We're excited to share a new tutorial that walks through how to run YOLO neural network models directly onboard OAK4.
As edge AI applications continue to grow in complexity, deploying inference directly on-device has become increasingly important for achieving low latency, reducing bandwidth requirements, and simplifying system architectures. OAK4 is designed to make this process straightforward by combining powerful vision capabilities with dedicated AI acceleration in a compact and efficient platform.
In this video, we demonstrate the complete workflow for deploying and running YOLO models on OAK4.
You can also follow this tutorial in written format on our docs: https://docs.luxonis.com/cloud/tutorials/use-custom-models-on-hub-ai/.
Whether you're developing robotics solutions, industrial automation systems, smart cameras, or other computer vision projects, this tutorial provides a practical starting point for leveraging onboard AI processing with OAK4.
If you're interested in bringing real-time object detection to the edge, this guide will help you get up and running quickly with YOLO and OAK4.
