- support@husseinkey.com
- livechat
Luxonis OpenCV AI Kits (OAK) are turn-key products that allow running with performant, spatial AI, and CV in minutes. These kits are built on DepthAI, which is an MIT-licensed open-source hardware, software, and AI-training suite based on the Myriad X. OAK-D is a spatial AI powerhouse, capable of simultaneously running neural inference (AI) and accelerated computer vision functions while providing depth from two stereo cameras and color information from a single 4K camera in the center. OAK-1 is the tiny-but-mighty 4K camera capable of running the same advanced neural networks as OAK-D, but in an even more minuscule form factor for projects where space and power are at a premium.
OAK is a modular, open-source ecosystem composed of MIT-licensed hardware, software, and AI training. This allows for embedding the super-power of spatial AI plus accelerated computer vision functions into projects. OAK provides a single, cohesive solution that would otherwise require cobbling together disparate hardware and software components.
The OAK API is a fast way to get started in spatial AI. The OAK-1 module’s single USB-C connector provides data and power. Go from unboxing the hardware to running an advanced image classifier in under a minute.
There are two ways to use OAK-D to get Spatial AI results: Monocular Neural Inference fused with Stereo Depth and Stereo Neural Inference. The modes have strengths and weaknesses for specific use cases.
With the Monocular Neural Inference fused with Stereo Depth, the neural network is run on a single camera and fused with disparity depth results. The left, right, or RGB camera can be used to run the neural inference.
When using Stereo Neural Inference the neural network is run in parallel on OAK-D’s left and right cameras to produce 3D position data directly with the neural network.
In these cases, standard neural networks can be used. There is no need for the neural networks to be trained with 3D data. OAK-D automatically provides the 3D results in both cases using standard 2D-trained networks.
