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:

  1. WiFi Router: Floods every room with radio waves.
  2. CSI Capture: ESP32 mesh (4-6 nodes) captures CSI on channels 1/6/11 via TDM protocol.
  3. Multi-Band Fusion: 3 channels × 56 subcarriers = 168 virtual subcarriers per link.
  4. Multistatic Fusion: N×(N-1) links → attention-weighted cross-viewpoint embedding.
  5. Coherence Gate: Accept/reject measurements → stable for days without tuning.
  6. Signal Processing: Hampel, SpotFi, Fresnel, BVP, spectrogram → clean features.
  7. AI Backbone: Attention networks, graph algorithms, and smart compression replace hand-tuned thresholds.
  8. Signal-Line Protocol: 6-stage gestalt → sensory → topology → coherence → search → model.
  9. Neural Network: Processed signals → 17 body keypoints + vital signs + room model.
  10. 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

quick.as — a curated link directory