Paper Info
Title
Stroke Patient Daily Activity Observation System
Abstract
Stroke is a leading cause of long-term adult disability. Stroke patients can recover through rehabilitation programs prescribed by occupational therapists (OT); however, an individualized rehabilitation program can reduce recovery times compared to traditional ones. In this paper, we propose a daily activity observation system (DAOS) that uses a Kinect v2 sensor to collect and retrieve motion data. The DAOS has a robust interface to extract depth and skeleton data, and supports data collection in an unstructured kitchen environment. Depth data are used to perform action recognition and track problematic movements, while skeleton data are used to calculate mean velocities of hand joints, max extensions, symmetry of hand movements, and other assessment metrics for therapists. Histogram of oriented 4D normalsis used for action recognition. The action recognition accuracy is 97% on a multi-class kitchen action dataset. Through action recognition and accurate assessment, we present a novel system that can assist therapists and their ability to provide quality care to stroke patients.
Year
DOI
Venue
2017
10.1109/BIBM.2017.8217765
2017 IEEE INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICINE (BIBM)
Keywords
DocType
ISSN
KinectV2, Stroke Rehabilitation, Machine Vision, HON4D, Activity Recognition, Assessment, Daily Observation System
Conference
2156-1125
Citations 
PageRank 
References 
0
0.34
0
Authors
5
Name
Order
Citations
PageRank
Jaired Collins100.34
Joseph Warren200.34
Mengxuan Ma311.76
Rachel Proffitt4254.17
Marjorie Skubic51045105.36