Explosives detection

A security company has issued a warning to commuters after a worrying rise in theft and antisocial behaviour at train stations. Kingdom Security, who provide a range of security measures including security personnel to a wide range of sites across the country are becoming increasingly concerned about a rise in theft at several train stations and are asking regular commuters to remain vigilant. Shoplifting offences According to the ONS, England, and Wales reached a new 20-year high with 443,995 shoplifting offences committed in 2023/2024. The situation is certainly worrying and although commitments were made in July’s Kings Speech, Graham Allison, COO of Kingdom Security, is urging commuters to be vigilant and to make security aware if they see any causes for concern in train station shops. Campaign against shoplifting and violence “Kingdom welcomes the government’s commitments to crack down on shoplifting and violence against shop workers. Train station retail workers are under immense pressure, especially during peak commuter hours, and unfortunately, some people rushing to get their train may be tempted to steal rather than wait in line.”  “Nationwide, we are also seeing a rise in the verbal and physical abuse being faced by retail workers, and we fully support Co-op's campaign to make this a standalone criminal offence,” continues Graham. “At train stations, there are fewer staff in store to deal with situations that escalate, so security personnel needs to be trained to deal with these issues and protect shop workers.” Preventative solutions Incident Reporting software allows store managers to log the value of goods and the time of day There are many preventative solutions retailers in train stations can take to better protect themselves. For example, Kingdom Security is rolling out new innovative measures to crack down on shoplifting. Their Incident Reporting software allows store managers to log the value of goods and the time of day these attacks happen through their mobile, to build a clearer image of when theft is most likely to occur, and to identify the high-value items. These forecasts let management staff prepare and prevent any abuse and theft within their stores, better-protecting team members and the public during especially busy commuter hours. The public to remain vigilant Graham emphasises, “The security industry is making huge strides forward, in not only reacting to theft after the fact but creating a basis from which retailers can better prepare for it." "We are asking the public to remain vigilant, especially during commuter hours when stations are at their busiest, and if you see anything suspicious alert the relevant authorities including the British Transport Police immediately.” 

ZeroEyes, the creators of the only AI-based gun detection video analytics platform that holds the US Department of Homeland Security (DHS) SAFETY Act Designation announced that its technology has progressed beyond its previous DTE (Developmental Testing and Evaluation) Designation to earn full SAFETY Act Designation. Full Designation Full Designation is granted only to technologies that have been thoroughly tested and proven their effectiveness in mitigating terrorism risks. It eliminates the third-party liability of all ZeroEyes customers for claims resulting from acts of terrorism when the platform is in use. To obtain full Designation, ZeroEyes demonstrated that its solution has a history of successful deployment and has been thoroughly tested and evaluated. Liability protection has been expanded to all ZeroEyes’ customers until mid-2029. Reliability and efficacy To secure full Designation, ZeroEyes worked closely with consultant Dave McWhorter, PhD, founder and CEO of The Homeland Security Consulting Group and former Deputy Project Leader on DHS’ SAFETY Act program itself. McWhorter states, “It has been an honor working with the ZeroEyes team to ensure that its pioneering technology is the first AI-based gun detection solution to be recognized by the U.S. Department of Homeland Security as an effective anti-terrorism technology. This Designation is a testament to the platform’s reliability and efficacy, measured through rigorous testing, evaluation, and real-life events.” AI gun detection and intelligent situational awareness If a gun is identified, images are instantly shared with the ZOC which is staffed 24/7/365 ZeroEyes' AI gun detection and intelligent situational awareness software layers onto existing digital security cameras. If a gun is identified, images are instantly shared with the ZeroEyes Operations Centre (ZOC), the industry's only U.S.-based, fully in-house operation centre, which is staffed 24/7/365 by specially trained U.S. military and law enforcement veterans.  If these experts determine that the threat is valid, they dispatch alerts and actionable intelligence including visual description, gun type, and last known location to first responders and local staff as quickly as 3 to 5 seconds from detection. Liability protection “The process of receiving this Designation required us to demonstrate several years of pressure testing to DHS to ensure that our technology is sound, reliable, and delivers what we promise,” said Mike Lahiff, CEO and co-founder of ZeroEyes. “As a result, we now provide significant value in liability protection, especially to our commercial enterprise customers, including stadiums, shopping malls, and third-party logistics companies.”

