System-On-Modules - SOM Compute Module CM3+/Lite - Single Board Computer (SBC) 1.2GHZ 1 CORE 1GB RAM

Raspberry Pi CM3+ and CM3+ Lite are supported products with an end-of-life (EOL) date no earlier than January 2028.

Cameras & Camera Modules 12MP Sony IMX500 Intelligent Vision Sensor 76-degree

Raspberry Pi AI Camera is based on the Sony IMX500 Intelligent Vision Sensor. The IMX500 sensor combines a 12-megapixel CMOS image sensor with onboard inferencing acceleration for a variety of common neural network models, enabling users to develop sophisticated vision-based AI applications without the need for 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 lib-camera, Picamera2 libraries, and the price-apps application suite makes 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:

• 12.3MP Sony IMX500 intelligent vision sensor, 7.857mm (type 1/2.3)
• 1.55μm × 1.55μm pixel size
• 4056 × 3040 pixels (horizontal x vertical)
• Integrated IR cut filter
• Integrated low-power inference engine
• Manual adjustable focus
• 20cm to ∞ focus range
• 4.74mm focal length
• 66° ±3° horizontal field of view (FOV), 52.3° ±3° vertical
• F1.79 focal ratio (F-stop)
• Image (Bayer RAW10), ISP output (YUV/RGB), ROI, and metadata output types
• 640 × 640 ((HxV) maximum input tensor size
• 'int8' or 'uint8' input data type
• 8388480-byte memory size for firmware, network weight file, and working memory
• Framerate
  
  • 2×2 binned: 2028×1520 10-bit 30fps
  • Full resolution: 4056×3040 10-bit 10fps
• Pre-loaded with MobileNet machine vision model
• 25mm × 24mm × 11.9mm dimensions
• 200mm ribbon cable length
• 15 × 1mm FPC or 22 × 0.5mm FPC cable connector
• 0°C to +50°C operating temperature range

Applications:

• Home automation
• Face recognition
• Object detection
• Smart traffic monitoring
• Wildlife observation
• Healthcare monitoring
• Retail analytics
• Gesture recognition
• Agricultural monitoring
• Automated quality control

Object Detection:

Pose Estimation:

The Compute Module 3+ (CM3+) is a Raspberry Pi 3 Model B+ in a flexible form factor, intended for industrial applications. The CM3+/Lite contains the guts of a Raspberry Pi 3 Model B+ (the BCM2837 processor and 1GB RAM).

• Broadcom BCM2837B0, Cortex-A53 (ARMv8) 64-bit SoC @ 1.2GHz
• 1GB LPDDR2 SDRAM

This is all integrated onto a small (67.6mm × 31mm) board that fits into a standard DDR2 SODIMM connector. The processor interfaces are available to the user via the connector pins. You get the full flexibility of the BCM2837 SoC (which means that many more GPIOs and interfaces are available than with a standard Raspberry Pi), and designing the Module into a custom system should be relatively straightforward because we’ve put all the tricky bits onto the Module itself.

The Compute Module 3+ (CM3+) is a Raspberry Pi 3 Model B+ in a flexible form factor, intended for industrial applications.

The CM3+/32GB Compute Module contains the guts of a Raspberry Pi 3 Model B+ (the BCM2837 processor and 1GB RAM) as well as an 32GB eMMC Flash device (which is the equivalent of the SD card in the Pi).

• Broadcom BCM2837B0, Cortex-A53 (ARMv8) 64-bit SoC @ 1.2GHz
• 1GB LPDDR2 SDRAM
• 32GB eMMC Flash memory

This is all integrated onto a small (67.6mm × 31mm) board that fits into a standard DDR2 SODIMM connector. The Flash memory is connected directly to the processor on the board, but the remaining processor interfaces are available to the user via the connector pins. You get the full flexibility of the BCM2837 SoC (which means that many more GPIOs and interfaces are available than with a standard Raspberry Pi), and designing the Module into a custom system should be relatively straightforward because we’ve put all the tricky bits onto the Module itself.