OpenNISLab/Pro-Fusang

Open-source code for the paper "Fusang: Graph-inspired Robust and Accurate Object Recognition on Commodity mmWave Devices".

22
/ 100
Experimental

This project helps operations engineers or researchers accurately identify common objects in indoor environments using only a single millimeter-wave (mmWave) radar device. It takes raw radar signal data (HRRP and IQ samples) and outputs a precise classification of the object being scanned, even in complex, multi-path settings. It's designed for someone needing robust object recognition without relying on optical hardware or extensive data augmentation.

No commits in the last 6 months.

Use this if you need to identify stationary or moving objects in an indoor space with high accuracy (around 97%) using only a single mmWave radar, especially when visual recognition is not feasible or desired.

Not ideal if you don't have access to a commodity mmWave radar device or if you're looking for an out-of-the-box solution that doesn't require Python and MATLAB environments for setup and execution.

object-recognition radar-sensing indoor-navigation environmental-monitoring signal-processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

19

Forks

Language

Python

License

MIT

Last pushed

Aug 15, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/OpenNISLab/Pro-Fusang"

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