Automated operation is a key function for expanding rail capacity and strengthening the performance of railways. Working together with S-Bahn Berlin, Siemens Mobility has installed and will be testing an obstacle detection system – a key technology component for enabling fully automated driving – for the first time during regular daily operation.  The project’s goal is to thoroughly evaluate the performance of the new obstacle detection system during daily operation in various weather and route conditions. The test data will be used to further refine the system and optimise the positioning of the detection sensors. Siemens’ new obstacle detection system In the future, the obstacle detection system can help drivers avoid accidents The system will record background data for the duration of the project, and neither the train drivers nor the passengers will notice its operation. In the future, the obstacle detection system can help drivers avoid accidents, which will stabilise daily S-Bahn operations and increase punctuality. The system promises to be a key technology for enabling digitalised, fully automated rail operations in the future. Albrecht Neumann, CEO Rolling Stock at Siemens Mobility, said: “Intelligent trains that relieve their drivers of routine tasks and support them in their work are the future of digitalised rail transport. These trains will be able to automatically set themselves up and shut down, ensure energy-optimised operation, react quickly and safely to obstacles on the track, and shunt fully automatically on the depot grounds.” Albrecht Neumann adds, “We look forward to working with our partners to qualify our innovative obstacle detection technology for practical application in Germany’s largest S-Bahn network.” Berlin S-Bahn Peter Buchner, CEO S-Bahn Berlin GmbH, said: “For 100 years, the Berlin S-Bahn has stood for innovation and progress. We are partnering with industry to test new technologies that support environmentally friendly rail transportation. Automatic obstacle detection will be an indispensable component for automated driving in the future. It is already capable of supporting our drivers and contributing to better operational quality.” Martin Fuchs, CEO Verkehrsverbund Berlin Brandenburg (VBB), said: “The states of Berlin and Brandenburg and the Berlin-Brandenburg public transport authority (VBB) support innovation and the groundwork needed to make S-Bahn operations more efficient and effective.” Automatic obstacle detection project Martin Fuchs adds, “This automatic obstacle detection project will generate valuable findings and enable us to further develop the S-Bahn system. Exactly 100 years after the S-Bahn was first electrified, we are preparing yet another technological leap that will make Berlin’s S-Bahn system fit for the future.” Testing of the technology will be carried out in a partnership between Siemens Mobility GmbH (installation supervision, sensors, hardware, software and digital map), S-Bahn Berlin GmbH (trains, installation, operation), and Digitale Schiene Deutschland/DB InfraGo (digital mapping, open data platform). Results of the tests will be evaluated together with the VBB. Sensors used include high-performance LiDARs On the technical side, the sensors used in the project will include high-performance LiDARs On the technical side, the sensors used in the project will include high-performance LiDARs for close- and long-range object detection and an infrared camera. The algorithms for evaluating the sensor data have been specially developed for the rail sector in the ‘Berlin Digital Rail Operations – BerDiBa’ research project by Siemens in Berlin-Adlershof and have already been optimised several times. The system continually compares the position of a train with the location of detected objects using a digital map. Decisions whether to warn the driver or brake the train are made on the basis of these ongoing calculations. A newly developed map from DB InfraGo, which depicts reality with centimetre-accurate precision in 3D, is being used for this purpose for the first time. Digital Rail Germany initiative As part of the Digital Rail Germany initiative, Siemens, a technology major in the field of rail automation, and Deutsche Bahn are pursuing a new approach to accelerate the introduction of this detection technology in the rail sector and promote innovation in Germany. In the project, selected data showing obstacles on the track will be made available centrally in anonymised form and can be used for research purposes, such as training AI models or for system validation. Emergency braking assistance system Following a one-year test phase through all seasons, the assistance system should be ready for use Following a one-year test phase through all seasons, the assistance system should be ready for use as an emergency braking assistance system that operates in the background to support the driver.  On the basis of the data generated during this phase, it will be possible to use the system together with other automation components for automated driving at low speeds, such as during depot shunting or when deploying or shutting down a train. The field test aims to: Gain knowledge about boundary conditions for obstacle detection with the help of joint data evaluation, Record and evaluate the performance of the sensor technology under special operating conditions such as rain, fog, snow, and dirt, Minimise risks related to planning projects (technology, calculations, deadlines), and Optimise system settings to avoid false alarms, essential for driverless operation. Cooperation partners The cooperation partners - Siemens Mobility, Deutsche Bahn AG (S-Bahn Berlin GmbH, DB InfraGo, DB Systemtechnik) and the states of Berlin and Brandenburg with the Berlin/Brandenburg Transport Association will jointly analyse the findings and data from the project in the research project. Installation of a set of prototype sensors for detecting obstacles has already been completed in an S-Bahn Berlin train. As part of the field test, up to ten trains in the Berlin S-Bahn fleet will be equipped with the sensors. Once the field test has been completed, it is planned to remove the sensors.

