Vertical solution: Advancements in analytics enhance airport surveillance

Due to the strict regulations for safety and air travel, airports require comprehensive security technology. To meet these requirements, the world’s largest airports use some of the most advanced technologies available — some of which are centered around video surveillance.
Izvor: a&s International
E-mail: redakcija@asadria.com
Kategorije za web: Transport, video surveillance, Software, Access Control

Airports today are more focused on security than ever before. The number of attacks on airports in recent years have only further highlighted the need to better protect passengers and staff, even the reputation of the airports themselves. In terms of video surveillance, in the past it has been used as a source of video verification or observation into what has happened, but it has since become an essential source of data, too.

Developments in Analytics
Video analytics are in high demand at airports. With so many cameras to monitor, video surveillance that works with advanced video analytics to proactively identify potential threats is critical to the success of a security plan. Furthermore, these technologies can help operators identify the most critical information at any given time.

“Powered by sophisticated, computer- based algorithms, these advanced analytics incorporate neural networks and deep learning to imitate a human’s ability to recognize, allowing the technology to adapt to and learn from new situations,” said Alan Stoddard, VP and GM of Situational Intelligence Solutions at Verint. “These innovations open up new doors to airports because they can deliver the accuracy and scalability required to support advanced recognition in real-world environments with heavy traffic and diverse popula- tions, rather than relying on one-to-one scenarios.”

Jumbi Edulbehram, Regional President of Americas at Oncam, pointed out how airports are a notori- ously difficult environment for traditional analytics to work well. However, nowadays with machine learning-based analytics things are changing.

Machine-learning based analytics are capable of learning what is “normal” in a scene over time and raising an alert when something is out of the ordinary, such as people going the wrong way, bags left unattended for a period of time, etc. This is making it much more valuable. “These analytics may also be able to identify behaviors/anomalies in the scene that had previously gone unnoticed, which could be useful for airport security or even for operational efficiencies,” Edulbehram added.

Maarten Wings, Global Vertical Manager Airports at Bosch Building Technologies, highlighted how video analytics can be configured to recognize changes in speed (running), shape (crouching) or aspect ratio (falling), all of which can be very beneficial to airports.

“With the recent addition of machine learning capabilities Bosch cameras can now be trained to recognize objects or situations that matter most to airport customers. This is important consid- ering that in today’s market there is no ‘one-size-fits-all’ when it comes to protecting people and property or delivering data for business intelli- gence,” Wings explained. “Now video cameras can be taught to recognize and detect stationary objects or certain situations instead of being triggered by motion alone. With this, video metadata is further enriched and delivers data when objects are present, but also once they have been removed, therefore providing more informative data.”

More Accurate Face Recognition
The advancements in machine learning and artificial intelligence (AI) are enabling analytics like face recognition to deliver highly accurate, automated and intelligent identification capabilities in mission-critical security applications like airports.

“Greater accuracy in facial recognition is obviously very beneficial at airports where correct identification of passengers, staff, etc., is critical. Some airports/ airlines have already started using facial recognition to identify passengers boarding flights, while others are using it as a biometric for access to restricted areas at the airport,” Edulbehram said.

Benjamin Low, VP of APAC at Milestone Systems noted that face recognition is also being used as another form of authentication for border control, passport and security access; tracking of black- and white-list individuals; speedy clearance in congested places; and real-time matching.

Need for Improved Situational Awareness
Video surveillance today still requires intensive manual labor. This leads to a higher number of errors since humans are not very good at attentively watching video for a long time, which in a critical location like an airport can have major consequences. Modern video management systems, however, can reliably bring forward incidents to operators and ideally enable prevention of incidents.

David Lenot, Airport Practice Lead at Genetec, noted how greater camera perfor- mance and resolution, higher computational power, AI, neuronal networks, etc., are all helping deliver more in-depth insights and improving situational awareness.

“In today’s complex risk environment, airports require solutions to help enhance risk management, boost operational efficiency and improve situational awareness. In particular, situational awareness software platforms can deliver significant benefits. These systems help stakeholders gain critical insight into an airport’s security operations — both physical and cybersecurity systems — to help protect infrastructure and build analytical data,” Stoddard said.

“By collecting actionable intelligence from any number of sensors, such as video surveillance, open source web intelligence, crowdsourcing, weather sensors, mobile locations and more, leaders are empowered to manage and respond to situations efficiently and share information easily with multiple agencies, employees, citizens, aligned agencies and first responders,” Stoddard added. “Moreover, by creating a single enterprise-wide view across disparate systems and technologies, these solutions can help airports improve response times, lower operational costs, and increase operational efficiencies.”

Improving situational awareness also involves ensuring that every nook and cranny of a facility is covered by video, without blind spots. This, according to Edulbehram, is what many airport customers most want.

“Many airports have opted to strengthen their video camera arsenal with panoramic technology — both through 180- and 360-degree cameras. Think about the expansive areas of an airport, such as long corridors connecting terminals, large areas with baggage claim carousels or spacious boarding areas — all of these areas require extensive coverage that a traditional pan-tilt-zoom (PTZ) camera cannot reach without units that are pointing in every direction. Instead, airports are uniquely suited to panoramic cameras that can maintain situational awareness in these vast areas and help officials track individuals to critical choke points, where narrow field-of-view cameras can help identify persons of interest in an investi- gation,” Edulbehram explained.

Major Challenges
Airports today face a massive increase in passenger counts. Not only this, but high volumes of luggage, public and employee access, and the vast size of these facilities can pose problems for integrators when implementing video surveillance solutions. Furthermore, wide-open spaces around a perimeter and large passageways from terminal to terminal can present a significant challenge for video coverage.

