Artificial Intelligence (AI) trends in physical security systems

Download PDF version

If you’ve been paying attention over the last twelve months, you will have noticed that deep learning techniques and artificial intelligence (AI) are making waves in the physical security market, with manufacturers eagerly adopting these buzzwords at the industry's biggest trade shows. With all the hype, security professionals are curious to know what these terms really mean, and how these technologies can boost real-world security system performance.

The growing number of applications of deep learning technology and AI in physical security is a clear indication that these are more than a passing fad. This review of some of our most comprehensive articles on these topics shows that AI is an all-pervasive trend that the physical security industry will do well to embrace quickly. Here, we examine the opportunities that artificial intelligence presents for smart security applications, and look back at how some of the leading security companies are adapting to respond to rapidly-changing expectations:

What is deep learning technology?

Machine Learning involves collecting large amounts of data related to a problem, training a model using this data and employing this model to process new data. Recently, there have been huge advances in a branch of Machine Learning called Deep Learning. This describes a family of algorithms based on neural networks. These algorithms are able to learn efficiently from example, and subsequently apply this learning to new data. Here, Zvika Ashani explains how deep learning technology can boost video surveillance systems.

Relationship between deep learning and artificial intelligence

There have been huge advances in a branch of Machine Learning called Deep Learning

With deep learning, you can show a computer many different images and it will "learn" to distinguish the differences. This is the "training" phase. After the neural network learns about the data, it can then use "inference" to interpret new data based on what it has learned. For example, if it has seen enough cats before, the system will know when a new image is a cat. In effect, the system “learns” by looking at lots of data to achieve artificial intelligence (AI). Larry Anderson explores how new computer hardware - the Graphic Processing Unit (GPU) – is making artificial intelligence accessible to the security industry.

Improving surveillance efficiency and accuracy with AI

The Graphic Processing Unit (GPU) – is making artificial intelligence accessible to the security industry

Larry Anderson explains how the latest technologies from Neurala and Motorola will enable the addition of AI to existing products, changing an existing solution from a passive sensor to a device that is “active in its thinking.” The technology is already being added to existing Motorola body-worn-cameras to enable police officers to more efficiently search for objects or persons of interest. In surveillance applications, AI could eliminate the need for humans to do repetitive or boring work, such as look at hours of video footage.

Intelligent security systems overcome smart city surveillance challenges

In surveillance applications, AI could eliminate the need for humans to do repetitive or boring work, such as look at hours of video footage

AI technology is expected to answer the pressing industry questions of how to use Big Data effectively and make a return on the investment in expensive storage, while maintaining (or even lowering) human capital costs. However, until recently, these expectations have been limited by factors such as a limited ability to learn, and high ongoing costs. Zvika Ashani examines how these challenges are being met and overcome, making artificial intelligence the standard in Smart City surveillance deployments.

Combining AI and robotics to enhance security operations

Artificial intelligence is becoming the standard in Smart City surveillance deployments

With the abilities afforded by AI, robots can navigate any designated area autonomously to keep an eye out for suspicious behaviour or alert first responders to those who may need aid. This also means that fewer law enforcement and/or security personnel will have be pulled from surrounding areas. While drones still require a human operator to chart their flight paths, the evolution of artificial intelligence (AI) is increasing the capabilities of these machines to work autonomously, says Steve Reinharz.

Future of artificial intelligence in the security industry

While drones still require a human operator to chart their flight paths, the evolution of artificial intelligence (AI) is increasing the capabilities of these machines to work autonomously

Contributors to SourceSecurity.com have been eager to embrace artificial intelligence and its ability to make video analytics more accurate and effective. Manufacturers predicted that deep learning technology could provide unprecedented insight into human behaviour, allowing video systems to more accurately monitor and predict crime. They also noted how cloud-based systems hold an advantage for deep learning video analytics. All in all, manufacturers are hoping that AI will provide scalable solutions across a range of vertical markets.

Download PDF version

People mentioned in this article

Larry Anderson

Zvika Ashani Agent Vi (Agent Video Intelligence)

Steve Reinharz Robotic Assistance Devices, LLC.