GSX 2023 marks a poignant moment for the security industry as an increasingly complex risk landscape converges with the acceleration of technology innovation. Emerging from this environment are three key trends that will dominate the conference and the future of the security industry: (i) the adoption of AI, (ii) the use of predictive analytics, and (iii) a hybrid global and local risk management approach. As Chief Security Officer of Crisis24, a GardaWorld company, I regularly advise clients on how these trends are evolving and impacting their security and risk management approach. Here’s how we can expect to see them discussed at the show next month:​ Trend 1: Artificial intelligence is the new industry standard.  AI is this year's buzzword. While AI is not new to the industry, this year it has become a standard to operate with AI being adopted or expanded more ubiquitously. Legacy AI-enhanced security offerings that have been years in the making are becoming more advanced and are being integrated into expert analyst teams to leverage the best of both man and machine.  Limitations AI augments the data processing ability; however, human-led intelligence is still necessary AI can generate unparalleled levels of data and insights, but it also has its limitations. AI does not have the emotional intelligence that can influence decision-making. For instance, our Crisis24 analyst teams know that every one of the intelligence alerts they provide to leadership may save a life or protect a business. AI augments the data processing ability; however, human-led intelligence is still necessary to effectively elevate knowledge of those threats through an organisation to incite action.  Trend 2: Predictive analytics powered by AI will transform security operations.  Predictive analytics enabled by AI will allow for more precise planning and execution of true emergency management. Those living or operating in conflict zones must be ready to spring into action and predictive analytics can help better evaluate risks, threat levels, and the probability of certain events.   When I served in Iraq in 2003, our greatest challenge was operating in an unpredictable environment and navigating the many unknown threats. With these large-scale threats, it was difficult to account for the vast array of variables involved and ensure that all parties were protected. Broad and instant visibility Predictive analytics provides broad and instant visibility into numerous potential outcomes, impacts, and mitigation strategies for a wide variety of threats.  When dealing with risks that are constantly evolving and quickly accelerating, the insights from predictive analytics can have a direct impact on risk management, mitigation strategies, and preparedness levels. Predictive analytics can anticipate the ripple effect that threats can have on organisations, their people, and their assets and enable security teams to plan.​ Trend 3: Risk mitigation is increasingly both global and hyper-local.  A company’s workforce is often scattered across the country or the world, working from home or on the go Remote work and a flood of 24/7 data sources have driven demand for timely, accurate, and hyper-local intelligence.  Where before an organisation may have had a handful of facilities around the world where its employees gathered, now a company’s workforce is often scattered across the country or the world, working from home or on the go.  Preventive mitigation steps To keep their people and assets safe, business pioneers need to know what’s happening in all corners of the globe, while also easily accessing details on what is happening at the street corner level.  How a business takes care of its people, including anticipating risks and taking preventive mitigation steps as well as responding quickly in the face of threats, can directly affect its reputation. Every company is in the business of safety and security when it comes to looking after its people on a global, national, and increasingly hyper-local scale. 

