SAFETYLIT WEEKLY UPDATE

We compile citations and summaries of about 400 new articles every week.
RSS Feed

HELP: Tutorials | FAQ
CONTACT US: Contact info

Search Results

Journal Article

Citation

Staranowicz AN, Ray C, Mariottini GL. Conf. Proc. IEEE Eng. Med. Biol. Soc. 2015; 2015: 4994-4998.

Copyright

(Copyright © 2015, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/EMBC.2015.7319513

PMID

26737413

Abstract

Falls are the most-common causes of unintentional injury and death in older adults. Many clinics, hospitals, and health-care providers are urgently seeking accurate, low-cost, and easy-to-use technology to predict falls before they happen, e.g., by monitoring the human walking pattern (or "gait"). Despite the wide popularity of Microsoft's Kinect and the plethora of solutions for gait monitoring, no strategy has been proposed to date to allow non-expert users to calibrate the cameras, which is essential to accurately fuse the body motion observed by each camera in a single frame of reference. In this paper, we present a novel multi-Kinect calibration algorithm that has advanced features when compared to existing methods: 1) is easy to use, 2) it can be used in any generic Kinect arrangement, and 3) it provides accurate calibration. Extensive real-world experiments have been conducted to validate our algorithm and to compare its performance against other multi-Kinect calibration approaches, especially to show the improved estimate of gait parameters. Finally, a MATLAB Toolbox has been made publicly available for the entire research community.


Language: en

NEW SEARCH


All SafetyLit records are available for automatic download to Zotero & Mendeley
Print