ACM Transactions on Graphics · 2012 · 252 citations · 5 references
ComputingComputer ScienceVisualizationBiomedical ImagingFlow VisualizationScientific VisualizationMotion CaptureOptical FlowPhysiological VisualizationTemporal VisualizationVideo AnalysisVideo RecordingFilteringMagnificationReal-time ProcessingSpatial DecompositionSpatio-temporal FilteringTemporal FilteringTemporal Medical VisualizationTemporal Signal Filtering
The study aims to make subtle temporal variations in videos visible and interpretable. Eulerian Video Magnification processes a standard video by spatial decomposition, temporal filtering, and signal amplification to reveal hidden motion. The technique successfully visualizes facial blood flow, amplifies minute motions, and operates in real time to display user‑selected temporal phenomena.
Our goal is to reveal temporal variations in videos that are difficult or impossible to see with the naked eye and display them in an indicative manner. Our method, which we call Eulerian Video Magnification, takes a standard video sequence as input, and applies spatial decomposition, followed by temporal filtering to the frames. The resulting signal is then amplified to reveal hidden information. Using our method, we are able to visualize the flow of blood as it fills the face and also to amplify and reveal small motions. Our technique can run in real time to show phenomena occurring at the temporal frequencies selected by the user.
5
Berthold K. P. Horn, Brian G. Schunck · Artificial Intelligence · 1981 · 9.9K citations · Full text
Remote plethysmographic imaging using ambient light
Wim Verkruysse, Lars O. Svaasand, J. Stuart Nelson · Optics Express · 2008 · 1.7K citations · Full text
Noise Estimation from a Single Image
Ce Liu, William T. Freeman, Richard Szeliski et al. · 2006 · 318 citations
Jue Wang, Steven M. Drucker, Maneesh Agrawala et al. · 2006 · 34 citations