The Raspberry Pi AI Camera is a compact camera module from Raspberry Pi based on the Sony IMX500 Intelligent Vision Sensor. IMX500 combines a 12-megapixel CMOS image sensor with on-board inferencing acceleration for various common neural network models, enabling users to develop sophisticated vision-based AI applications without needing a separate accelerator.

The AI Camera transparently augments captured still images or video with tensor metadata, leaving the processor in the host Raspberry Pi free to perform other operations. Support for tensor metadata in the libcamera and Picamera2 libraries, and in the rpicam-apps application suite, make it easy for beginners to use while offering advanced users unparalleled power and flexibility.

The Raspberry Pi AI Camera is compatible with all Raspberry Pi computers. The PCB outline and mounting hole locations are identical to those of Raspberry Pi Camera Module 3, while the overall depth is greater to accommodate the larger IMX500 sensor and optical subassembly.

Features:

• 12MP Sony IMX500 Intelligent Vision Sensor (1/2.3 size)
• Integrated low-power inference accelerator
• Import custom models from TensorFlow and PyTorch
• Pre-loaded with MobileNet SSD object detection model
• 76-degree field of view
• Manually adjustable focus
• Supplied with 200mm cables for connection to all Raspberry Pi computers

Specifications:

• 12.3 MP Sony IMX500 Intelligent Vision Sensor with a powerful neural network accelerator
• Framerates:

• 2×2 binned: 2028×1520 10-bit 30fps
• Full resolution: 4056×3040 10-bit 10fps
• 7.857 mm sensor size
• 1.55 μm × 1.55 μm pixel size
• 78.3 (±3) degree FoV with manual/mechanical adjustable focus
• F1.79 focal ratio
• 25 × 24 × 11.9 mm module dimensions
• Integrated RP2040 for neural network firmware management
• Works with all Raspberry Pi models using standard camera connector cable