Download PDF version Contact company

ISC West, the world's largest security industry trade show, is just around the corner. This in-person show gathered more than 1,000 manufacturers and over 30,000 visitors from all over the world in 2019. On top of that, more than 200 brands exhibited at ISC West for the first time. This year's event promises to be just as exciting, if not more so. Let’s overview some leading security trends in video management systems development, and what's worth your time and attention at ISC West 2020.

AI analytics

Emerging two or three years ago, the AI-based video analytics market is experiencing a boom in growth. The prototypes and ideas displayed at ISC West 2019 could This year's event promises to be just as exciting, if not more soalready be part of a functioning system today. There's a lot of hype around this new trend. So, if you're looking for solutions for your needs, it is important to be able to tell the difference between technologies that work and marketing bluster. To do that, you have to understand what today's AI-based analytics (also often referred to as a neural network, deep learning, or machine learning) can and can't do.

Let's start with what AI can't do in video surveillance. It can't analyse the sequence in which events occur or understand the 'logic' of what's happening in the scene. In other words, there's no such thing as a 'suspicious behavior detection tool'. Nevertheless, neural networks are really good at recognising and classifying objects. For instance, they can distinguish humans from vehicles, vehicles from other moving objects, and cyclists from pedestrians.

Neural network trackers

This technology is primarily used as a neural network tracker or object tracker that can identify and track objects of a specific type. Usually, it's applied to complex scenes with a large amount of non-relevant details where a classic tracker would drown in false alarms. The neural tracker can be used to detect people in dangerous areas at production facilities, cyclists riding on pedestrian lanes, or poachers trying to sneak into a nature preserve.

Neural networks are really good at recognising and classifying objectsObject identification function can be used for other site-specific tasks, such as detecting people without a helmet or a high-visibility vest at facilities where those are required by safety regulations. It can also be used to detect fire and smoke in open spaces, or at big premises with high ceilings or active air circulation, where common fire alarm systems can't be used or may go off too late.

Behaviour analytics 

Behavior analytics is another field of analytics based on artificial neural networks. Even if recognising suspicious or inappropriate behavior is nearly impossible, it can detect risky situations based on human postures, such as an active shooter pose, raised arms, crouching, or man down. In addition to that, AI has been successfully used to perform facial and number plate recognition for quite some time now. Although these systems aren't new, their recognition quality improves each year.

Looking for solutions? You'll definitely find some interesting and new options from developers specialising in VMS and modular AI analytics at ISC West 2020.

Even if recognising suspicious or inappropriate behavior is nearly impossible, AI can detect risky situations based on human postures

Smart search

The ability to perform a quick, flexible search in a video archive is one of the most important features of a video surveillance system. In many ways, it's even more AI has been successfully used to perform facial and number plate recognition for quite some time nowimportant than real-time monitoring itself. Constantly keeping an eye out for what's happening onsite is the security service's job. Medium- to large-sized companies usually have that kind of department. Meanwhile, lots of small businesses and households use video footage to investigate accidents, resolve conflicts, or analyse employee's work. They generally don't need real-time monitoring, but video search is a crucial element.

The most basic search tools offer an interface that enables easy access to recorded video and event-based search (from video analytics, detectors, etc.). Smart systems with forensic search features that allow the user to set criteria enhance the system's search capabilities even more.

How it works 

VMS analyses the video as it is recorded and saves the resulting metadata to a database. In the most basic case, the metadata contains information about motion in the scene as well as the moving object's coordinates. When searching, you can select an area of interest within the frame and take a quick look at all video segments containing motion in this area. More advanced systems save the parameters of moving objects, such as their size, color, motion speed and direction. TThe ability to perform a quick, flexible search in a video archive is one of the most important features of a video surveillance systemYou'll quickly find what you're looking for by setting more precise criteria.

The first VMS with forensic search features appeared in the early 2010s. Since then, a growing number of users and VMS developers have recognised the importance of these tools. More and more manufacturers enrich their products with forensic search features, starting from basic search by motion detection.

