solutions Corporation (SSS).
The camera incorporates Sony's IMX500 intelligent vision sensor for on-chip AI image processing. That means there's no need for high-end GPUs or accelerators. It is compatible with Raspberry Pi single-board computers, making it relatively cheap and easy to create AI tools that rely on images.
The AI camera is around 12.3 megapixels and can film at ten frames per second at 4056 x 3040 or 40 fps at 2028 x 1520. The built-in neural network firmware allows AI image processing to run in the camera. This allows Raspberry to handle other elements of an embedded device, opening up options for Raspberry Pi users who don't want to use the Raspberry Pi AI Kit alone.
Raspberry Pi AI Camera: Object Detection Demo – YouTube
Look
Raspberry AI
On-chip AI processing reduces the load on the host device and enables real-time data processing without requiring cloud-based computing power. Processing data locally generates faster and more efficient artificial intelligence tools. Because it is compatible with much of the Raspberry Pi ecosystem, users can still use hardware and software libraries they are familiar with and enjoy. For example, AI Camera supports popular libraries such as lib-camera and Picamera2.
“AI-based image processing is becoming an attractive tool for developers around the world,” said Raspberry Pi Ltd. CEO Eben Upton. “Together with our long-standing image sensor partner, Sony Semiconductor Solutions, we have developed the Raspberry Pi AI camera, incorporating Sony's image sensor expertise. “We look forward to seeing what members of our community can achieve using the power of the Raspberry Pi AI camera.”