Qengineering/YoloV8-NPU
YoloV8 NPU for the RK3566/68/88
This project provides pre-optimized computer vision models, specifically for object detection and image segmentation, tailored for embedded systems like the Rock 5, Orange Pi 5, or Radxa Zero 3. It takes live camera feeds or images and outputs bounding boxes around detected objects or segmented areas, making it useful for applications requiring real-time visual analysis on compact hardware. End-users include engineers and hobbyists building smart cameras, automated surveillance systems, or robots.
No commits in the last 6 months.
Use this if you need to run fast, efficient object detection or image segmentation on low-power, single-board computers that feature an NPU.
Not ideal if you are working with high-end GPUs, cloud-based processing, or if your application requires model training rather than deployment.
Stars
85
Forks
18
Language
C++
License
BSD-3-Clause
Category
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/YoloV8-NPU"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PINTO0309/OpenVINO-YoloV3
YoloV3/tiny-YoloV3+RaspberryPi3/Ubuntu LaptopPC+NCS/NCS2+USB Camera+Python+OpenVINO
RangiLyu/nanodet
NanoDet-Plus⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) /...
dog-qiuqiu/MobileNet-Yolo
MobileNetV2-YoloV3-Nano: 0.5BFlops 3MB HUAWEI P40: 6ms/img, YoloFace-500k:0.1Bflops...
Qengineering/Face-Recognition-Jetson-Nano
Recognize 2000+ faces on your Jetson Nano with database auto-fill and anti-spoofing
Qengineering/Face-Recognition-Raspberry-Pi-64-bits
Recognize 2000+ faces on your Raspberry Pi 4 with database auto-fill and anti-spoofing