Most of the assumptions you’ve made about gunshot detection could be wrong. To those security professionals who stay on top of their homework, this is probably not true, but the ‘you’ in this context is directed to the collective security industry reader that, when looking into indoor gunshot detection products, sees terms like concussive force, percussion, or shockwave and wonders if these are important differentiators – or something the marketing department decided would get a reader’s attention. The truth is that all these terms, from an application standpoint, mean the same thing. Detractors of gunshot detection might question the validity of the technology since the perpetrator is already in action and shooting is in progress. Directing emergency personnel The purpose of gunshot detection is to alert with absolute certainty and as soon as possible that there is a shooting in progress, and very importantly, to identify the location of the incident. The purpose of gunshot detection is to alert with absolute certainty and as soon as possible With this information, we can guide victims away from the shooter while also directing emergency personnel to the perpetrator’s location so they can mitigate the threat. If your loved one found themselves in a work or school shooting, which would you prefer – that they hide until law enforcement arrives, or that they know a safe path for immediate evacuation? As a security operator, would you prefer to manually search camera feeds to find the shooter, or have gunshot detection instantly cue cameras to the incident location? Gunshot detection technologies When you see the value gunshot detection has to offer, the next step is gaining a deeper understanding of the technology and sifting through marketing claims to find the system that works for your application. Before jumping into the circuit boards and algorithms of modern indoor gunshot detection sensors, it helps to go back in time and learn about the genesis of gunshot detection technologies. Many sources generalise gunshot detection into two classifications: military or civilian/law enforcement application. Gunshot detection’s history tracks back to systems built in the 1990s for military applications that detected and reported on sniper fire from high calibre weapons. These systems were then made available for civilian applications in the form of city-wide applications that triangulate signals to locate gunfire in urban areas. Existing outdoor technology This feeds the collective understanding that all gunshot detection systems operate in one simplistic way Although these systems differ in how they detect, locate, and report gunfire, at their core is a reliance on acoustics (and therefore microphones) as their single mode of detection. Because these systems were essentially first to market, they are the most publicised and reported on. This feeds the collective understanding that all gunshot detection systems operate in one simplistic way; they ‘listen’ for the sound of gunshots, triangulate a location, and then produce some type of alert. Detecting a gunshot outdoors is different than detecting one indoors. Early attempts by indoor gunshot detection pioneers to use the existing outdoor technology didn’t work very well. There are several reasons for this, but they can be summarised as follows: The acoustic pattern of a gunshot indoors is different than one that is produced outdoors. Walls, furniture, and general building layout will create echoes and reverberations that combine to create a signal that is difficult to interpretate. Some outdoor systems were reliant on the shockwave of supersonic rounds outdoors. In the indoor environment, the acoustic properties of that shockwave can break down quickly, rendering the result degraded and therefore unusable as a reliable indicator of gunfire. Systems reliant upon triangulation, like the ones used in city applications, also do not work indoors because those echoes and reflections in the acoustic environment interfere with both detection and location accuracy. Indoor gunshot detection This compression continues as the bullet moves forward through the air Indoor gunshot detection requires a different approach. But before diving into the deep end of the technical pool, a few words about what happens when a gun is fired. We are all familiar with the bullet flying out of the gun part, but what else happens? When the bullet leaves the muzzle (end) of the gun, air molecules around the bullet get rapidly compressed. Just like a guitar string that has just been plucked, rapid compression or vibration moves the air molecules around it. This compression continues as the bullet moves forward through the air, but the initial, violent change is what we first capture. The gasses that are part of the gun powder burned to propel the bullet out of the gun are also released. This causes a ‘flash’ which can been recorded as part of the visible and infrared (IR) spectrum. Indoor gunshot detection requires a different approach Sound pressure sensor The talk of 'rapid vibrating or compression of air molecules’ is where confusion can begin. Why? Because this same property can be measured in different ways. One way is acoustical – a microphone recording the ‘bang’. Another way is through pressure. But wait a minute – if we remember our high school physics, a sound wave is the same as a pressure wave! Simply stated, a microphone is a pressure sensor - usually tuned to capture very small changes - and a sound pressure sensor is just a clunky microphone. As humans, we forget that sound – like the loud bang of a firearm – is just our way of describing a very distinct change in the vibrations of air molecules around us. Air pressure sensors Gunshot detection devices use sensors to detect a change in the compression of air molecules Gunshot detection devices use sensors to detect a change in the compression of air molecules. Manufacturers can say that they use different types of sensors – microphones, air pressure sensors, concussive force sensors, shockwave sensors, etc. – but these devices are all measuring the same thing. The primary difference between different sensors is how sensitive to disruption they are, which is usually a function of cost, and what frequency or range of disruption they are designed to look for. Some manufacturers claim to capture the ‘shockwave’ of a bullet. Shockwave is a rather loose term, but the manufacturer is usually referring to a special pressure wave in the air that is created when an object travels faster than the speed of the sound. An object passing through the sound barrier will make a loud noise – or large, fast pressure change – but again, the sensor is simply capturing a change in the compression of air molecules. Serving particular market At first, the idea of using a bullet’s speed – and therefore shockwave - as an inexpensive mechanism for capturing and verifying that a gunshot