Carnegie Mellon tracking algorithm inspired by Harry Potter's Marauder's map (w/ video)

May 30, 2013 by Nancy Owano weblog
Credit: Shoou-I Yu

(Phys.org) —Researchers from Carnegie Mellon have developed a solution for finding people through computer analysis making use of facial recognition, color matching and location tracking. With homage to the fictional map used by Harry Potter, they came up with a solution that can effectively track people in the real world just like The Marauder's Map locates and tracks people in Harry Potter's magical world. Security camera footage across a network of cameras can be analyzed via an algorithm that combines facial recognition, color matching of clothing, and a person's expected position based on last known location.

In designing the map, Shoou-I Yu, a PhD student at Carnegie Mellon University, who has been working on multi-object tracking in multi-camera environments for surveillance scenarios, sought to take on the challenge of finding and following individuals in complex where walls and furniture may obstruct views. He and his team found a solution by combining several tracking techniques.

In one of the settings tested, a nursing home, 13 people were tracked as they moved through the building. The result was that their algorithms were far more accurate than other tested, they said. The researchers will present a paper on the work at the IEEE and Pattern Recognition conference in Portland, Oregon in June. This is considered a top-level conference in computer vision.

In their paper, "Harry Potter's Marauder's Map: Localizing and Tracking Multiple Persons-of-Interest by Nonnegative Discretization," authors Shoou-I Yu, Yi Yang, and Alexander Hauptmann noted that their algorithm's advantage is its ability to track people not only in outdoor but also in complex indoor environments that may involve many walls and corridors."An ideal Marauder's Map algorithm should integrate different sources of information," they said, which led them to propose their localization and tracking algorithm. They said their algorithm makes use of "color, person detection, face recognition and non-background detection cues to perform robust tracking." Being able to incorporate all the available cues seamlessly, though, into a framework was not trivial. Their paper detailed their methodology and results. "Our algorithm is effective because of reliable face recognition and the combination of manifold learning with nonnegative discretization," they said.

This video is not supported by your browser at this time.
Demo Video. Credit: Shoou-I Yu

While an easy application assumption may be for law-enforcement investigations, other potential applications for such a Marauder's Map might be to find a nursing home resident with dementia who is lost, or as a service application used in large stores and malls.

Explore further: Ride-sharing could cut cabs' road time by 30 percent

More information: Project site: www.cs.cmu.edu/~iyu/cvpr13.html
Research paper: www.cs.cmu.edu/~iyu/files/cvpr13/cvpr13.pdf

Press release

Related Stories

Facial-recognition technology proves its mettle

May 24, 2013

(Phys.org) —In a study that evaluated some of the latest in automatic facial recognition technology, researchers at Michigan State University were able to quickly identify one of the Boston Marathon bombing ...

Intel's Perceptual Computing marks neo-desktop era

Jan 14, 2013

(Phys.org)—Intel wants you to know that voice, face and gesture control will become a familiar feature in computers. The time for a new kind of notebook world is now, for Intel, and computing facets including ...

Scientists map all possible drug-like chemical compounds

Apr 22, 2013

(Phys.org) —Drug developers may have a new tool to search for more effective medications and new materials. It's a computer algorithm that can model and catalogue the entire set of lightweight, carbon-containing ...

Making surveillance cameras more efficient

Mar 05, 2012

A University of California, Riverside professor has recently co-authored a book about his surveillance camera research that has applications in everything from homeland security, environmental monitoring and home monitoring.

Recommended for you

Ride-sharing could cut cabs' road time by 30 percent

13 hours ago

Cellphone apps that find users car rides in real time are exploding in popularity: The car-service company Uber was recently valued at $18 billion, and even as it faces legal wrangles, a number of companies ...

Avatars make the Internet sign to deaf people

Aug 29, 2014

It is challenging for deaf people to learn a sound-based language, since they are physically not able to hear those sounds. Hence, most of them struggle with written language as well as with text reading ...

Chameleon: Cloud computing for computer science

Aug 26, 2014

Cloud computing has changed the way we work, the way we communicate online, even the way we relax at night with a movie. But even as "the cloud" starts to cross over into popular parlance, the full potential ...

User comments : 3

Adjust slider to filter visible comments by rank

Display comments: newest first

Shakescene21
3.7 / 5 (3) May 30, 2013
Arthur Weasley observed that Muggle technology was getting so amazing that some of it resembled magic.
Dhanne
5 / 5 (2) May 31, 2013
Just to point out, the mention of Harry Potter is a writing technique called attention grabber. Its whole purpose is, of course, to grab attention, to get you hooked on reading this article. So don't rate the article down just because of it.
Jotaf
not rated yet May 31, 2013
The paper is solid, but there are other very interesting multi-object tracking papers at the CVPR this year. The fact that one is getting all the attention just because of an unconventional title is probably going to irk some people, and it's a reflection of a (IMO) bad precedent created over the past few years in Computer Vision conferences. I mean, just calling it the "Marauder's map" would probably give it a good measure of subtle humor, but splashing Harry Potter all over the title and introduction (!) may be a bit too much :)

Also the non-negative factorization approach is pretty cool but I fear everyone will just discuss the title and not the actual technical content. (As I am no doubt doing right now...)