Integrating search functions with AI

Recently, search technologies have gone even further by integrating search functions with AI analytics. Some systems are capable to recognise all faces and number plates captured by cameras and save them to the database. You can quickly find all videos containing an image of a person or a car just by searching a photo or a number plate across multiple camera archives at a time. One usage scenario for these systems can be seen in law enforcement deploying them to find suspects using CCTV cameras around the city.

Another option for integrating smart search and AI is searching by criteria based on a neural network tracker. When you use it, you can set object's size, color, motion speed and direction in the scene, as well as object's type (such as a human or a vehicle). So, if you need to find out when a red car appeared in the surveillance area, the system will show you only red cars while ignoring other objects like people in red clothes. This technology lets you find what you're looking for even faster.

If you or your clients use VMS primarily to record video, be sure to ask the manufacturers you'll talk to at the show what search capabilities they offer.

More advanced systems save the parameters of moving objects, such as their size, color, motion speed and direction

Hardware AI acceleration

High CPU resource consumption is one of the hardest challenges that stem from implementing a neural network–based video analytics system. This significantly decreases the number of cameras that can be connected to a server that hosts AI analytics. It also makes the system much more expensive.

AI technology lets you find what you're looking for even fasterThe solution is to use AI accelerators. GPUs and dedicated accelerator cards are used on servers to provide hardware acceleration for the neural networks' workload. These devices are mostly manufactured by Intel and NVIDIA. Intel also offers the OpenVINO™ toolkit, a software package for developers that helps distribute workload between CPU, GPU, and accelerators as effectively as possible using all available resources.

New solutions

Due to AI's growing popularity, lots of minor microchip manufacturers became interested in developing neural accelerator chips. The healthy competition will work in the market's favor, serving to stimulate tech development and cut prices. New solutions in the field were on display at ISC West 2019; they'll definitely be present at ISC West again in 2020. Developers specialising in VMS and modular AI video analytics should absolutely check these out.

But users should understand that it's impossible to build a cost-effective video surveillance system with significant number (10–20 and more) of AI analytics channels without using neural accelerators. That said, various accelerator models may significantly differ in price and power consumption. So, when you talk to developers specialising in VMS and AI analytics modules, ask what accelerator makes and models they support.

In conclusion

Whether you're an integrator looking for interesting VMS offers for clients or an end-user searching for solutions to your own tasks, check out what AI analytics can do. This sector is developing very fast and is continuously introducing new features that may be just what you're looking for. Incorporating forensic search in recorded video footage is key to building an effective video surveillance system for users, and important to creating a unique product offering for integrators. Needless to say, you can't build a cost-effective video surveillance system without using CPU resources wisely. If a system's functionality completely aligns with what you're looking for, ask what neural accelerator hardware it supports to correctly estimate the cost of your video servers.

Share with LinkedIn Share with Twitter Share with Facebook Share with Facebook
Download PDF version Download PDF version

Author profile

Alan Ataev Chief Sales and Marketing Officer, AxxonSoft

In case you missed it

The future of accommodation: when coliving and PropTech combine
The future of accommodation: when coliving and PropTech combine