has occurred may seem interesting. But be careful of products that promote shockwave as their principal factor of gunshot detection. Many types of bullets – a 45 calibre pistol for example – do not create a shockwave when fired, meaning these types of gunshots fired in your building will be excluded from detection. Manufacturers all take different approaches to serving a particular market. In the world of security, one would hope that all products deliver exactly as advertised. Unfortunately, a sensor that is calibrated to one range of sound or pressure can inadvertently register other, unwanted sounds. Different building configurations A nail gun or balloon popping will trip a sensor calibrated to listen for the frequency A nail gun or balloon popping will trip a sensor calibrated to listen for the frequency – or vibrational – range of most gunshots. Sensors can be pre-programmed with a library of gunshot-like sounds, but this requires the sensor to analyse the signal it just captured, creating a delay in alert times. A study done by Florida Atlantic University’s College of Engineering and Computer Science recently concluded that ‘most gunshot detection systems cannot tell the difference between a gunshot and a plastic bag popping’ – and this points to why consumers believe that gunshot detection systems are unreliable. Also, as we learned above, different building configurations will create different signal characteristics. Is there a library of gunshots signals for all possible building or room configurations? Single sensor approach As a way to reduce costs, some manufacturers offer a single measurement sensor for both indoor and outdoor applications, but this approach requires extensive calibration for two different environments, meaning that accuracy inevitability suffers. As a way to reduce costs, some manufacturers offer a single measurement sensor Define your expectations accordingly because the single sensor approach is limited. The level of accuracy will be low, and you will experience false alerts, creating a need for an additional layer of verification that further delays notification. In the physics lesson above, we mentioned that there was a second characteristic of a gunshot – the release of light – or more accurately, heat – from the infrared (IR) spectrum. To avoid the problem of concussive force/shockwave/microphone sensors capturing signals that are not gunshots, a second sensor dedicated to measuring the IR signal emitted by a bullet leaving a gun is added. Generate false alerts Just like online banking services enforce two-factor authentication to ensure authenticity, gunshot detectors can use two sensors measuring the two different characteristics of a gunshot to deliver the highest level of accuracy. And since the speed of light and the speed of sound are different, programming can be employed to further validate that the signal received was truly a gunshot and not a similar-sounding non-ballistic event, like a nail gun. From an accuracy standpoint, single measurement sensors perform worse than a dual-sensor in all cases and are significantly more likely to generate false alerts. The only benefit of a single-sensor shot detection system is that they may be cheaper to purchase in terms of upfront costs. But those savings will quickly be erased by the cost of avoidable business disruptions due to a higher false alert rate. Normal hospital services Schools are probably the hardest to estimate as intangible costs like staff/student wellbeing In manufacturing, warehousing, or transportation environment your accounting department can easily calculate how much a one-hour shutdown of work will cost the organisation if a false alert causes an interruption in operations. In industries like healthcare, calculating the cost of a false alert is a little more complicated, but one study determined that cancelling normal hospital services for just one day can cost approximately $978,418.00. Schools are probably the hardest to estimate as intangible costs like staff/student wellbeing and law enforcement-related activities do not lend themselves to a straightforward financial calculus. Single measurement sensors However, when investigating indoor gunshot detection systems, the following top five questions should be asked of each vendor you contact: Does the system use Single Factor or Dual Factor sensor verification to reduce false alerts? The definition of Dual Factor, in this case, is that both factors are required to produce a gunshot alert. Remember that merely adding more single measurement sensors to a product will not reduce false alerts. Does the manufacturer have an independent, third-party verification of their product? If so, what were the testing parameters? Look for gunshots occluded (facing away) from the sensor, types of noises tested including firearms and false alert tools used, sensor distance from the gunshot, and the validity of the testing agency as a trusted, impartial operation. Real-world testing is also extremely valuable, meaning in a customer’s installed environment, outside of the gun range. If the single factor sensor is advertised to work both indoors and outdoors, how does the device technology compensate for these two different environments? Does the manufacturer’s solution require a human to validate that the signal received was a gunshot? Systems that require human verification will considerably slow down the speed at which Law Enforcement is contacted and, because of normal human behaviors during periods of stress, can also lead to inaccurate information being communicated to first responders. Is the manufacturer an expert in gunshot detection or did they just add a microphone to a product and bundle it with other types of sensors like smoke detection, aggression, vaping, glass breaking, etc.? These all-in-one sensors are currently common as manufacturers attempt to test the market’s appetite for gunshot detection. False gunshot alert There are currently no regulatory bodies monitoring gunshot detection manufacturers and their claims Gunshot detection does not have to be complicated, but when an emerging technology begins to gain traction in the marketplace, it is important to follow the science and keep learning. There are currently no regulatory bodies monitoring gunshot detection manufacturers and their claims, so doing your due diligence is key with this technology. Talk to your business leaders about the impact a false gunshot alert could have on the organisation from a risk standpoint. Seek to understand the underlying technology of any shot detection system you are considering and look for two factors of gunshot authentication. Hopefully, this technology primer on gunshot detection helps integrators and end-users understand the underlying technology so they can find the most effective solution for their facilities. Bill Aheimer, Principal of Security DNA, is co-author of this article.

