sjsreehari/Wi-Fi-gesture-dectection
WiFi CSI-based gesture recognition using dual-path ensemble deep learning (CNN2D + CNN1D-LSTM). 90.19% accuracy on ESP32 hardware with 426K parameters.
This system helps you detect human presence and specific gestures in a room using standard Wi-Fi signals, without needing cameras or wearable devices. It takes raw Wi-Fi Channel State Information (CSI) data from an ESP32 device and outputs classifications like 'Not Occupied', 'Occupied Static', or 'Occupied Motion'. This is ideal for smart home enthusiasts, facility managers, or privacy-conscious individuals looking for contact-free sensing solutions.
Use this if you need to detect human presence and gestures discreetly and without visual data, leveraging existing Wi-Fi infrastructure.
Not ideal if you need to identify individuals, perform very fine-grained gesture recognition, or require extreme precision in complex environments.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
Nov 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sjsreehari/Wi-Fi-gesture-dectection"
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...