huangshk/WiMANS
[ECCV 2024] WiMANS: A Benchmark Dataset for WiFi-based Multi-user Activity Sensing
This project provides a comprehensive dataset to help researchers and developers build and evaluate systems that can sense multiple people's activities using standard WiFi signals. It takes raw WiFi Channel State Information (CSI) and synchronized video recordings, then provides annotations for user identities, locations, and specific activities. Scientists and engineers working on smart spaces, elder care, or security systems would use this to train and test their models.
No commits in the last 6 months.
Use this if you need a rich, multi-user dataset with both WiFi CSI and video to develop or benchmark models for human activity, identity, or location sensing without cameras.
Not ideal if you are looking for an out-of-the-box solution to deploy a WiFi sensing system, as this project focuses on providing data and benchmarks for research and development.
Stars
71
Forks
15
Language
Python
License
—
Category
Last pushed
Jul 08, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/huangshk/WiMANS"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
OxWearables/stepcount
Improved Step Counting via Foundation Models for Wrist-Worn Accelerometers
OxWearables/actinet
An activity classification model based on self-supervised learning for wrist-worn accelerometer data.
aqibsaeed/Human-Activity-Recognition-using-CNN
Convolutional Neural Network for Human Activity Recognition in Tensorflow
felixchenfy/Realtime-Action-Recognition
Apply ML to the skeletons from OpenPose; 9 actions; multiple people. (WARNING: I'm sorry that...
guillaume-chevalier/LSTM-Human-Activity-Recognition
Human Activity Recognition example using TensorFlow on smartphone sensors dataset and an LSTM...