According to the reports of not-for-profit organisation Gun Violence Archive, the year 2018 has seen 323 mass shooting incidents as of November 28 in the United States. This number is 346 for the year 2017 and 382 for 2016 (more statistics are available here), with “mass shooting” defined as cases where four or more people are shot or killed in the same time period and location. While definitions of mass shooting vary with organisations in the US, the count of over 300 incidents per year, or about once per day on average, is simply alarming. It raises public safety concerns, ignites debates and protests, which in turn lead to public unrest and potentially more violence, and increases costs for governments from the regional to federal level. Most importantly, the loss of lives demands not only improvement in post-incident handling and investigation, but also new prevention technologies. Gunshot detection solutions AI weapon detection offers a more efficient alternative to prevent active shooting There are several gunshot detection solutions in the security market, commonly used by law enforcement agencies to detect and locate gun fires. These systems function based on acoustic recordings and analyses and often in combination with signals detected by sensors of the optical flash and shockwave when a gun is fired. However, gunshot detection by nature dictates that the law enforcement can only react to a shooting incident that has occurred. With fast action, law enforcement can prevent the incident from escalating, but lives that are lost cannot be recovered. With the development of artificial intelligence in object recognition, AI weapon detection offers a more efficient alternative to prevent active shooting: AI can visually detect guns based on their shapes before they are fired. The AI is trained to recognise firearms in different shapes, sizes, colours, and at different angles in videos, so that the AI weapon detector can be deployed with existing cameras systems, analyse the video feeds, and instantly notify security staff when a gun is spotted. Comparison of the advantages for law enforcement and public security agencies Legacy gunshot detection using sensors AI weapon detection Reactive measure: detect after guns have been fired Proactive measure: detect before guns are fired Time to action: within 1 second Time to action: within 1 second Unable to provide visual data about shooter(s) Can provide data about shooter(s) based on the camera recording: clothing, luggage (backpack, handbag, etc.), facial features, vehicle Unable to track the location of the shooter(s) before and after shooting because of the lack of sound Can track the shooter(s) using AI Person & Vehicle Tracking, AI Face Recognition, and AI License Plate Recognition False detection caused by similar sound such as fireworks and cars backfiring Minimal to no false detection, as AI can distinguish different types of handguns and rifles from normal objects (umbrella, cellphone, etc.) Require physical deployment of gunshot detection sensors Can be used with existing camera systems, do not require special hardware Complicated to deploy, require highly trained professional Easy to deploy as an add-on to existing video surveillance system - Can integrate with gun-shot detection to create a “double knock” audio and video active shooter alert system Gun-shot detection advantages In addition to advantages for law enforcement and public security agencies, this type of visual-based pre-incident detector has three-fold advantages for the public: Save lives by spotting the shooter before the shooting event. Minimise the chaos entailing an incident: panic and chaos caused by a shooting incident often adds to injury, as people run, fall, trample on others… With an AI weapon detector, when a gun is spotted, the system sends an alert to security staff, who can quickly control the situation in an organised manner and apprehend the intending shooter. Can be added as a SaaS (Security as a Service) component to small business and home surveillance systems, e.g., intrusion detection alerts (home invasion incidents with firearms number over 2500 per year nationwide). For a complete active shooter detection system, video-based AI detector can operate in conjunction with gunshot detectors for enhanced security. Traditional X-ray based weapon detection or metal detection entrance systems are complicated and expensive; with AI video technology, active shooter detection system can be cost-effective, and after all, what price tag can one put on a life? Written by Paul Sun and Mai Truong, IronYun

