A technology poised to transform the physical security market is deep learning, which is a neural network approach to machine learning, differentiated by an ability to train using large data sets for greater accuracy. In effect, the system “learns” by looking at lots of data to achieve artificial intelligence (AI).

Phases Of Deep Learning

I heard a lot about AI, including how it can transform the physical security marketplace, when I attended NVIDIA’s GPU Technology Conference (GTC) in San Jose recently.  

Recognizing images, including video images, is a big focus of AI. In the past, you needed programmers to spend months telling a computer how to recognize an image. In deep learning, instead of programming the computer, you just show it many different images and it "learns" 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. In effect, if it has seen enough cats before, it will know when a new image is a cat.

Factors enabling AI

Deep learning and AI are fast-growing areas for a wide range of uses – physical security is just one. It is all made possible by the coming together of three factors. One is the availability of lots of data. This is the “big data” we have been hearing about; in effect, a proliferation of sensors (including video cameras) has produced a large enough mass of data to enable systems to be trained effectively. The second factor is the development of new algorithms to train neural networks faster, and the third is the availability of computer hardware (specifically GPUs, graphics processing units), that is capable of rapidly completing the involved calculations. NVIDIA manufactures those GPUs and sponsors the annual GTC conference, all about how they can be used more effectively.

“Deep learning is about teaching technology to understand the world around us in a way that is similar to how we understand it”

Deep learning and neural network computing is everywhere. It is now widely available in on-premises computers, in systems embedded in edge devices, and even in the cloud. The edge is particularly important in the video surveillance market, enabling systems to function despite any bandwidth or latency issues that would limit the effectiveness of a central server-based system. Edge-based functionality also limits concerns about the privacy of information, and eliminates dependence on the availability of 3G connectivity.

NVIDIA AI City Initiative

Video analytics applications fall under NVIDIA's “AI City” initiative, which they describe as a combination of "safe cities" (video surveillance, law enforcement, forensics) and "smart cities" (traffic management, retail analytics, resource optimization). Depending on the application, AI City technology must function in the cloud, on premises and/or at the edge. NVIDIA’s new Metropolis initiative offers AI at every system level, from the Jetson TX2 "embedded supercomputer" available at the edge, to on-premises servers (using NVIDIA’s Tesla and Quadro) to cloud systems (using NVIDIA’s DGX).

“AI City applications need an edge-to-cloud architecture,” says Jesse Clayton, Senior Manager, Product Management, Intelligent Machines, at NVIDIA. “Some applications, such as body cameras and parking entrance applications, have to have AI at the edge. But for other problems, you need to aggregate multiple sources of information, such as using AI on an on-premises server for hundreds of video cameras.”

The sheer volume of installed cameras in the world makes video an AI problem – more than 1 billion cameras worldwide by 2020 will provide 30 billion frames of video per day. The existing limitations of current video systems to adapt and function well in real-world conditions point to a need for better technology, as do the traditional shortcomings of video analytics systems. Video systems can achieve "super-human" results, identifying and classifying images using artificial intelligence.

NVIDIA’s Quadro GPU system enables Avigilon network video recorders (NVRs) to search simultaneously across hundreds of cameras to find images that are similar in appearance
NVIDIA’s GPU Technology Conference offered a chance for Avigilon to interact with others focused on AI

AI In Video Surveillance

AI is steadily making its way into video surveillance. Multiple security industry partners are using NVIDIA GPUs to boost the effectiveness of their systems. Many companies highlighted their initiatives at ISC West in April and again at NVIDIA’s GPU Technology Conference. Among them are Avigilon’s Appearance Search and BriefCam’s real-time video synopsis system. Hikvision uses the technology for a six-fold improvement detecting pedestrians in the rain, while Dahua is speeding up its license plate recognition system by five times. Other companies using the technology are UNV Uniview (vehicle classification), SeeQuestor (investigations), Xjera Labs (people and attribute detection) and Sensetime (object detection).

NVIDIA’s Quadro GPU system enables Avigilon network video recorders (NVRs) to search simultaneously across hundreds of cameras to find images that are similar in appearance, such as faces that match an example. The GPU’s fast and efficient processing power, available in a small and affordable form factor, provides a system that is scalable and cost-effective but can run complex algorithms to provide rapid results.

Beyond recognizing objects, the
system can also learn about how
objects interact in the environment,
and look for anomalies

“Deep learning is about teaching technology to understand the world around us in a way that is similar to how we understand it,” says Willem Ryan, Senior Director, Global Marketing at Avigilon. “What seem simple to us in terms of how we perceive the world is complex for a machine to do, but a machine learns faster. Deep learning allows you to teach a machine how to make connections that we make every day. Using GPUs, a system can make assumptions and calculations instantaneously.”

Beyond recognizing objects, the system can also learn about how objects interact in the environment, and look for anomalies or non-typical events. For example, if the system sees a car go onto a sidewalk, it could provide an alert.

How Will AI Develop?