As technology develops at an ever-faster rate, the possibilities for where and how new innovations can be used are endless. The property sector is one such area where new technology, such as smarter video surveillance, is being used to improve the quality of life for families and communities by increasing security as well as implementing changes based on new insights. Specifically for the coliving movement, cloud-based video surveillance is helping operators to improve the communal spaces for their tenants in ways that on-premises surveillance never could. From tighter security measures to better social spaces, here’s how coliving is benefitting from the PropTech (property technology) boom. What is coliving? The coliving movement is the latest iteration of a recurring human trend. The act of communally sharing space and resources while benefiting from a supportive community is something we’ve seen time and again throughout history. A place that everyone can call home addresses multiple needs. With the concept of shared spaces, and the possibility to work and socialise together, it’s no longer simply a trend. Specifically for the coliving movement, cloud-based video surveillance is helping operators to improve the communal spaces for their tenants in ways that on-premises surveillance never could. As living expenses become ever higher, for many – particularly younger – people getting on the property ladder is difficult, and renting an apartment alone can feel isolating. Coliving spaces offer a ready-built community, and many responsibilities – like maintenance, for example – lie with the building owners, and the cost is included. Where does PropTech come in? PropTech is dramatically changing the way people research, rent, buy, sell and manage property. The combination of the internet, huge compute power, cloud platforms and artificial intelligence (AI) have all combined to create technologies that are transforming the way the entire property sector works. Whether that’s helping buildings to operate more efficiently or even become more sustainable, PropTech is a sector that’s on the rise. When it comes to coliving, PropTech is helping to make these environments safer and smarter for the people who live there. One of the fundamental areas of building design is people’s safety. Following the past year where health has been at the forefront of everyone’s minds, PropTech is enabling entrance systems with touchless doorways and innovative ventilation systems, for example. And even without taking the pandemic into consideration, people living in shared spaces need to be confident that the security is well-managed, and the management wants to ensure that only tenants and their guests can enter the premises. How cloud video surveillance drives better coliving Once seen as an ‘add-on’ to building design, video surveillance and access control are now becoming increasingly important elements of the PropTech movement, and they are equally as desirable for coliving too. Surveillance cameras are essentially sensors that can monitor activity, patterns, and any other changes in a given environment. Analysis of video data can occur in real-time to effect changes immediately, or video can be stored and evaluated at a later date. In a coliving environment, a cloud-based video surveillance system can help operators to understand how tenants use their space, and implement changes to benefit them. Traditionally, video surveillance data stored on-premises had limited uses, as it was often only accessed after a security incident, such as a break-in. The video therefore wouldn’t be used frequently and the camera and storage system would just be another cost not yielding any ROI. Cloud technology has had a dramatic impact on video surveillance. Remote management delivers the ability to modify, adjust and perfect the system without needing to be present at the site, while remote monitoring alerts operators to any unusual incidents such as an equipment malfunction or breakage. In a coliving environment, a cloud-based video surveillance system can help operators to understand how tenants use their space, and implement changes to benefit them. For example, surveillance can show operators which areas in the communal spaces are frequented the most and at what times, including areas such as the laundry room or gym where space might be limited. By using AI to analyse the video, operators can use insights from it to improve the existing set up wherever possible, and also learn lessons about how to better design future co-living spaces. In today’s world, this technology can also help to keep everyone safe and healthy. Cameras can identify if someone is wearing a face mask as they go to enter a building and deny entry until they put one on. Thermal cameras are another easy tool to screen people for an elevated temperature before they even enter a communal space. Though a raised temperature does not mean you have COVID-19, the technology can provide an initial screening, so that individuals with elevated temperature readings can be checked manually for other symptoms or possibly be recommended for a test. The future of smart living Coliving is not a new phenomenon – humans have been living in communal places for many years, working and socialising together for the benefit of everyone. What makes today’s coliving movement unique is the range of rapidly developing technology that is being implemented to improve the environments for tenants. As an arguably lower cost and higher quality way of life, coliving spaces are certainly here to stay, and so the PropTech surge is no doubt going to grow with it.

How AI is revolutionising fraud detection
How AI is revolutionising fraud detection

