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. Recognising images, including video images, is a big focus of AI. In the past, you needed programmers to spend months telling a computer how to recognise 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 optimisation). 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 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 licence 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 recognising 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 recognising 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 pavement, 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 realise 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 realisation of that impact over the next few years will be fascinating to watch.
The key driver to growth in the IP market is the effectiveness and efficiency of the technology Technological advances in video surveillance are allowing end users the flexibility to do more with their systems than previously imagined. 2014 saw several new technological trends that shaped the future of the security market, with 4K and cyber security being the main drivers. The drift continues this year too with end users demanding HD video surveillance and wide-spread implementation of video analytics. Studies show that new technologies in both these areas are being assessed and adopted. Adding value via HD surveillance and video analytics That is the view of Willem Ryan, director of product marketing at Canadian based manufacturer, Avigilon. He thinks it’s a very interesting time in the security market with two factors driving it – the increased need for and development of high definition surveillance, and the resurgence of analytics. “Now 4K (8 megapixels) is part of the conversation, and we are seeing analytics making a resurgence. A few years ago analytics was over-hyped and under-delivered. Now it’s quickly becoming part of a system.” “The idea is to get all the evidence and detail you need in one image. This enables our end users to make quick decisions and capture footage that is immediately actionable”, says Willem Ryan, director of product marketing at Avigilon “Using analytics beyond security and using it as a business tool are very exciting. Video surveillance becomes dual-purpose or even multi-purpose. So a security department that faces the challenge of being a cost centre is now transformed into a value centre.” Need for an IP-oriented approach Ryan says we are also seeing more integration of access control and video verification of alarms. “To have those integrated tightly is a good thing. Another example is managing doors and identities over IP. Our products have to work together with IT security. You need to have the technology to play well within that IT ecosystem.” According to Ryan, the debate over IP or analogue is over. While analogue is still out there, now the question is: What is the most effective way of implementing IP? “People want the power and benefit of IP with the ease of installation of analogue.” There is less of a learning curve for installers, says Ryan, allowing them to offer all the benefits of IP, such as high definition. In Ryan’s view, the key driver to growth in the IP market is the effectiveness and efficiency of the technology. Together with the reduction in storage costs, people can monitor more of their premises than is presently the case. Mobile is also important; chief security officers are demanding access to video while they are out of the office – the idea is that the connection to your security is in the palm of your hand Improving access to security systems In the consumer market, people expect high definition video. That feeds through to the security surveillance market creating a demand for better and better resolution. Mobile is also important, says Ryan; chief security officers are demanding access to video while they are out of the office – the idea is that the connection to your security is in the palm of your hand. At an earlier media event, Avigilon demonstrated its new 7K HD Pro camera, said to be the industry’s first single-sensor 7K camera. “The idea is to get all the evidence and detail you need in one image. This enables our end users to make quick decisions and capture footage that is immediately actionable,” said Ryan. HD data processing challenges “For Avigilon, we believe in innovation and that analytics and high definition should be available to all. Doing that fast enough is a great problem to have but is a challenge. We’ve been one of the fastest growing companies in the industry, but we still find people who have never even seen the benefits of high definition video.” But higher definition means more data, which means more of a challenge to manage all that data. ‘Infobesity’ is a term that Avigilon sometimes uses, and to counter that you need a system that delivers the right information at the right time. Finding the best way to do that is a great challenge, concludes Ryan.
When asking exhibitors at IFSEC International 2015 about what drives their markets, many cite system integration as a key factor. And they want more of it. Integration as business “driving force” For example, John Davies of TDSI says customers are now seeking out system integration. “They want a solution rather than components, such as linking access control with building management systems or with an organisation’s IT network to control access to its computers,” he says. Suprema – a specialist in fingerprint biometrics based in South Korea – is also reaping the benefits of a drive towards greater integration. Baudouin Genouville, global alliances and integration manager, says the main driver for their business is the integration of the company’s fingerprint readers with third-party access control software. “This is possible because we provide an SDK (Software Development Kit), and the industry understands it well. The more people who know your SDK, the more integration there is. Another example of integration is that we can embed our BioStar2 software in a NVR to run access control – that is what I mean by integration. Every year I come to IFSEC I see the trend towards more integration. This is a big trend and won’t change,” says Baudouin Genouville. TDSI’s John Davies says Europe was in the doldrums until three or four months ago, but is starting to show promise. The UK market is buoyant with sales up 10% while the Middle East, Southeast Asia and China are very buoyant Video and access control integration According to video solutions company Avigilon, we are also seeing more integration of access control with video surveillance. An example is video verification, according to Willem Ryan, director of product marketing. “To have video verification of alarms, for example, to have those integrated tightly is a good thing. Another example is managing doors and identities over IP. Our products have to work together with IT security. You need to have the technology to play well within that IT ecosystem.” At video specialists Wavestore, integration is their raison d’etre. “With a truly open platform, what we do well is to bring disparate technologies together. We can put it all together and run it seamlessly," says James Smith, director of marketing. Market trends At IFSEC International, exhibitors also share their views on the wider security market and technological trends. TDSI’s John Davies says Europe was in the doldrums until three or four months ago, but is starting to show promise. The UK market is buoyant with sales up 10% while the Middle East, Southeast Asia and China are very buoyant. “There are a lot of infrastructure projects going on in China. All in all, we are experiencing double-digit sales growth since 2012.” A few years ago, video analytics was over-hyped and under-delivered. Now it is quickly becoming part of a system, and is being used beyond security as a business tool Avigilon’s Willem Ryan says it’s an interesting time in the security market, and it is being driven by the increased need for and development of high-definition surveillance, with 4K (8 megapixels) being “part of the conversation”. We are also seeing a resurgence in video analytics, says Ryan. A few years ago, video analytics was over-hyped and under-delivered. Now it is quickly becoming part of a system, and is being used beyond security as a business tool, with the security department being transformed from a cost centre to a value centre. He goes on to say that the consumer market now expects high-definition video, so that creates a demand for better and better resolution in the surveillance market. IFSEC exhibitors mostly agreed: Integration is critical in the development of new security solutions, while the growing presence of IP contributes to their ease of implementation.