Companies at GSX 2023 emphasised new ways that technologies such as artificial intelligence (AI) and the cloud can address long-standing issues in the security market. Among the exhibitors at the event in Dallas were companies seeking creative ways to apply technology, lower costs, and make the world a safer place. Reflecting on the exhibition, here are some additional takeaways. Expanding AI at the edge  i-PRO is a company reflecting the continued expansion of edge AI capability in the security market. Today, more than half of the company’s lineup supports AI at the edge so the customer has a wide choice of form factors when seeking to leverage the feature set.  AI processing relay, extended warranty i-PRO is increasing their warranty period from 5 to 7 years, which could be a lifetime warranty in some cases I-PRO also has an “AI processing relay” device that accepts non-AI video streams and applies edge analytics. AI has progressed from a high-end technology to a feature available in a variety of cameras at different price points. i-PRO is also increasing its warranty period from 5 to 7 years, which could be a lifetime warranty in some cases depending on a customer’s refresh schedule and lifecycle management. Active Guard, MonitorCast The company’s video management system (Video Insight) is continuing to build new features including “Active Guard,” an integrated metadata sorter. Their access control platform, MonitorCast, is a Mercury-based solution that is tightly integrated with Video Insight. Their embedded recorders now have PoE built in.  “We can move at a faster pace to fill out our product line since leaving Panasonic,” says Adam Lowenstein, Director of Product Management. “We can focus our business on adapting to the market.” Emphasis on retail and other verticals  Shoplifting is a timely issue, and retail is a vertical market that got a lot of attention at GSX 2023. “We see a lot of retailers who are primarily interested in protecting employee safety, but also assets,” says Brandon Davito, Verkada’s SVP of Product and Operations. “Shrinkage is a CEO-level priority.”  “Retailers are getting more engaged with security posture, instead of letting perpetrators walk,” Davito adds. Intrusion detection Verkada has an intrusion product that will notify a central station if there is an alarm On the alarm side, Verkada has an intrusion product that will notify a central station if there is an alarm, and operators can review videos to confirm the alarm. Other capabilities seeking to discourage trespassers include sirens, strobes, and “talkdown” capabilities.  International expansion Verkada continues to expand internationally with 16 offices in all, including Sydney, Tokyo, and London. The core value proposition is to enable customers to manage their onsite infrastructure more simply, including new elements such as PTZ cameras, intercoms, and visitor management. Verkada emphasises ease of use, including a mobile application to allow access to be managed across the user base. Forging partnerships “We are committed to the channel and industry, and we continue to build relationships and expand our reach,” says Davito. Among the industry relationships is a new partnership with Convergint, which was hinted at during the show and announced later the same day. They are also expanding their partnerships with Schlage, Allegion, and ASSA ABLOY.  Working with other verticals They offer new features for K -12 schools, and a new alarm platform is easier to deploy and manage Verkada has also found success across multiple other verticals, notably healthcare, where they integrate with an electronic medical records system. They offer new features for K-12 schools, and a new alarm platform is easier to deploy and manage. They are integrating wireless locks to secure interior doors in schools, looking to secure the perimeter, and installing guest management systems. Transitioning the mid-market to the cloud  Salient is squarely focused on the “mid-market,” a large swath of systems somewhere between small businesses and enterprise-level systems. Pure cloud systems are not as attractive to this market, which has a built-out infrastructure of on-premise systems. Adding a camera to an existing system is easier and less expensive than tying it to the cloud. Benefits of cloud It’s a market that may not be ready for the pure cloud, but there are benefits to be realised from adding a cloud element to existing systems. “We are continuing to augment our premise-based solutions with added cloud capabilities and flexibility,” says Sanjay Challa, Salient’s Chief Product Officer.  The feedback Salient hears from their customers is “I want to own my data.” The hybrid cloud approach offers the right mix of control, flexibility, and unit economics. Cloud add-on capabilities We want to provide the flexibility for customers to go full-cloud as it becomes more economically attractive" Cloud add-on capabilities include bringing more intelligence about system operation to the user via the cloud. Over time, Salient expects to sell more cloud-centric offerings based on feedback from integrators and customers. “We want to provide the flexibility for customers to go full-cloud as it becomes more economically attractive over time,” says Challa.  