GitHub - ruvnet/RuView: π RuView: WiFi DensePose turns commodity WiFi signals into real-time human pose estimation, vital sign monitoring, and presence detection — all without a single pixel of video. · GitHub
WiFi DensePose: Real-Time Human Pose Estimation and Vital Sign Monitoring using WiFi Signals
Overview
WiFi DensePose is a system that uses WiFi signals to estimate human pose and vital signs in real-time, without the need for cameras or wearables. It works by analyzing Channel State Information (CSI) disturbances caused by human movement and reconstructing body position, breathing rate, and heartbeat using physics-based signal processing and machine learning.
Key Features
- Real-Time Pose Estimation: Estimates human pose in real-time, with a frame rate of up to 54,000 frames per second.
- Vital Sign Monitoring: Detects breathing rate (6-30 breaths/min) and heart rate (40-120 bpm) without any wearable.
- Multi-Person Tracking: Tracks multiple people simultaneously, each with independent pose and vitals.
- Through-Wall Sensing: WiFi signals can pass through walls, furniture, and debris, making it possible to detect people and vital signs through obstacles.
- Disaster Response: Detects trapped survivors through rubble and classifies injury severity (START triage).
- Multistatic Mesh: 4-6 low-cost sensor nodes work together, combining 12+ overlapping signal paths for full 360-degree room coverage with sub-inch accuracy and no person mix-ups.
How It Works
WiFi DensePose works by analyzing WiFi signals in the following steps:
- WiFi Router: Floods every room with radio waves.
- CSI Capture: ESP32 mesh (4-6 nodes) captures CSI on channels 1/6/11 via TDM protocol.
- Multi-Band Fusion: 3 channels × 56 subcarriers = 168 virtual subcarriers per link.
- Multistatic Fusion: N×(N-1) links → attention-weighted cross-viewpoint embedding.
- Coherence Gate: Accept/reject measurements → stable for days without tuning.
- Signal Processing: Hampel, SpotFi, Fresnel, BVP, spectrogram → clean features.
- AI Backbone: Attention networks, graph algorithms, and smart compression replace hand-tuned thresholds.
- Signal-Line Protocol: 6-stage gestalt → sensory → topology → coherence → search → model.
- Neural Network: Processed signals → 17 body keypoints + vital signs + room model.
- Output: Real-time pose, breathing, heart rate, room fingerprint, drift alerts.
Use Cases and Applications
WiFi DensePose has a wide range of use cases and applications, including:
- Healthcare: Elderly care, patient monitoring, emergency room triage.
- Retail: Occupancy and flow monitoring, customer behavior analysis.
- Office Space: Utilization and presence monitoring, HVAC optimization.
- Hotel and Hospitality: Room occupancy, minibar and bathroom usage patterns.
- Restaurants and Food Service: Table turnover tracking, kitchen staff presence.
- Parking Garages: Pedestrian presence in stairwells and elevators.
- Smart Home Automation: Room-level presence triggers for lights, HVAC, and music.
- Fitness and Sports: Rep counting, posture correction, breathing cadence.
- Childcare and Schools: Naptime breathing monitoring, playground headcount, restricted-area alerts.
Advantages
WiFi DensePose has several advantages over traditional camera-based systems, including:
- No Cameras: Avoids privacy regulations and camera-related issues.
- Through-Wall Sensing: Can detect people and vital signs through obstacles.
- Real-Time Monitoring: Provides real-time data for immediate action.
- Low Cost: Uses low-cost ESP32 nodes and WiFi signals.
- Easy Deployment: Can be deployed in existing WiFi infrastructure.
Link: https://github.com/ruvnet/RuView
Submitted by pete-e2gddzqh