Information Processing and Fusion: Change Point Detection for Video-Based Stressor Identification

Abstract

The objective of the proposed research is to lay the foundation of a robust analysis framework for video-based stress detection through change detection. Effort will establish novel blind deconvolution algorithms for robust extraction of the cardiac interbeat intervals (known as RR series). Focus will be placed on (1) overcoming the difficulties introduced by both noise and the low-pass nature of the cardiovascular system in detecting the cardiac interbeat interval, and (2) adaptation of novel entropic measures for heart rate variability analysis to change point detection from visually acquired heart beat signal.

Document Details

Document Type
DoD Grant Award
Publication Date
Jan 12, 2017
Source ID
W911NF1610153

Entities

People

  • Vasiliki Ikonomidou

Organizations

  • Army Contracting Command
  • George Mason University
  • United States Army

Tags

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Cardiovascular Physiology
  • Computer Vision.