Develop with the Raspberry Pi AI Camera featuring IMX500

Develop AI models and run them directly on a Raspberry Pi AI Camera for real‑time vision AI applications at the edge.

SET UP THE CAMERA

Install and set up your camera, deploy a precompiled AI model, and try out a simple edge application like object detection or pose estimation.

Get started with the AI Camera ↗

INSTANT LAUNCH

Accelerate your AI model development with AI services. Use a simple UI and no-code environment to create your own classifier, detector, and anomaly detection AI models.

See available AI services

DO IT YOURSELF

Learn how to prepare datasets, train your AI models, and create AI vision applications for Raspberry Pi AI Camera through a variety of tutorials and examples.

Develop and deploy AI models

Scale up with AITRIOS

AITRIOS combines powerful AI development tools, training services, and edge devices into an integrated Vision AI platform, empowering teams of all skill levels to build, deploy and operate vision AI applications at the edge.

Learn more

Note: You can access all of the Raspberry Pi AI Camera content on this site without logging in or registering.

Raspberry Pi AI Camera with IMX500

The Raspberry Pi AI Camera, equipped with the IMX500 Intelligent Vision Sensor from Sony, offers high-speed edge AI inference in a compact, all-in-one solution that works with any Raspberry Pi.

Buy the camera ↗

IMX500 key benefits

IMX500 is the world's first Intelligent Vision Sensor with edge processing functionality.

image of the Raspberry pi AI Camera
One-chip solution

IMX500 has a stacked sensor structure combining an image sensor with a powerful DSP and dedicated on-chip SRAM equipped with AI processing without needing a round trip to a server.

High-performance AI inference

IMX500 eliminates the need for high-performance processors or external memory. Deploy a new AI model and reuse the same powerful hardware for different tasks.

Low power requirements and cost-effective

IMX500 eliminates the need for high-performance processors or external memory, so your vision AI system will need less bandwidth and less power.

Low latency and privacy

AI inference at the edge means image data never leaves the chip, unless you want it to, helping you address privacy concerns.

Product names, service names or logo marks used in this Web Site are registered trademarks or trademarks and copyrighted properties of their respective owners and/or licensors. See Trademarks.