The Weakly Identifying System for Doorway Monitoring
Date
2007-05-10
Author
Advisors
Ellis, Carla
Brady, David
Cox, Landon
Parr, Ron
Repository Usage Stats
694
views
views
836
downloads
downloads
Abstract
The System Architecture for Tracking Individuals (SAFTI) is an indoor person location
tracking system designed for use in the field of pervasive computing. SAFTI provides
location tracking in environments where cameras are too privacy invasive, where tracking
devices are too costly, insecure or inconvenient, and where usability is a high priority.
While many location tracking systems satisfy each of these constraints individually,
SAFTI satisfies all three constraints simultaneously. Upon entering and exiting SAFTI
buildings, users submit identification credentials. Once inside the building, using
SAFTI is effortless - simply passing through doorways is sufficient for supplying
SAFTI with the information it needs to perform location tracking. An integral part
of SAFTI is the Weakly Identifying System for Doorway Monitoring (WISDOM). These instrumented
doorways contain a variety of infrared, ultrasonic and pressure sensors that detect
the direction of passage and measure each user's body size and shape. We quantify
the measurement and identification accuracy of WISDOM by analyzing data collected
from a user study containing 530 passes through a WISDOM prototype from 10 different
subjects. We combine the results from WISDOM with large publicly available anthropometric
databases to evaluate how accurately SAFTI performs location tracking with respect
to building size, density of occupants, and matching algorithm used.
Type
DissertationDepartment
Computer SciencePermalink
https://hdl.handle.net/10161/204Citation
Jenkins, Christopher James (2007). The Weakly Identifying System for Doorway Monitoring. Dissertation, Duke University. Retrieved from https://hdl.handle.net/10161/204.Collections
More Info
Show full item record
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 3.0 United States License.
Rights for Collection: Duke Dissertations
Works are deposited here by their authors, and represent their research and opinions, not that of Duke University. Some materials and descriptions may include offensive content. More info