Eulerian Phase-based Motion Magnification for High-Fidelity Vital Sign Estimation with Radar in Clinical Settings

Md Farhan Tasnim Oshim, Toral Surti, Charlotte Goldfine, Stephanie Carreiro, Deepak Ganesan, Suren Jayasuriya, Tauhidur Rahman

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Efficient and accurate detection of subtle motion generated from small objects in noisy environments, as needed for vital sign monitoring, is challenging, but can be substantially improved with magnification. We developed a complex Gabor filter-based decomposition method to amplify phases at different spatial wavelength levels to magnify motion and extract 1D motion signals for fundamental frequency estimation. The phase-based complex Gabor filter outputs are processed and then used to train machine learning models that predict respiration and heart rate with greater accuracy. We show that our proposed technique performs better than the conventional temporal FFT-based method in clinical settings, such as sleep laboratories and emergency departments, as well for a variety of human postures.

Original languageEnglish (US)
Title of host publication2022 IEEE Sensors, SENSORS 2022 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781665484640
StatePublished - 2022
Externally publishedYes
Event2022 IEEE Sensors Conference, SENSORS 2022 - Dallas, United States
Duration: Oct 30 2022Nov 2 2022

Publication series

NameProceedings of IEEE Sensors
ISSN (Print)1930-0395
ISSN (Electronic)2168-9229


Conference2022 IEEE Sensors Conference, SENSORS 2022
Country/TerritoryUnited States


  • Clinical Settings
  • Gabor Filter
  • Motion Magnification
  • UWB Radar
  • Vital Sign Estimation

ASJC Scopus subject areas

  • Electrical and Electronic Engineering


Dive into the research topics of 'Eulerian Phase-based Motion Magnification for High-Fidelity Vital Sign Estimation with Radar in Clinical Settings'. Together they form a unique fingerprint.

Cite this