NVIDIA’s GTC conference offered a chance for Avigilon to interact with others focused on AI, and to share Avigilon’s knowledge of the unique AI challenges of the video surveillance market. “This is the heart of the development of AI and deep learning,” said Ryan at the GTC conference. “To be involved and part of this is exciting to Avigilon, and we can expose people here to how AI can be used in a way they may not be familiar with. We have talked to people who didn’t realize how video surveillance happens currently, and how AI is changing it. “

“We want to continue to support the idea of GPU processing and how using it can make video surveillance solutions more effective, and change how people interact with video,” he added. “That’s where we see the impact. There have been challenges we have struggled to overcome in the security industry, and these are the breakthroughs that will help us overcome those challenges. So, we want to be at the forefront and involved in those discussions.”

The impact of AI and deep learning on the physical security industry is only beginning. The full realization of that impact over the next few years will be fascinating to watch.

Download PDF version Download PDF version

Author profile

Larry Anderson Editor, SecurityInformed.com & SourceSecurity.com

An experienced journalist and long-time presence in the US security industry, Larry is SecurityInformed.com's eyes and ears in the fast-changing security marketplace, attending industry and corporate events, interviewing security leaders and contributing original editorial content to the site. He leads SecurityInformed's team of dedicated editorial and content professionals, guiding the "editorial roadmap" to ensure the site provides the most relevant content for security professionals.

In case you missed it

What Are New Trends In Residential Security?
What Are New Trends In Residential Security?

Residential security and smart homes are rapidly changing facets of the larger physical security marketplace, driven by advances in consumer technology and concerns about rising crime rates. During the COVID-19 pandemic, many people spent more time at home and became more aware of the need for greater security. As workplaces opened back up, returning workers turned to technology to help them keep watch over their homes from afar. We asked this week’s Expert Panel Roundtable: What are the trends in residential security in 2021?

How Businesses Can Protect Their People In The New Age Of Work
How Businesses Can Protect Their People In The New Age Of Work

Ensuring employee health and safety remains a key priority for organizations this year, especially as we see COVID-19 cases continue to rise in different areas of the world. As an ongoing challenge, COVID-19 has shifted the priorities of many organizations. In fact, “improving health and safety for employees” is the top strategic goal this year of manufacturing and logistics organizations in the U.S. and U.K., according to research conducted by Forrester on behalf of STANLEY Security. But as we think about reopening and as hybrid workforce models and “workspace-on-demand” approaches rise in popularity, leaders need to consider implementing the right technologies to help ensure a safe return to the office. This means investing in health, safety, and security solutions that can help leaders protect their people. The intersection of security technology and health and safety There’s no doubt that the scope of security has expanded in the wake of the global pandemic. What was once an area governed by a select few security or IT professionals within a business has now become a crucial company investment involving many key stakeholders. The role of security has expanded to encompass a broader range of health and safety challenges for businesses Additionally, the role of security has expanded to encompass a broader range of health and safety challenges for businesses. Fortunately, security technologies have made significant strides and many solutions, both existing and new, have been thrust forward to address today’s biggest business challenges. Investment in security technology It’s important to note that businesses are eager to adopt tech that can help them protect their people. Nearly half (46%) of organizations surveyed by Forrester report that they’re considering an increasing investment in technology solutions that ensure employee safety. Technologies like touchless access control, visitor management systems, occupancy monitoring, and installed/wearable proximity sensors are among some of the many security technologies these organizations have implemented or are planning to implement yet this year. Facilitating a safe return to work But what does the future look like? When it comes to the post-pandemic workplace, organizations are taking a hard look at their return-to-work strategy. Flexible or hybrid workforce models require a suite of security solutions to help ensure a safer, healthier environment More than half (53%) of organizations surveyed by Forrester are looking to introduce a flexible work schedule for their employees as they make decisions about returning to work and keeping employees safe post-pandemic. Such flexible – or hybrid – workforce models require a suite of security solutions to help ensure a safer, healthier environment for all who traverse a facility or work on-site. One of the central safety and security challenges raised by these hybrid models is tracking who is present in the building at any one time – and where or how they interact. Leveraging security technology With staggered schedules and what may seem like a steady stream of people passing through, it can be difficult to know who’s an employee and who’s a visitor. Access control will be key to monitoring and managing the flow of people on-site and preventing unauthorized access. When access control systems are properly integrated with visitor management solutions, businesses can unlock further benefits and efficiencies. For instance, integrated visitor management systems can allow for pre-registration of visitors and employees – granting cellphone credentials before people arrive on-site – and automated health screening surveys can be sent out in advance to help mitigate risk. Once someone reaches the premises, these systems can also be used to detect the person’s temperature and scan for a face mask, if needed.  We will likely see these types of visitor management and advanced screening solutions continue to rise in popularity, as 47% of organizations surveyed by Forrester report that they’re considering requiring employee health screening post-pandemic. Defining the office of the future A modern, dynamic workforce model will require an agile approach to office management. It’s imperative to strike the right balance between making people feel welcome and reassuring Businesses want to create an environment in which people feel comfortable and confident – a space where employees can collaborate and be creative. It’s imperative to strike the right balance between making people feel welcome and reassuring them that the necessary security measures are in place to ensure not only their safety but also their health. In many cases, this balancing act has created an unintended consequence: Everyone now feels like a visitor to a building. Protocols and processes With employees required to undergo the same screening processes and protocols as a guest, we’ve seen a transformation in the on-site experience. This further underscores the need for seamless, automated, and tightly integrated security solutions that can improve the employee and visitor experience, while helping to ensure health and safety. Ultimately, the future of the office is not about what a space looks like, but how people feel in it. This means adopting a “safety-always” culture, underpinned by the right technology, to ensure people that their safety remains a business’ top priority. 

