Peace of mind on match day: facial recognition solution at the football stadium

Due to the aggressive behaviour of just a limited number of heated supporters, regular fans and those with young family members are often scared away from going to the stadium to watch matches. In the summer of 2019, Panasonic introduced a facial recognition system at a football stadium in Denmark that was dealing with this problem. By entrusting the high-precision system to identify and stop known troublemakers from entering, a process which was conventionally done manually by security staff at the entrance gates, the stadium has become a safer place where anyone can watch matches with peace of mind.

Brøndby IF is a professional football club in the Danish Superliga. At Brøndby IF’s stadium, Panasonic has installed “FacePRO,” a deep-learning facial recognition system.
This system leverages Panasonic’s 60+ years of security system technology and 30 years of Panasonic developing image sensing technology to combine security cameras equipped with the “Best-Shot” function and the high-precision deep-learning FacePRO facial recognition software.

Photo: The face of a person wearing a hood and a cap is recognized and surrounded by a red square.

Individuals who have been caught breaking the stadium rules receive a ban from coming back to games, and are registered on a blacklist. Brøndby IF has an average home game attendance of roughly 14,000 people, with up to 100 people registered on the blacklist at any given time. In the past, the security staff at the entrance gates prevented them from entering the stadium through visual checks but this manual approach had its limits, and it was difficult to stop every person, especially individuals who attempted to circumvent security by wearing disguises to avoid being recognised.
Faced with this issue, Panasonic spent approximately two years working with the club to develop a facial recognition system that could meet the stadium’s needs. When the system matches a face at the gate to someone who has been registered on the blacklist, a real time notification is seen by staff in the stadium surveillance room., A manual inspection is done to confirm its accuracy, then a message is sent to the security staff at the entrance to stop the individual before they can proceed through the gates. Through this, a strong security procedure has been established with a multi-check system comprised of the facial recognition system and security staff.

Photo: Message being sent from the surveillance room to the security staff’s terminal at gate to prevent a suspicious person from entering the stadium.

The final solution integrates Panasonic’s proprietary technology in the camera and the software that analyses the facial images.

On the camera side, Panasonic’s “Best-Shot” function is utilized to automatically select the best facial images for analysis, even in situations with insufficient light. Only the best images suitable for facial recognition are selected and sent to the server from the multiple facial images obtained of the same person. This enables a large number of faces to be processed without overloading the network, and contributes to cost reduction of the entire system.

Only images suitable for facial recognition are sent to the server.

Reducing server load by only sending images suitable for facial recognition to the server from the images shot with the camera.

On the software side, the world’s highest-level*1 of facial recognition performance has been achieved with the facial image analysis algorithm. The software enables extremely precise checks even outdoors where the lighting tends to be extreme, or with angled views of the face. The accuracy of the system allows for faces that are turned 45 degrees either side, or 30 degrees up or down. It is also capable of detecting a match in situations where the face is difficult to distinguish with the human eye due to aging (equivalent to 10 years), or even when the face is partially concealed by sunglasses or a mask.

The world’s highest-level recognition performance using deep learning technology

Image: Facial images will be analyzed with deep learning technology and similarity calculation to identify the person.

Compatible with various conditions

Image: High-precision verification is possible under various conditions, such as when the facial direction is 45 degrees horizontal and 30 degrees vertical, when the face is partially concealed by sunglasses or a mask, and changes in appearance over time.

*1 Evaluation points from the official evaluation report of the National Institute of Standards and Technology (NIST) as of May 9, 2017: https://www.nist.gov/programs-projects/face-challenges (The IJB-A Face Verification Challenge Performance Report, The IJB-A Face Identification Challenge Performance Report). This technology has been published as a paper. https://arxiv.org/abs/1704.00438

Photo: Computer screen showing the facial recognition system deleting photo data.

Another issue that had to be addressed at a stadium where many visitors gather was the new GDPR*2 regulations that were put into place to protect personal data within the EU. After a series of in-depth discussions with Brøndby IF, the risk of information leakage was prevented by developing a mechanism that both encrypted the data from the camera and purged data of people not registered on the blacklist after verifying a non-match., Additionally the list of registered banned individuals was strategically housed on a server that was orphaned from the Internet and all other external systems.

*2 GDPR (General Data Protection Regulation):
A regulation adopted by the European Parliament, European Council and European Commission intended to enhance and integrate data protection and privacy for all individual citizens of the European Union. Extensive and strict provisions are set in place regarding the processing and transfer of personal information.

With the introduction of this system, Brøndby IF’s family-friendly stadium has become an even safer place for fans of all ages to enjoy matches with peace of mind. Also, the reduced burden on the security staff has allowed them to divert resources to providing improved fan support services.
Panasonic continues to work on new applications including facial recognition solutions for monitoring important public facilities, building entrance management, and passport control at airports, contributing to a safer and more secure society.

Photo: A child cheering.
Image: A Better Life, A Better World

Contact

Panasonic Corporation
Groupwide Brand Communications Division
Contact [Global Site]