Raspberry Pi launches a $70 AI-powered camera module

Raspberry Pi announces a new AI-powered camera module. The Raspberry Pi AI Camera was built in partnership with imaging giant Sony, featuring a Sony IMX500 “Intelligent Vision Sensor” which can process images using the integrated RP2040 microcontroller. The IMX500 also has 8GB of dedicated memory to handle most computing tasks.

Having an onboard AI image processor means that Raspberry Pi doesn’t need to use a GPU or cloud-based computing power. It also frees up the Pi microcomputer to do other tasks. The Raspberry Pi AI Camera retails for $70 and is now available from approved resellers.

Key features

The Raspberry PI AI Camera module has a 12.3-megapixel sensor and a burst rate of ten frames per second at full resolution. Lowering the resolution to 2028×1520 allows the camera to record images at 30fps. The resolution and framerate should be enough for most applications.

Sony’s IMX500 sensor is paired with a manual focus lens with a 4.75mm focal length and an aperture of F/1.79. The lens has a 66° horizontal and 52.3° vertical field of view. The module does not support interchangeable lenses.

The Raspberry Pi AI Camera module is compatible with all variants of the Raspberry Pi. The module attaches to the microcomputer using regular camera ribbon cables.
One key advantage of using the Raspberry Pi AI camera is its seamless integration with the Pi camera software stack. The module will also work with popular camera frameworks like Picamera2 and rpicam-apps. Raspberry Pi provided a simple object detection demo video using the AI Camera module running rpicams-apps.

The camera module is compatible with most existing neural network models to process visual information. The Raspberry Pi AI Camera targets users looking to experiment with artificial intelligence on the microcomputer. We are really excited to see the camera module in real-time object detection, facial recognition, and pose estimation projects. The AI Camera can also be integrated into robotics projects as an obstacle avoidance tool.

• Sensor: Sony IMX500 Intelligent Vision Sensor (12.3 megapixels, 7.857mm, 1.55μm pixel size, rolling shutter)
• Resolution: 4,056×3,040
• Framerate: 10 frames per second full-resolution, 30fps 2×2 binned
• Focus: Manual 20cm-∞, 4.74mm focal length
• Field of View: 66° horizontal, 52.3° vertical (±3°)
• F-stop: f/1.79
• Output: Bayer, RAW10, YUV, RGB, Regions of Interest (ROI), metadata
• Maximum Tensor Resolution: 640×640
• Precision: INT8
• Memory: 8,388,480 bytes (~8MB) shared between firmware, weights, working RAM
• Size: 25×24×11.9mm (around 0.98×0.94×0.47")
• Price: $70