Raspberry Pi AI Camera (12.3 MP, Sony IMX500 Intelligent Vision Sensor)
Introduction
The Raspberry Pi AI Camera is a compact and powerful module designed for advanced vision-based AI applications. Featuring the Sony IMX500 Intelligent Vision Sensor, it combines a 12.3-megapixel CMOS sensor with on-board inferencing capabilities, enabling real-time processing of visual data without the need for an external AI accelerator. This makes it ideal for tasks like object recognition and facial detection. Fully compatible with all Raspberry Pi computers, it integrates easily with existing camera software and supports tensor metadata output for advanced image processing. The camera is designed to be user-friendly with libraries like libcamera and Picamera2, providing flexibility for both beginners and advanced users.
Powerful Vision AI Processing
The IMX500 sensor is built with an integrated AI processor that accelerates machine learning tasks directly on the camera module. This eliminates the need for additional hardware accelerators, simplifying the development of AI-powered applications such as real-time image classification or facial recognition.
High-Resolution Imaging
With a 12.3-megapixel resolution and a wide field of view, the camera captures high-quality images and video, suitable for a variety of applications including security monitoring, robotics, and environmental sensing.
Seamless Integration with Raspberry Pi Ecosystem
Fully compatible with all Raspberry Pi computers, the camera integrates effortlessly with the Raspberry Pi software stack, including Picamera2 and libcamera libraries. This makes it easy to implement complex AI vision projects with minimal setup.
Flexible Output and Metadata Support
The camera supports a range of outputs, including Bayer RAW10, YUV/RGB ISP outputs, and metadata. This flexibility provides users with the ability to work with a wide array of image formats and process additional data like region-of-interest (ROI) for advanced applications.
Applications
- Security systems
- Smart robotics
- Environmental monitoring
Specification
- Sensor: Sony IMX500 Intelligent Vision Sensor
- Resolution: 12.3 megapixels
- Sensor Size: 7.857 mm (1/2.3” type)
- Pixel Size: 1.55 µm x 1.55 µm
- Image Dimensions: 4056 x 3040 pixels (horizontal/vertical)
- IR Cut Filter: Integrated
- Autofocus System: Manual adjustable focus
- Focus Range: 20 cm to infinity
- Focal Length: 4.74 mm
- Field of View:
- Horizontal: 66° ±3°
- Vertical: 52.3° ±3°
- F-stop: f/1.79
- Infrared Sensitivity: No
- Image Output:
- Bayer RAW10
- ISP output (YUV/RGB)
- ROI
- Metadata
- Tensor Input Size: Max. 640 x 640 (H x V)
- Data Type: int8 or uint8
- Memory: 8,388,480 bytes (firmware, network weights, and working memory)
- Framerate:
- 2x2 binned: 2028 x 1520 10-bit @ 30fps
- Full resolution: 4056 x 3040 10-bit @ 10fps
- Dimensions: 25 mm x 24 mm x 11.9 mm
- Cable Length: 200 mm
- Cable Connector: 15 x 1 mm FPC or 22 x 0.5 mm FPC
- Operating Temperature: 0°C to 50°C
Documents
Shipping List
- Raspberry Pi AI Camera × 1
| Specification | |
| Accuracy | 1.55 µm x 1.55 µm |
| Cable Lenght | 20cm |
| Connector | Gravity |
| Output | Bayer RAW10 ISP output (YUV/RGB) ROI Metadata |
| Refresh rate | 30fps |
| Resolution | 12.3 megapixels 4056 x 3040 pixels (horizontal/vertical) |
| Waterproof Grade | IP68 |
| Power | 3.3V |
| Range Output | 2x2 binned: 2028 x 1520 10-bit @ 30fps Full resolution: 4056 x 3040 10-bit @ 10fps |
| Memory | |
| Flash(M) | 8,388,480 bytes (firmware, network weights, and working memory) |