RVC2 inside

This OAK device is built on top of the RVC2. Main features:

• 4 TOPS of processing power (1.4 TOPS for AI – RVC2 NN Performance)
• Run any AI model, even custom- architecture/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

OAK-D vs OAK-D-Lite

OAK-D-Lite is smaller, lighter and uses less power; compared to OAK-D. The main differences are:

• Mono cameras have lower resolution (640×480 instead of 1280×800)
• Initial versions of OAK-D-Lites (KickStarter batch) had no IMU. Current batches have BMI270.
• There is no power jack, as most users just used the USB-C for power delivery, which provides 900mA at 5V and is enough for most use-cases. However some functions (e.g. inference, video encoding) can lead to large current spikes, so there is a chance hosts like RPi won’t be able to provide enough power. In that case, you should use Y-adapter.

Additionally, the more technical differences are the following:

• Robotics Vision Core 2 chip-down design, instead of connecting the OAK-SoM to the baseboard (like it is done on OAK-D)
• In collaboration with ArduCam, we developed custom camera sensor connectors, which are shorter and take up less space

Fixed-focus vs Auto-focus

When ordering the OAK-D-Lite, you can select whether you want Fixed-focus (FF) or Auto-focus (AF) on the color camera. You should select FF if you are mounting OAK camera to something that vibrates. You should select AF when you need things closer than ~50cm to be in focus. More information can be found at Auto-Focus vs Fixed-Focus.

Dimensions and Weight

• Width: 91 mm
• Height: 28 mm
• Length: 17.5 mm
• Baseline: 75 mm
• Weight: 61 g