OAK-D CM4 Camera

The OAK-D CM4 combines OAK-D with Raspberry Pi CM4 module acting as host computer. It’s designed to provide developers with a platform for creating advanced computer vision applications.

Key Features:

• 4 TOPS of processing power (1.4 TOPS for AI – RVC2 NN Performance)
• CM4004032: 4GB RAM, 32GB eMMC, no WiFi
• Pre-flashed with Raspberry Pi OS and DepthAI Python interface
• 1x Ethernet, 2x USB2.0, HDMI

Description

This product has an integrated Raspberry Pi CM4, which acts as a host computer. So this device is capable of full stand-alone operations. It has the same functions as OAK-D camera connected via USB cable to Raspberry Pi4.

OAK-D CM4 is the ultimate camera for robotic vision that perceives the world like a human by combining stereo depth camera and high-resolution color camera with an on-device Neural Network inferencing and Computer Vision capabilities.

RVC2 architecture on-board features:

• 4 TOPS of processing power (1.4 TOPS for AI – RVC2 NN Performance)
• Run any AI model, even custom architected/built ones (models need to be converted)
• Encoding: H.264, H.265, MJPEG – 4K/30FPS, 1080P/60FPS
• Computer vision: warp (undistortion), resize, crop via ImageManip node, edge detection, feature tracking. You can also run custom CV functions
• Stereo depth perception with filtering, post-processing, RGB-depth alignment, and high configurability
• Object tracking: 2D and 3D tracking with ObjectTracker node

• CM4: Raspberry Pi acts as a host computer, which you can access via SSH/VNC. CM4 connects to the OAK-SOM, see Deploy with Raspberry Pi for additional information.
• Base line: 90 mm
• Ideal depth range: 85cm – 10m. See technical specifications.
• Power consumption: Up to 15W (please see technical specifications)
• Dimension: 110x60x27mm
• Weight: 106g

Technical Specifications

Camera Specifications

This camera uses 12MP auto-focus camera with IMX378 as main RGB camera.

Sensors specifications

Stereo depth perception

This OAK camera has a baseline of 9.0cm – the distance between the left and the right stereo camera. Minimal and maximal depth perception (MinZ and Max) depends on camera FOV, resolution, and baseline – more information here.

• Ideal depth range: 85cm – 10m
• MinZ: ~20cm (400P, extended), ~40cm (400P OR 800P, extended), ~80cm (800P)
• MaxZ: ~17 meters with a variance of 10%

Extended means that StereoDepth node has Extended disparity mode enabled.

Power and connectivity

Connectivity

Camera offers USB-C (USB 3.2 Gen1, 5 Gbps) for power and connectivity.

Power consumption

Most of the power is consumed by the RVC2, so the power consumption mostly depends on the workload of the VPU:

• Base consumption + camera streaming: 2.5W – 3W
• AI subsystem consumption: Up to 1W
• Stereo depth pipeline subsystem: Up to 0.5W
• Video Encoder subsystem: Up to 0.5W
• Raspberry Pi CM: Between 0.5W and 10W, depending on the CPU usage

So the total power consumption can be up to ~15W if you are using all the features at 100% at the same time. To reduce the power consumption, you can reduce CPU computation on the RPi CM, or FPS of the whole pipeline – that way, subsystems wont be utilized at 100% and will consume less power.

Operating Characteristics

Temperature

The ambient operating temperature of RVC2 based devices is between -20C and 50C when fully utilizing the VPU. To find out more, see our operating temperature range documentation.

Package Includes

Package contains:

• OAK-D CM4 board
• Power supply with international adapters

Files

1. 3D Models (Download STEP file)
2. Board layout
3. Altium design files
4. Assembly drawing
5. Assembly output
6. Fabrication Drawing
7. Fabrication output
8. Schematics