Abstract | ||
---|---|---|
We present an approach for patient activity recognition in hospital rooms using depth data collected using a Kinect sensor. Depth sensors such as the Kinect ensure that activity segmentation is possible during day time as well as night while addressing the privacy concerns of patients. It also provides a technique to remotely monitor patients in a non-intrusive manner. An existing fall detection algorithm is currently generating fall alerts in several rooms in the University of Missouri Hospital (MUH). In this paper we describe a technique to reduce false alerts such as pillows falling off the bed or equipment movement. We do so by detecting the presence of the patient in the bed for the times when the fall alert is generated. We test our algorithm on 96 hours obtained in two hospital rooms from MUH. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/EMBC.2014.6944972 | EMBC |
Keywords | Field | DocType |
biomechanics,biomedical telemetry,remote sensing,equipment movement recognition,hospital rooms,telemedicine,alarm systems,patient monitoring,image segmentation,patient privacy,kinect sensor,fall alert generation,hospitals,nonintrusive patient monitoring,false alert reduction,night time activity segmentation,accidents,hospital beds,unobtrusive depth sensors,feature extraction,patient presence detection,day time activity segmentation,remote patient monitoring,furniture,fall detection algorithm,patient activity recognition,medical image processing,pillow falling recognition,image motion analysis | Computer vision,Activity recognition,Computer science,Segmentation,Artificial intelligence | Conference |
Volume | ISSN | Citations |
2014 | 1557-170X | 2 |
PageRank | References | Authors |
0.39 | 0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Tanvi Banerjee | 1 | 83 | 16.41 |
Moein Enayati | 2 | 4 | 1.80 |
James M. Keller | 3 | 3201 | 436.69 |
Marjorie Skubic | 4 | 1045 | 105.36 |
Mihail Popescu | 5 | 8 | 1.97 |
Marilyn Rantz | 6 | 310 | 26.24 |