Access The Right Areas - Making A Smart Home Genius With Biometrics
Access The Right Areas - Making A Smart Home Genius With Biometrics

Household adoption of smart home systems currently sits at 12.1% and is set to grow to 21.4% by 2025, expanding the market from US$ 78.3 billion to US$ 135 billion, in the same period. Although closely linked to the growth of connectivity technologies, including 5G, tech-savvy consumers are also recognizing the benefits of next-generation security systems, to protect and secure their domestic lives. Biometric technologies are already commonplace in our smartphones, PCs and payment cards, enhancing security without compromising convenience. Consequently, manufacturers and developers are taking note of biometric solutions, as a way of leveling-up their smart home solutions. Biometrics offer enhanced security As with any home, security starts at the front door and the first opportunity for biometrics to make a smart home genius lies within the smart lock. Why? Relying on inconvenient unsecure PINs and codes takes the ‘smart’ out of smart locks. As the number of connected systems in our homes increase, we cannot expect consumers to create, remember and use an ever-expanding list of unique passwords and PINs. Indeed, 60% of consumers feel they have too many to remember and the number can be as high as 85 for all personal and private accounts. Biometric solutions strengthen home access control Biometric solutions have a real opportunity to strengthen the security and convenience of home access control Doing this risks consumers becoming apathetic with security, as 41% of consumers admit to re-using the same password or introducing simple minor variations, increasing the risk of hacks and breaches from weak or stolen passwords. Furthermore, continually updating and refreshing passwords, and PINs is unappealing and inconvenient. Consequently, biometric solutions have a real opportunity to strengthen the security and convenience of home access control. Positives of on-device biometric storage Biometric authentication, such as fingerprint recognition uses personally identifiable information, which is stored securely on-device. By using on-device biometric storage, manufacturers are supporting the 38% of consumers, who are worried about privacy and biometrics, and potentially winning over the 17% of people, who don’t use smart home devices for this very reason. Compared to conventional security, such as passwords, PINs or even keys, which can be spoofed, stolen, forgotten or lost, biometrics is difficult to hack and near impossible to spoof. Consequently, homes secured with biometric smart locks are made safer in a significantly more seamless and convenient way for the user. Biometric smart locks Physical access in our domestic lives doesn’t end at the front door with smart locks. Biometrics has endless opportunities to ease our daily lives, replacing passwords and PINs in all devices. Biometric smart locks provide personalized access control to sensitive and hazardous areas, such as medicine cabinets, kitchen drawers, safes, kitchen appliances and bike locks. They offer effective security with a touch or glance. Multi-tenanted sites, such as apartment blocks and student halls, can also become smarter and more secure. With hundreds of people occupying the same building, maintaining high levels of security is the responsibility for every individual occupant. Biometric smart locks limit entry to authorized tenants and eliminate the impact of lost or stolen keys, and passcodes. Furthermore, there’s no need for costly lock replacements and when people leave the building permanently, their data is easily removed from the device. Authorized building access Like biometric smart locks in general, the benefits extend beyond the front door Like biometric smart locks in general, the benefits extend beyond the front door, but also throughout the entire building, such as washing rooms, mail rooms, bike rooms and community spaces, such as gyms. Different people might have different levels of access to these areas, depending on their contracts, creating an access control headache. But, by having biometric smart locks, security teams can ensure that only authorized people have access to the right combination of rooms and areas. Convenience of biometric access cards Additionally, if building owners have options, the biometric sensors can be integrated into the doors themselves, thereby allowing users to touch the sensor, to unlock the door and enter. Furthermore, the latest technology allows biometric access cards to be used. This embeds the sensor into a contactless keycard, allowing the user to place their thumb on the sensor and tap the card to unlock the door. This may be preferable in circumstances where contactless keycards are already in use and can be upgraded. Smarter and seamless security In tandem with the growth of the smart home ecosystem, biometrics has real potential to enhance our daily lives, by delivering smarter, seamless and more convenient security. Significant innovation has made biometrics access control faster, more accurate and secure. Furthermore, today’s sensors are durable and energy efficient. With the capacity for over 10 million touches and ultra-low power consumption, smart home system developers no longer have to worry about added power demands. As consumers continue to invest in their homes and explore new ways to secure and access them, biometrics offers a golden opportunity for market players, to differentiate and make smart homes even smarter.