Paper Info
Title
Preprocessing Realistic Video for Contactless Heart Rate Monitoring Using Video Magnification
Abstract
This research seeks to improve the outcomes of Eulerian Video Magnification in real life scenarios. We address the core requirement in Eulerian Magnification that the person in the video be completely still. The proposed system pre-processes the video in multiple stages using subject targeting and stabilization. The resulting video is better suited to Eulerian Magnification restrictions. Our method enables the use of magnification in a variety of applications where motion is present such as monitoring the heart rate of a person using a treadmill. Stabilization, which is the core element of our research, was achieved through two methods. First, we used face tracking to generate a stabilized video with limited motion. Second, feature detection, extraction, and matching with skin selection were used to produce a stabilized video that is ready to be processed for measuring heart rate. However, skin tone and illumination in the environment adversely affected the results. Since heart rate is monitored by counting the subtle changes in skin redness related to blood flow, managing the skin's redness helps to produce more accurate results.
Year
DOI
Venue
2015
10.1109/CRV.2015.41
CRV
Keywords
Field
DocType
video magnification, computer vision, stabilization preprocessing video, contactless heart rate monitoring
Heart rate monitoring,Computer vision,Computer science,Feature extraction,Eulerian path,Video tracking,Preprocessor,Artificial intelligence,Magnification,Skin tone,Facial motion capture
Conference
Citations 
PageRank 
References 
4
0.45
15
Authors
2
Name
Order
Citations
PageRank
Ahmed Alzahrani140.45
Anthony Whitehead214320.84