Qengineering/YoloV8-seg-NPU

YoloV8 segmentation NPU for the RK 3566/68/88

22
/ 100
Experimental

This project helps you perform real-time object detection and segmentation on video feeds or images using specialized hardware. It takes visual input and outputs identified objects with precise outlines, enabling tasks like counting items, monitoring areas, or enhancing robotic vision. It's designed for engineers and hobbyists building embedded vision systems with Rockchip NPU-enabled single-board computers.

No commits in the last 6 months.

Use this if you need fast, efficient, and accurate object segmentation on embedded Linux devices like the Rock 5, Orange Pi 5, or Radxa Zero 3, leveraging their Neural Processing Units (NPUs).

Not ideal if you need a cloud-based solution, are working with general-purpose CPUs without an NPU, or require a high-level API for rapid application development without low-level C++ interaction.

embedded-vision robotics real-time-object-segmentation edge-ai surveillance-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

17

Forks

Language

C++

License

BSD-3-Clause

Last pushed

Apr 30, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Qengineering/YoloV8-seg-NPU"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.