Publication Date
2017
Document Type
Thesis
Committee Members
Tanvi Banerjee (Advisor), Yong Pei (Committee Member), Thomas Wischgoll (Committee Member)
Degree Name
Master of Science (MS)
Abstract
We present the results of analyzing gait motion in-person video taken from a commercially available wearable camera embedded in a pair of glasses. The video is analyzed with three different computer vision methods to extract motion vectors from different gait sequences from four individuals for comparison against a manually annotated ground truth dataset. Using a combination of signal processing and computer vision techniques, gait features are extracted to identify the walking pace of the individual wearing the camera and are validated using the ground truth dataset. We perform an additional data collection with both the camera and a body-worn accelerometer to understand the correlation between our vision-based data and a more traditional set of accelerometer data. Our results indicate that the extraction of activity from the video in a controlled setting shows strong promise of being utilized in different activity monitoring applications such as in the eldercare environment, as well as for monitoring chronic healthcare conditions.
Page Count
60
Department or Program
Department of Computer Science and Engineering
Year Degree Awarded
2017
Copyright
Copyright 2017, all rights reserved. My ETD will be available under the "Fair Use" terms of copyright law.
ORCID ID
0000-0003-3059-8288
