OAK-D-CM4

Overview : Based off of the OAK-D-CM3 and Raspberry PI CM4IO board, the OAK-D CM4 combines a host (RPi CM4) and the OAK-SoM to allow for a fully standalone and integrated solution for real-time Spatial AI. The biggest difference between OAK-D-CM4 and OAK-D-CM3 architecture is that OAK-D-CM4 integrates CM4 module, has gigabit ethernet, and is populated with MagJack supporting PoE. PoE can be used with additional PoE Hat. Most OAK-D-CM4 devices have eMMC memory on-board. If you would like to flash a new image to it, follow the tutorial here.

Hardware specifications :

Sensor specifications

Myriad X inside : This OAK device has on-board Myriad X VPU (product pdf). Main features:
4 TOPS of processing power (1.4 TOPS for AI)
Run any AI model, even custom architectured/built ones - models need to be converted.
Encoding: H.264, H.265, MJPEG - 4K/30FPS, 1080P/60FPS
Computer vision: warp/dewarp, 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

Depth perception :

This OAK camera has a baseline of 9.0cm - the distance between left and right stereo camera. Minimal and maximal depth perception depends on camera FOV, resolution, and baseline.
Min perceivable distance: ~20cm (400P, extended), ~40cm (400P OR 800P, extended), ~80cm (800P)
Max perceivable distance: ~35 meters
Extended means that StereoDepth node has Extended disparity mode enabled.

Dimensions and Weight :

Width: 110 mm
Height: 60 mm
Length: 27 mm
Weight: 106g

Board Layout