Qengineering/YoloX-Tracking-ncnn-RPi_64-bit

YoloX with tracking for a bare Raspberry Pi 4 using ncnn.

38
/ 100
Emerging

This project helps you accurately track multiple individual objects moving within a video stream, even when they temporarily block each other. It takes a video file or live camera feed as input and outputs the same video with bounding boxes and unique IDs for each detected object, allowing you to follow their paths over time. It's designed for engineers or hobbyists building custom computer vision applications on a Raspberry Pi 4.

No commits in the last 6 months.

Use this if you need robust, real-time object tracking for specific items within a scene using a Raspberry Pi 4, for applications like surveillance, robotics, or interactive displays.

Not ideal if you need to run object tracking on more powerful hardware, require higher frame rates than what a Raspberry Pi 4 can provide, or are not comfortable with C++ development on embedded systems.

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

How are scores calculated?

Stars

19

Forks

7

Language

C++

License

BSD-3-Clause

Last pushed

Nov 06, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/Qengineering/YoloX-Tracking-ncnn-RPi_64-bit"

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