SecurePose: Automated Face Blurring and Human Movement Kinematics Extraction from Videos Recorded in Clinical Settings

arXiv:2402.14143v1 Announce Type: new
Abstract: Movement disorders are typically diagnosed by consensus-based expert evaluation of clinically acquired patient videos. However, such broad sharing of patient videos poses risks to patient privacy. Face blurring can be used to de-identify videos, but this process is often manual and time-consuming. Available automated face blurring techniques are subject to either excessive, inconsistent, or insufficient facial blurring - all of which can be disastrous for video assessment and patient privacy. Furthermore, assessing movement disorders in …

abstract acquired arxiv automated clinical consensus cs.ai cs.cv evaluation expert extraction face human identify patient privacy process risks type videos