Spatial Artifact Coherence Determines Codec Robustness in Patch-Based rPPG
Researchers have developed a new metric called Spatial Artifact Coherence (SAC) to predict the performance of remote photoplethysmography (rPPG) algorithms under video compression. SAC, calculated from the covariance matrix of video patches, effectively distinguishes between different codec families and their impact on rPPG accuracy. The study found that certain conditions, like low-to-moderate motion and specific SAC values, are necessary for patch-based methods to outperform global projection techniques, offering guidance for selecting robust algorithms in clinical applications. AI
IMPACT Provides a method to select robust AI algorithms for remote health monitoring under compressed video conditions.