Alexander Hauptmann, Shoou-I Yu and Yi Yang, two researchers at Carnegie Mellon University (CMU) have developed a technology to track the positions of numerous individuals in a complex, indoor setting using a network of video cameras.
The researchers have employed a unique algorithm that can trace people's movement from one camera to the other and can determine their locations when they are in the camera network's blind spots.
Doesn't this technique sound familiar? According to the researchers, the project is very similar to the fictional Marauder's Map used by Harry Potter to locate and track his friends, enemies and teachers in the magical world of Hogwarts School of Witchcraft and Wizardry.
The Carnegie Mellon researchers developed the tracking technology in an attempt to observe and check the health of nursing home residents.
The system automatically followed the movements of 13 people within the nursing home, even when individuals went out of the view of the cameras. Researchers were able to find them by using multiple hints from the video feed such as apparel color, person detection, trajectory and facial recognition.
"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," Hauptmann said.
Earlier, automated techniques have only been active in well-controlled lab environments. The research group at Carnegie Mellon utilized the technique successfully in challenging environments in the nursing home including long hallways, doorways, and people mingling in the hallways, variations in lighting and too few cameras to provide comprehensive, overlapping views.
The CMU research team began observing nursing home residents in 2005 as part of a National Institutes of Health-sponsored project called CareMedia.
The researchers- Alexander Hauptmann, principal systems scientist in the Computer Science Department (CSD); Shoou-I Yu, a Ph.D. student in the Language Technologies Institute; and Yi Yang, a CSD post-doctoral researcher - will present their findings June 27 at the Computer Vision and Pattern Recognition Conference in Portland, Ore.
Their algorithm is considered to be the best version as it could locate individuals within one meter of their actual site 88 percent of the time when compared to 35 percent and 56 percent for the other algorithms.
This automated tracking technique could prove beneficial in airports, public facilities and other areas where security is a concern.
