;

Disney Research Team Unveils Cutting-Edge Video Surveillance Software

Researchers at Disney have developed a new software that can follow the same subject across a network of surveillance cameras.

Disney Research Team Unveils Cutting-Edge Video Surveillance Software

PITTSBURGH — Keeping a theme park filled with thousands of people safe is no easy task. Disney theme parks are known for their “Imagineers,” so it should come as no surprise that its researchers have developed a new video surveillance software.

Designed to track faces around the park, the software relies on a ‘deep spatial pyramid’ method for person re-identification.

Here is the abstract from the research paper:

Re-identification refers to the task of finding the same subject across a network of surveillance cameras. This task must deal with appearance changes caused by variations in illumination, a person’s pose, camera viewing angle and background clutter. State-of-the-art approaches usually focus either on feature modeling – designing image descriptors that are robust to changes in imaging conditions, or dissimilarity functions – learning effective metrics to compare images from different cameras.

Typically, with novel deep architectures both approaches can be merged into a single end-to-end training, but to become effective, this requires annotating thousands of subjects in each camera pair. Unlike standard CNN-based approaches, we introduce a spatial pyramid-like structure to the image and learn CNNs for image sub-regions at different scales. When training a CNN using only image sub-regions, we force the model to recognize not only the person’s identity but also the spatial location of the sub-region. This results in highly effective feature representations, which when combined with Mahalanobis-like metric learning significantly outperform state-of-the-art approaches.

You’re probably wondering what this all means. To put it simply, instead of identifying the full face of a person, the video surveillance software only identifies small rectangular sub-regions (patches) of a person’s face.

This allows for easier identification and tracking in poor lighting and background conditions and different camera angles due to the model recognizing not only the person’s identity, but also the spatial location of the sub-region.

After experimenting with the software, the research team found that the deep spatial pyramid software was more effective than previously used detection systems.

While park-goers may appreciate Disney’s focus on improving security, there will no doubt be backlash over privacy concerns.

The New York City Police Department was sued this past May for not releasing documents related to its use of facial recognition technology.

Concerns over privacy are at an all-time high. Are you comfortable with giving up privacy for more efficient security?

You can view the full Disney research paper here.

Tagged with: News Video Surveillance

About the Author

Contact:

Steven A. Karantzoulidis is the Web Editor for Security Sales & Integration. He graduated from the University of Massachusetts Amherst with a degree in Communication and has a background in Film, A/V and Social Media.

Security Is Our Business, Too

For professionals who recommend, buy and install all types of electronic security equipment, a free subscription to Security Sales & Integration is like having a consultant on call. You’ll find an ideal balance of technology and business coverage, with installation tips and techniques for products and updates on how to add sales to your bottom line.

A free subscription to the #1 resource for the residential and commercial security industry will prove to be invaluable. Subscribe today!


Leave a Reply

Your email address will not be published. Required fields are marked *

Get Our Newsletters
Sammy Awards