In case you missed it

Artificial Intelligence: A new weapon in the cyber security arms race

The cyber security threat is constant and real. Entire businesses, large enterprises and even whole cities have been vulnerable to these attacks. Growing threat of cyber attacks The threat is not trivial. Recently, two cities in Florida hit by ransom ware attacks – Rivera Beach and Lake City – opted to capitulate and pay ransom totaling more than $1.1 million to hackers. The attacks had disrupted communications for first responders and crippled online payment and traffic-ticketing systems. It was reminiscent of the $4 billion global WannaCry attacks on financial and healthcare companies. A full two years after the WannaCry attack, many of the hundreds of thousands of computers affected remain infected. And hackers are continuously devising new techniques, adapting the latest technology innovations including machine learning and artificial intelligence to devise more destructive forms of attack. Indeed, AI promises to become the next major weapon in the cyber arms race. For enterprises, there is no choice but to recognise the threat and adopt effective countermeasures Enterprise security For enterprises, there is no choice but to recognise the threat and adopt effective countermeasures. Not surprisingly, as the number, scale and sophistication of cyber-attacks has grown, so has the significance of the Chief Information Security Officer, or CISO, who owns the responsibility of sounding the alarm to the C-suite and the board – and recommending the best defense strategies. Consider it a grim irony of the digital economy. As companies have migrated to the cloud to gain scale and efficiency and integrated new channels and touch points to make it easier for their customers and suppliers to do business with them, they have also created more potential points of entry for cyber-attacks. IoT increases threat of cyber-attacks Amplifying that vulnerability is the trend of allowing employees to bring their own laptops, smartphones and other digital devices to the office or use to work remotely. And thanks to the Internet of Things, as more devices connect to enterprise systems – from thermostats to cars – the threat surface or targets of intrusion are multiplying exponentially. According to the McAfee Labs 2019 Threats Predictions Report, hackers will increasingly turn to AI to help them evade detection and automate their target selection. Companies will have no choice but to begin adopting AI defenses to counter these cybercriminals. Importance of cyber security This escalation in the cyber arms race reflects the sheer volume of data and transactions in modern life. In businesses like financial services and healthcare it is not humanly possible to examine every transaction for anomalies that might signal cyber snooping. Even when oddities are glimpsed, simply flagging potential problems can create so-called threat fatigue from endless false alarms. What’s more, attacks like those from Trickbots are specifically designed to go undetected by end users. The fact is, even if throwing more people at the problem were a solution, there aren’t enough skilled cyber security workers in the world. By some estimates, as many as 10 million cyber security jobs now go unfilled. AI is being used to conduct predictive analysis at a scale beyond human means Deploying AI As a result, AI is being deployed on multiple cyber-defense fronts. So far, it is mainly being used to conduct predictive analysis at a scale beyond human means. AI programs can sift through petabytes of data, identifying anomalies and even helping an organisation recognise and diagnose intrusions before they turn into catastrophic attacks. AI can also be used to continually monitor and allocate levels of access to a network’s multitude of legitimate users – whether employees, customers, partners or suppliers – to ensure that all parties have the access they need, but only the access they need. Countering cyber security threats To harden defenses, some AI programs can be configured to perform simulated war games To harden defenses, some AI programs can be configured to perform simulated war games. Because cyber attackers have stealth on their side, organisations might need dozens of experts to counter only a handful of attackers. AI can help even the odds, scoping out the potential permutations of vulnerabilities. As CISOs – and the CIOs they typically report to – advise C-suites and boards on their growing cybersecurity risk, they can also help those leaders recognize an enduring truth: AI programs cannot replace experienced cybersecurity professionals. But the technology can make staff smarter, more vigilant and more nimbly responsive. AI-based cyber security tools Financial and healthcare companies are leading this charge because of the sheer volume and variety of transactions they handle and because of the value and sensitivity of the data. Organisations like the U.S. Department of Defense and the space agency NASA, as well as governments around the world are also implementing AI-based tools to address the cyber threat. For businesses of all types, the threat stretches from the back office to the supply chain to the store front. That is why recognising and countering that threat must involve everyone from the CISO to the CEO to the Chairman of the Board. The AI arms race is underway in security. To delay joining it is to risk letting your enterprise become one of the grim statistics.

How are smart home systems impacting security?

