Qengineering/YoloV5-NPU

YoloV5 NPU for the RK3566/68/88

40
/ 100
Emerging

This project offers pre-optimized computer vision models, specifically object detection (like identifying cars, people, or signs) and text recognition, tailored for embedded systems with Rockchip NPUs (Neural Processing Units). It takes live camera feeds or image files as input and outputs identified objects or text in real-time. This is intended for embedded systems developers or hobbyists building applications on devices like the Rock 5 or Radxa Zero 3.

124 stars. No commits in the last 6 months.

Use this if you need to perform fast object detection or text recognition on a low-power, embedded Linux device equipped with a Rockchip RK3566, RK3568, or RK3588 NPU.

Not ideal if you are looking for a general-purpose object detection library for desktop PCs, cloud servers, or devices without a compatible Rockchip NPU, as it's highly specialized for specific embedded hardware.

embedded-systems real-time-object-detection edge-ai computer-vision optical-character-recognition
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

124

Forks

15

Language

C++

License

BSD-3-Clause

Last pushed

Jun 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Qengineering/YoloV5-NPU"

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