Rppg Pulse Detection
- 10 installs
- 1 repo stars
- Updated March 10, 2026
- davidcastagnetoa/skills
Remote photoplethysmography (rPPG) pulse detection from video frames using computer vision.
About
ML skill for non-contact heart rate detection using rPPG algorithms on video. Enables health monitoring without sensors.
- Computer vision
- Health monitoring
Rppg Pulse Detection by the numbers
- 10 all-time installs (skills.sh)
- Ranked #1,561 of 2,064 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Jul 29, 2026 (Skillselion catalog sync)
npx skills add https://github.com/davidcastagnetoa/skills --skill rppg_pulse_detectionAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 10 |
|---|---|
| repo stars | ★ 1 |
| Last updated | March 10, 2026 |
| Repository | davidcastagnetoa/skills ↗ |
What it does
Remote photoplethysmography (rPPG) pulse detection from video frames using computer vision.
Files
rppg_pulse_detection
Remote Photoplethysmography (rPPG) detecta cambios sutiles en el color de la piel causados por el flujo sanguíneo, permitiendo medir el pulso cardiaco desde video. Una señal de pulso válida es evidencia biológica irrefutable de que hay una persona viva frente a la cámara.
When to use
Usar como señal de liveness de última línea en el liveness_agent. Requiere 5-10 segundos de video estable. Aplicar solo cuando otros métodos de liveness dan scores ambiguos (entre 0.4 y 0.7).
Instructions
1. Capturar mínimo 5 segundos de video a 30fps con iluminación estable. 2. Detectar y trackear la región de la frente/mejillas frame a frame con Mediapipe. 3. Extraer la señal de color verde promedio (canal G) de la ROI facial por frame. 4. Aplicar filtro bandpass (0.7-4 Hz) para aislar frecuencias cardiacas (42-240 bpm). 5. Calcular FFT de la señal filtrada e identificar el pico dominante. 6. Si el pico está entre 50-120 bpm con SNR > 3dB, clasificar como pulso válido. 7. Score: rppg_confidence basado en la claridad del pico de frecuencia.
Notes
- Requiere iluminación estable; luz artificial parpadeante puede crear artefactos.
- No funciona bien con pieles muy oscuras o con maquillaje pesado; usar solo como señal complementaria.
- Implementaciones open-source:
pyVHR,rPPG-Toolbox.
List_Agents.md
list_skills.md
CLAUDE.md
Agents.md
.DS_StoreRelated skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511