Scope of Video Magnification in Human Pulse Rate Estimation

In this paper, we present a system that is a combination of spatial and temporal processing to emphasize the subtle changes in a video. Images and videos contain valuable information about the changes that evolve over time. There is a lot of information in videos, which is not visible by naked eye, and we need to magnify these small changes to study its behavior. The human eye has limited spatial-temporal sensitivity and visualization capability within a certain frequency band. However many signals of interest lie below these bands and can be very much informative. For example, a slight variation in the human skin due to the blood flow cannot be seen by the naked eye. This slight variation can be used to extract the human pulse. In the same way, low motion amplitude is tough for the human eye to observe. This is magnified able to expose interesting information. The growth of new tackle to expose the unseen signals in a video is an open and extensive area of research. In this paper, we have proposed a system that combines the spatial and temporal processing of videos to amplify the small changes in the human skin to detect the heart rate. We have performed an experiment on thirty videos of different subjects. Subjects come from different age group, gender, and ethnicity. Simulation result shows that the proposed algorithm achieves around 93% accuracy in heart rate estimation. This area has an extensive research potential and in the last few decades, it has shown huge achievements not only in the field of medical but also in other fields of engineering and practical applications as like security.

[1]  Michael Gleicher,et al.  Subspace video stabilization , 2011, TOGS.

[2]  Anpeng Huang,et al.  Healthinfo Engineering: Technology Perspectives from Evidence-Based mHealth Study in WE-CARE Project , 2015, Int. J. E Health Medical Commun..

[3]  Daniel McDuff,et al.  Advancements in Noncontact, Multiparameter Physiological Measurements Using a Webcam , 2011, IEEE Transactions on Biomedical Engineering.

[4]  Frédo Durand,et al.  Revealing Invisible Changes in the World , 2013 .

[5]  A. Murat Tekalp,et al.  Adaptive motion-compensated filtering of noisy image sequences , 1993, IEEE Trans. Circuits Syst. Video Technol..

[6]  Frédo Durand,et al.  Motion magnification , 2005, ACM Trans. Graph..

[7]  Leonard McMillan,et al.  Computational time-lapse video , 2007, SIGGRAPH '07.

[8]  Anthony Whitehead,et al.  Preprocessing Realistic Video for Contactless Heart Rate Monitoring Using Video Magnification , 2015, 2015 12th Conference on Computer and Robot Vision.

[9]  Frédo Durand,et al.  Motion denoising with application to time-lapse photography , 2011, CVPR 2011.

[10]  Maneesh Agrawala,et al.  The cartoon animation filter , 2006, ACM Trans. Graph..

[11]  Richard Szeliski,et al.  Noise Estimation from a Single Image , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[12]  William T. Freeman,et al.  A High-Quality Video Denoising Algorithm Based on Reliable Motion Estimation , 2010, ECCV.

[13]  Michael Rubinstein,et al.  Analysis and visualization of temporal variations in video , 2014 .

[14]  Robert J. Toonen,et al.  Observing the Coral Symbiome Using Laser Scanning Confocal Microscopy , 2013 .

[15]  Edward H. Adelson,et al.  Motion without movement , 1991, SIGGRAPH.

[16]  Hans-Peter Seidel,et al.  Real-time temporal shaping of high-speed video streams , 2010, Comput. Graph..

[17]  Rosalind W. Picard,et al.  Non-contact, automated cardiac pulse measurements using video imaging and blind source separation , 2022 .

[18]  Eleni Stroulia,et al.  International Journal of Medical Informatics , 2016 .

[19]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[20]  Eero P. Simoncelli,et al.  A Parametric Texture Model Based on Joint Statistics of Complex Wavelet Coefficients , 2000, International Journal of Computer Vision.

[21]  Hao-Yu Wu Eulerian Video Processing and Medical Applications , 2013 .

[22]  Majid Ghasemi ECG noise cancellation using kernel adaptive filtering , 2013 .

[23]  Frédo Durand,et al.  Eulerian video magnification for revealing subtle changes in the world , 2012, ACM Trans. Graph..