Driven by technology developments such as voice recognition, smart devices and the Internet of Things, our homes are getting “smarter” all the time. Increasingly, we expect our residential environments to be responsive to our voice commands, whether we are adjusting a thermostat, turning on a light, or lowering the window shade. Smarter home integration yields new opportunities and challenges for home security, too, which contributes an element of safety and protection to the convenience aspects of smart homes. We asked this week’s Expert Panel Roundtable: How are new smart home systems impacting security?

viisights’ next generation of video analytics offer ‘behavioural understanding’

A video analytics system that provides ‘behavioural understanding’ can yield more meaningful and actionable data for a range of applications. In public safety and security, such a system can alert on violent or suspicious behaviours, such as people fighting, vandalism, people with weapons, etc. In advanced traffic surveillance and monitoring, it can provide alerts to vehicle collisions (accidents), traffic hazards or vehicle that aren’t using the road properly, such as a car that stops in the middle of the junction. For enterprise and campus security, it can provide advanced anti-tailgating and detect unauthorised activity. Video surveillance infrastructure viisights was founded by a group of entrepreneurs with track records in developing technology businesses These uses are among the benefits of viisights’ video analytics technology based on behavioural understanding of video content. “It means we can extract more meaningful data from the huge amount of video content that is captured, and we can transform that data to actionable insights that eventually justify the massive investment in video surveillance infrastructure,” says Asaf Birenzvieg, CEO of viisights. Their behavioural understanding systems for real-time video intelligence leverage artificial intelligence technology. viisights was founded by a group of serial entrepreneurs with track records in developing technology businesses. The Israeli company’s founders recognised a growing global need for intelligence to make physical and virtual public areas safer – and realised the role that smart video understanding technology can play. Developing artificial intelligence technologies viisights is committed to developing artificial intelligence technologies that facilitate human-like video understanding, which in turn serves as the basis for fully autonomous video intelligence systems powered by pattern prediction technology. “Behavioural recognition is the future of video analytics and the next generation of the object classification analytics systems that hold the majority of the market today,” says Birenzvieg. viisights has developed a video understanding technology for real-time video processing “To date most video analytics systems still base their product features on static analysis of objects from images using image recognition, even the ones that use ‘AI analytics.’ Products built using such object classification technology are extremely limited.” For example, object classification analytics cannot recognise behavioural events in a video such as people fighting or a car collision because such behaviours can’t accurately be concluded in large scale from analysing a single static image/frame. Video understanding technology viisights has developed a video understanding technology for real-time video processing. The technology can process live video feeds. In addition to recognising a particular object (e.g., person) and its attributes (e.g., red shirt), the system can understand an object’s actions, interactions with other objects (events), the scene being viewed (i.e., crowd is gathering, riots) and the context (a car is driving on the road or on the sidewalk). The main verticals are smart cities, enterprises and campuses, banks and ATM security “Basically, we are able to extract more meaningful data from a live video feed and therefore create actionable insights and greater ROI,” says Birenzvieg. The company focuses mostly on security and safety use-cases. The main verticals are smart cities, enterprises and campuses, banks and ATM security, security guard companies and transportation hubs. The company is working on a new product for in-vehicle monitoring mostly for security, safety, vehicle protection and proper vehicle use; it monitors passengers’ behaviour inside a bus, train, or taxi. The product will come to market next year. Video management system viisights’ video analytics offering is currently optimised for server-side deployment, and the integration architecture is similar to most video analytics systems. From one side it is integrated with the video management system (VMS). They are a Milestone verified partner and soon will be part of Milestone's marketplace. From the other end, it is connected to a command-and-control system for processing the data and presenting the alerts to the end-user. The analytics company makes most sales through system integrators. They have partnerships with big system integrators like Motorola Solutions and NEC and are also working with smaller ones. They are looking to expand their system integrator network, mostly in the USA and Europe. Behaviours can have many variations and they can be very diverse Cloud video surveillance “We will continue to invest in performance and accuracy, meaning higher recall and lower false positive rate,” says Birenzvieg. “Since our major value proposition is in behaviour recognition, behaviour events many times are not clearly defined, which is very different from object classification. Behaviours can have many variations and they can be very diverse.” An example is a simple behaviour like a person falling on the floor. A person can fall on the floor in many ways, but the challenge is to ignore similar behaviours that are not a person falling and that confuse the system, such as a person bending over to tie his shoelaces. With cloud video surveillance becoming a trend, viisights is also looking into offering some of their advanced functionalities in a video-analytics-as-a-service-model.