Communications of the ACM
Carnegie Mellon Method Uses Network of Cameras to Track People in Complex Indoor Settings
The Carnegie Mellon team proved their technique for tracking multiple individuals within a building with actual residents and employees in a nursing facility, despite camera views compromised by long hallways, doorways, people mingling in the hallways, va
Credit: Carnegie Mellon University
Carnegie Mellon University (CMU) researchers have developed a method for tracking the locations of multiple individuals in complex, indoor settings using a network of video cameras.
The researchers say their method was able to automatically follow the movements of 13 individuals in a nursing home, even though they sometimes moved out of view of the cameras. The system relies on multiple cues from the video feed, including apparel color, person detection, trajectory, and facial recognition.
The CMU algorithm located individuals within one meter of their actual position 88 percent of the time.
"The goal is not to be Big Brother, but to alert the caregivers of subtle changes in activity levels or behaviors that indicate a change of health status," says CMU's Alexander Hauptmann.
The researchers now are studying additional ways to use video to monitor resident activity while maintaining privacy. They also note the technology could be used in areas where security is a concern, such as airports and public facilities.
The researchers used previously recorded nursing home video for their study and say that more work is needed to enable real-time monitoring.
From Carnegie Mellon News (PA)
View Full Article
Abstracts Copyright © 2013 Information Inc., Bethesda, Maryland, USA
No entries found