Facial Recognition Cuts Checkpoint Congestion

February 20, 2019 Robert Moss

It’s a common experience. It seems like everyone arrives at work at the same time—just to queue up at the security gate and park their cars. It’s an annoying way to start the day.

Picture a scenario where there’s almost no wait—allowing people and vehicles to flow smoothly through the checkpoint. New technologies make this possible.

While data security dominates the headlines, physical security, particularly at entrances and exits, deserves greater attention. Bad actors target large public and private venues. Extensive campuses and transport hubs, for example, are especially vulnerable. Once inside, unauthorized and even dangerous individuals can blend into the crowd and commit theft or more serious offenses.

That’s why many safety and security operations managers are looking for a better approach to streamline parking lot checkpoints.

More Power at the Gate

Developers are building the next generation of solutions that run algorithms at the edge and provide real-time, dynamic facial recognition. Such solutions improve gate access control and reliability—automatically issuing warnings if unauthorized individuals attempt to enter.

Today’s facial recognition security systems must have the compute speed and power to rapidly process large volumes of data at the edge. They must also function in extreme conditions. And the equipment requires a compact design that works without fans. All of this demands sophisticated design and engineering in every system component.

Shenzhen Seavo Technology Co., Ltd. recognized that faster and higher-performing processors could satisfy those requirements. This led the company to choose Intel® technology. Intel solutions enable the accelerated processing and graphics performance needed to make edge-based face recognition a reality.

The Seavo Real-Time Face Recognition Gate Access Control Solution can achieve face recognition in just 0.2 seconds with a 99% accuracy rate. And it does not hog bandwidth since there is no need to upload tremendous volumes of data to the cloud for processing and analysis. It matches in real time the face of an approved or “white listed” individual and signals an alarm when an unauthorized person tries to enter.

Securing a Prominent University

Fudan University deployed the Seavo solution at its campus in Shanghai, China. The school, founded in 1905, is one of the most prestigious in the country.

The campus occupies 604 acres in the middle of Shanghai. It has an academic and administrative staff of more than 5,000 and approximately 33,500 students. Drivers can enter the campus through just six gates and checkpoints. In addition to its size, nearly 50 national government and ministerial labs are located at Fudan, making security even more critical.

Fudan University deployed the Seavo Real-Time Face Recognition Gate Access at its entrance checkpoints—reducing its trespasser intrusion rate. The system enabled Fudan’s security department to devote its energy to increasing safety and screening visitors, while speeding the movement of authorized employees and students.

“We use AI, machine learning, and the IoT to allow permitted personnel to quickly pass through security gates without showing ID,” explained Jason Jiang, Marketing Manager at Seavo.

“This reduces congestion while increasing security. Any visitor whose face is not in the database is automatically flagged, prompting security staff to stop and ask them for identification,” Jiang said.

Taking a Closer Look

Seavo’s unique solution consists of a Face Recognition Host on an edge device connected to an IP camera that gathers facial images. Intel® Core technology enables real-time facial detection and identification at the network edge.

“It’s preloaded with multi-feature facial recognition AI algorithms that help support gate access control and issue preemptive threat warnings,” said Jiang.

The Intelligent Face Recognition Server System facilitates remote updates of the custom face database at the edge and connection to the Cloud Platform (Figure 1).

Figure 1. Processing data at the edge enables the Seavo Real-Time Face Recognition Gate Access Control Solution to rapidly analyze data.

Unlike other systems, the solution uses One-to-Many (also known as I:N) Identification, which compares a new image of a person’s face with numerous images in its database each time he or she attempts to pass through a security gate.

This type of classification management is designed to deliver a higher degree of accuracy in confirming an individual’s identity.

Two types of software are used in the system. A Real-Time Face Recognition Program controls gate access using TCP/IP, and is based on a multi-feature algorithm. And a Unified Management Web System runs on Microsoft Windows, making it simple for IT to deploy.

The Seavo solution enables clear organizational benefits as shown in Figure 2.

Figure 2. Security and surveillance enable key use cases.

On the topic of customization and scalability, Jiang said that the solution enables organizations to gain security with the fewest resources: “They can deploy one- or two-way access control to monitor people going in, or people going both in and out. And they can select only the equipment and level of security necessary, to avoid paying for more than they need.”

Security That Enhances Business

To increase security while decreasing friction at entry and exit points, many organizations will turn to scalable and customizable systems, such as the face recognition system built by Seavo.

“We want to help our customers let authorized individuals rapidly pass through their gates, while preventing intruders from getting in,” said Jiang. “Our simple process does that and it prevents long lines, which create additional security risks.”

The bottom line: IoT, AI, and machine learning empower security staff to concentrate on screening visitors. And employees and students have a better experience when passing through parking checkpoints.

About the Author

Robert Moss

Robert Moss is an independent consultant and strategist who focuses on the value gained through IoT, AI, machine learning and other technologies. He also helps give voice to executives at leading technology companies, enabling their personal stories to show how they encourage innovation, overcome obstacles, and improve their leadership skills. Tweets @RobertMoss_IoT

More Content by Robert Moss
Previous Article
Top IoT Conferences of 2019
Top IoT Conferences of 2019

From CES and MWC to embedded world and Hannover Messe, here are our top IoT conferences for 2019. Check it ...

Next Article
Accelerate AI and Vision Designs in Edge Compute
Accelerate AI and Vision Designs in Edge Compute

Deep learning (or AI) can be a boon to IoT edge systems that collect massive amounts of data. But to be tru...

×

First Name
Last Name
Your Company
Phone Number
Country/Region
Subscribe To Intel Updates
Subscribe To Alliance Partner Updates
By submitting a form on this site, you are confirming you are an adult 18 years or older and you agree to Intel and Intel® IoT Solutions Alliance members contacting you with marketing-related emails or by telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.
I would like to be contacted by: - optional
Your contact request is submitted.
Error - something went wrong!
×

Stay up-to-date with the latest IoT news.

Country/Region
Subscribe To Intel Updates
Subscribe To Alliance Partner Updates
By submitting a form on this site, you are confirming you are an adult 18 years or older and you agree to Intel and Intel® IoT Solutions Alliance members contacting you with marketing-related emails or by telephone. You may unsubscribe at any time. Intel's web sites and communications are subject to our Privacy Notice and Terms of Use.
Subscribed.
Error - something went wrong!