“These challenges have only grown over the years, with the requirements of meeting federal regulations set forth by countries around the world on how long to keep surveillance video, which parts of an airport should be under surveillance, and how the video is used,” Edulbehram said.

Low said, “We often see older airports tearing out entire surveillance solutions because the legacy approach to using one brand of camera/software to try to fit an extremely challenging environment is no longer valid.”

Making the best use of existing infrastructure at airports means they are often very dynamic environments and physical infrastructure is constantly changing. “As a consequence, a lot of construction works are going on which need to be monitored from the control room. This also asks for frequent adaptation of the video security system (e.g., changing field of view or focus of a camera),” Wings said.

“Today a field technician is ordered to make the changes and while doing so he often disturbs the operational environment with a crane or ladder to work on the camera. Embedded remote commissioning and configuration features, which are available in the latest camera models, allow adaptation from a remote location without the need of a ladder or crane. It is done either from the ground with a smartphone or tablet application or from the configuration software on a PC somewhere remote,” Wings explained.

Lighting is also a common surveillance challenge at airports, and can especially affect analytics such as facial recognition. To combat this, in an airport environment (especially indoors), lighting conditions can be better controlled and there can be more trials on camera and angle deployment that allow for reduction of false positives, Low advised.

Lenot added, “Indoors, where lighting is mostly controlled, constraints are mostly related to the expected design/ aesthetic expectations of architects and the nature of the construction material such as glass, wood or aluminum that should not be altered by visible sensors/ devices. Finally, when used for video analytic purposes, camera locations must be selected very carefully to enable the analytic to perform at the expected quality level.”

Outdoor airport conditions can also be very challenging. However, camera vendors are now offering a greater variety of very wide angle, panoramic, multisensor cameras that improve visual coverage and may limit the burden of installation and deployment by limiting the number of cameras and the required cabling civil engineering work, according to Lenot.

Cybersecurity risks are also becoming more prevalent. Wings noted that video security solutions should offer the latest hardware and software measures to ensure data security and privacy protection at the highest level and data security should be approached end-to- end.

“This involves that communication can only be allowed between trusted devices, data must be encrypted both in-transit as well as stored, user access rights can be easily managed, and PKI (public key infrastructures) can be supported,” Wings said.

Evolving Future Challenges
As the security needs of airports continue to evolve, the need for more advanced technologies will become increasingly crucial to airport surveil- lance. Especially in today’s age of IoT and connected everything, cybersecurity risks will only become more of an issue. However, with more advanced analytics, better camera technology and improved situational awareness, airports will be safer than ever.

What to Look for When Choosing a Vendor

Airport security operations must incorporate a number of systems from a variety of manufacturers in order to achieve the type of coverage necessary to ensure the security of the entire facility. That is why choosing the right security vendor is important.

Video surveillance is just one of the many systems necessary for airport operators and security departments to deploy to have a comprehensive security solution. According to David Lenot, Airport Practice Lead at Genetec, nowadays, these entities are also expecting system platforms that unify all underlying systems, as well as the technical complexity to actually offer a human interface that grants: optimum situational awareness; stream- lines and support decision making; delivers insights to support process monitoring or incident resolution; and most importantly to improve the overall performances.

“The security vendors must have the distinctive abilities to select individual systems, sensors and devices, but also to master all aspects of IT, including servers, networking and software. And beyond technology and technics they must understand how an airport operates to help define workflows and standard operating procedures,” Lenot explained.

Maarten Wings, Global Vertical Manager for Airports at Bosch Building Technologies, explained that vendors should ideally be able to cover multiple security domains (e.g., video systems, intrusion, access control, management software, cloud services, etc.). Additionally they should be able to deliver future-proof solutions that can be regularly updated to ensure latest data protection and functionality; offer solutions that approach data security end-to-end and built-in intelligence (video analytics) to enable security operators to collect important statistics to further improve their levels of security.

“It can go without saying that all these capabilities and functionalities are seamlessly integrated with third- party vendors since there is no one-size fits all,” Wings said. “Airports are in intense competition with each other. Queues shall be short, travel at the airport transparent while at the same time gate turnaround times need to be short to keep airlines contracted. All within a safe environment as nobody flies from an unsafe airport. Airports need to optimize and in order to do so they need data to analyze, learn and optimize. Airports need a vendor with a clear digital strategy so they can make the transition toward the digital airport.”

It is also important to remember that different camera vendors often have advantages in outdoor, indoor, control room, etc., and customers should choose the best solution/vendor for their deployment, reminded Benjamin Low, VP of APAC at Milestone Systems.

How Airports Benefit From Analytics on the Edge

Video analytics at the edge allows every network video surveillance camera to be smart and understand what it sees. In an airport environment, this allows for operators, security staff and other users to be alerted to potential threats or situations the moment they happen.

Improved camera technology and advance- ments in analytics have made analytics at the edge a more viable option. At airports, edge analytics can, for example, detect counter flow on an escalator or a group forming in unusual places or a person or car near the perimeter fence.

“Built-in video analytics allows users to retrieve the right footage from hours of stored video instantly, analyze the scene by providing all kinds of statistics (metadata), and take appropriate action faster, easier and more efficiently,” said Maarten Wings, Global Vertical Manager for Airports at Bosch Building Technologies.

“With built-in video analytics it is possible to set certain alarm rules, such as someone approaching or climbing over a fence, someone loitering at the parking lot, or objects left behind in a certain area like a box blocking the emergency exit,” he explained. “Operators in the control room will be alerted the moment one of these alarm rules is met.”

This is different to what can already be detected today. “When data of multiple cameras is aggregated statistics like counting metrics, crowd density and other information can be used to inform passengers about waiting times, or other relevant information beyond security,” he added.