The Annual Fraud Indicator estimates that fraud costs the United Kingdom approximately £190 billion every year. The private sector is hit the hardest and loses around £140 billion a year, while the public sector loses more than £40 billion, and individuals lose roughly £7 billion. The effects of fraud can be devastating on both individuals and organisations. Companies can suffer irreversible damage to reputation and be forced to close, and individuals can experience significant personal losses. Everyone should be aware of the risks and take steps to protect themselves against fraudulent activity. Fraud detection technology Fraud detection technology has advanced rapidly, over the years and made it easier for security professionals to detect and prevent fraud. Here are some of the key ways that Artificial Intelligence (AI) is revolutionising fraud detection - with insight from Tessema Tesfachew, the Head of Product at Avora. An anomaly can be described as a behaviour that deviates from the expected An anomaly can be described as a behaviour that deviates from the expected. According to Tessema Tesfachew, “Autonomous monitoring and anomaly detection specifically, have made detecting fraudulent activity faster and more accurate. Machines can monitor data 24/7 as it comes in, build patterns of behaviour that take into account seasonality and shifting trends, and identify events that don’t fit the norm.” For example, banks can use AI software to gain an overview of a customer’s spending habits online. Having this level of insight allows an anomaly detection system to determine whether a transaction is normal or not. Suspicious transactions can be flagged for further investigation and verified by the customer. If the transaction is not fraudulent, then the information can be put into the anomaly detection system to learn more about the customer’s spending behaviour online. Accurate root cause analysis Root cause analysis goes one step further than anomaly detection, by allowing security professionals to pinpoint what caused the anomaly. Tessema explains how an example of this would be if a system detects that the rate of fraudulent transactions has increased. Root cause analysis would pinpoint the specific ATM or point of sale, where this increase is occurring. Swift action can then be taken to prevent fraudulent activity at that location in the future. Fewer false positives As mentioned, false positives can occur if a fraud detection system identifies behaviour that goes against the norm, for instance, if a customer makes a transaction in a new location. In many cases, customers are required to complete identity verification to prove that a transaction is not fraudulent. Digital customer identity verification can help brands build a strong and reputable image. That said, forcing users to complete identify certifications regularly can cause frustration and harm the customer experience. AI anomaly detection AI fraud detection systems can carry out accurate data analysis in milliseconds and identify complex patterns in data AI anomaly detection is far more accurate and results in fewer false positives. Increasing the accuracy of anomaly detection helps companies improve customer relationships and build a strong reputation. This will have a positive impact on brand image and sales revenue. AI fraud detection systems can carry out accurate data analysis in milliseconds and identify complex patterns in data. Machines are more efficient than even the most skilled fraud analysts and make fewer errors. This is why AI fraud detection software is the preferred option in larger organisations. Importance of fraud analysts However, fraud analysts still play an important role in fraud prevention. Using a combination of human intervention and AI is usually the most effective approach when it comes to fraud detection. According to pymnts.com, innovative organisations now use a variety of AI and supervised and unsupervised machine learning to identify and protect against fraud. AI systems can complete time-consuming and repetitive tasks, such as data collection and analysis. This means that fraud analysts can focus their time and attention on critical tasks that require human intervention, e.g. monitoring risk scores. AI can automate processes and enhance the quality of the fraud analysts’ work. Conclusion In to Tessema Tesfachew’s opinion, “Fraud detection has become vastly more efficient and effective with the introduction of Artificial Intelligence (AI). Previously, methods for detecting fraudulent activities were still data-rich, but relied more on human intervention and expert bias, and were thus, more time consuming and prone to error.” AI technology, particular anomaly detection, has streamlined fraud detection and created a more efficient, and accurate system for detecting and preventing fraud. Covid-19 has increased the number of online transactions, which creates more opportunities for fraudulent activity. However, it also allows businesses to gain more information on their customers and enhance the capabilities of AI security software. It is more important than ever for organisations to utilise AI technology in fraud detection strategies.

What new technologies and trends will shape video analytics?
What new technologies and trends will shape video analytics?

The topic of video analytics has been talked and written about for decades, and yet is still one of the cutting-edge themes in the physical security industry. Some say yesterday’s analytics systems tended to overpromise and underdeliver, and there are still some skeptics. However, newer technologies such as artificial intelligence (AI) are reinvigorating the sector and enabling it to finally live up to its promise. We asked this week’s Expert Panel Roundtable: What new technologies and trends will shape video analytics in 2021?