Skip to main content

Community

Research & Community

Explore the clinical research behind SmartSpectra and connect with developers building contactless applications.

Connect

Join the Community

Developer Updates

SDK releases, API changes, and best practices delivered to your inbox.

Discord

Ask questions, share projects, and connect with other developers building contactless vital sign applications with SmartSpectra.

Join the Discord

GitHub

Explore open-source SDK samples, integration guides, and developer tools for building rPPG and contactless health monitoring applications.

Follow on GitHub

Resources

Model Cards

Algorithm validation detail for each SmartSpectra measurement, including accuracy figures and the conditions each model was tested under.

Continuous Pulse Rate

Pulse Rate

Validation and information on the continuous pulse rate algorithm. Extracts pulse rate from video using Presage's proprietary computer vision pipeline analyzing facial blood flow patterns through consumer-grade cameras.

Key Findings

  • Contactless pulse rate measurement from standard video
  • Validated across diverse demographics and camera types
  • Continuous monitoring without wearables
  • Suitable for wellness and informational applications
See model card for Continuous Pulse Rate

Continuous Relative Blood Pressure

Relative BP Waveform

High resolution continuous relative blood pressure waveform algorithm. Extracts the arterial waveform from video frames using face detection and image processing to infer relative measures of systolic, diastolic, and mean blood pressure.

Key Findings

  • High resolution relative blood pressure waveform extraction
  • Infers relative systolic, diastolic, and mean blood pressure
  • Window-based Pearson's correlation for validation
  • Validated across multiple camera platforms
See model card for Continuous Relative Blood Pressure

Continuous Breathing Rate

Breathing Rate 0.55 BrPM MAE

High resolution continuous breathing rate algorithm. Estimates breathing rate and waveform from video analysis of a subject's face, chest, and shoulders using signal processing techniques, measuring rates between 4-40 breaths per minute.

Key Findings

  • MAE of 0.55 BrPM with RMSE of 0.95 BrPM
  • 80% return rate at confidence >= 70
  • Validated against ETCO2 capnography via Biopac MP160
  • Tested on 93 subjects (184 videos) across diverse Fitzpatrick types
  • Validated on Logitech C920 and Samsung S24 cameras
See model card for Continuous Breathing Rate

Continuous Heart Rate Variability

HRV (SDNN, RMSSD, Stress Index)

High resolution continuous heart rate variability algorithm measuring SDNN, RMSSD, and Stress Index from facial video. Provides beat-to-beat variation metrics for research, clinical, and wellness applications.

Key Findings

  • Measures SDNN, RMSSD, and Stress Index from video
  • Designed for clinicians, polygraphers, and researchers
  • Continuous HRV monitoring without wearables
  • Validated across multiple camera types and demographics
See model card for Continuous Heart Rate Variability

Showcase

Projects & Media

Projects

119 repositories

JavaScript
sborishchev/geeksafe

GeekSafe

Your AI-powered safety mirror: Combining Gemini’s medical intelligence with live biometric sensing to keep you safe from high-risk substance interactions.

View on GitHub
View all repositories