Vaidio AI technology Salient seeks to be a transition pioneer to help customers realise the path to the cloud. Their approach is “crawl, walk, run,” and helping customers make the transition at each stage. Salient has added AI to its product offering, incorporating Vaidio AI technology from IronYun into a powerful suite and broad array of on-premise analytics, which are gaining traction. The seamless approach makes it easy for customers to embrace AI analytics, although Salient remains broadly committed to open systems. Addressing ‘soft’ features for integrators AMAG is in the process of enhancing its product line with the next generation of access control panels. However, “product” is just part of the new developments at AMAG. In addition to “hard” features (such as products), the company is looking to improve its “soft” features, too; that is, how they work with the integrator channel. Integrator channel Rebuilding a process to make your organisation more efficient, is relatively easy; it just takes a lot of persistence" “We have the depth of our legacy customer base we can learn from, we just need to close the feedback loop quicker,” says Kyle Gordon, AMAG’s Executive Vice President of Global Sales, Marketing, and commercial Excellence, who acknowledges the value of reinstating face-to-face meetings after COVID. “We are laser-focused on nurturing our integrator channel,” he says.  “Developing new features takes time, but rebuilding a process to make your organisation more efficient, that’s relatively easy; it just takes a lot of persistence,” says Gordon. More cohesive internal communication is another useful tool, he says.  Disrupting the cloud based on price  Wasabi is working to make cloud applications less expensive by offering a “disruptive” price on cloud storage, $6.99 per terabyte per month (80% less than hyperscalers). Contending “hyperscalers” like AWS are charging too much for cloud storage, Wasabi is using its own intellectual property and server equipment co-located in data centres around the world. Wasabi sells “hot cloud storage,” which refers to the fact that they only have one tier of storage and data is always accessible. In contrast, a company such as AWS might charge an “egress fee” for access to data stored in a “colder” tier.  Cloud storage “We saw that several video surveillance companies had not yet adopted cloud storage, and we saw an opportunity to make it easy to use,” said Drew Schlussel, Wasabi’s Senior Director of Product Marketing. “We just install a little bit of software that allows them to store data in the cloud and bring it back from the cloud.” Performance, protection (cybersecurity), and price Wasabi works with integrators, resellers, and distributors and also integrates with VMS companies Wasabi works with integrators, resellers, and distributors and also integrates with VMS companies such as Genetec and Milestone. Emphasising performance, protection (cybersecurity), and price, their data centres are certified to SOC 2 and ISO 27001 standards.  Faster throughput for weapons detection Xtract One is a young company focusing on weapons detection in a time of accelerated concern about gun issues post-COVID. Founded in Canada and based on technology developed at McMaster University, Xtract One has found a niche in providing weapons detection at stadiums and arenas. These customers already have budgets, and it is easy to shift the money to a newer, faster technology. Madison Square Garden in New York City is among its customers.  Cost savings solution Xtract One can increase throughput to 30 to 50 people per entrance per minute (compared to 5 to 6 people per minute when using metal detectors). The solution doesn’t require anyone to empty their pockets and the system alarms on items beyond guns and knives. Using Xtract One allows customers to reduce the number of screening lanes and security staff, providing additional cost savings, all while getting fans through the screening process in half the time. Purpose-built sensors The system uses purpose-built sensors looking for specific characteristics, such as reflective and density properties In addition to stadiums and arenas, Xtract One, formerly Patriot One, is also getting “inbound” interest from schools, hospitals, manufacturers, and other verticals that makeup 50% of their business. “We’re on a rocket ride, mainly because the weapons issues are not going away,” says Peter Evans, CEO and Director at Xtract One. The system uses purpose-built sensors looking for specific characteristics, such as reflective and density properties, all correlated by an AI engine.  Providing early warning of violence ZeroEyes is another company focused on weapons detection. Their AI gun detection system works with video images to identify if someone is “brandishing” (carrying) a weapon. In other words, the system does not detect concealed weapons. Identifying someone carrying a weapon provides early warning of a possible violent act. Increased response with AI-enables images Images are identified by AI and sent to a monitoring centre where a human confirms the image before contacting first responders. Knowing the location of a shooter enables staff to lock entry points, move people to safety, and direct first responders. The company was founded to leverage existing camera views to stop mass shootings and gun violence by reducing response times. 

During the Parkland, Florida, school shooting in 2018, the shooter was caught on a security camera pulling his rifle out of a duffle bag in the staircase 15 seconds before discharging the first round. However, the School Resource Officer didn’t enter the building because he wasn’t confident about the situation, and the Coral Springs Police Department had no idea what the shooter even looked like until 7 minutes and 30 seconds after the first round was fired. If the video system had included technology to recognise the gun threat in real time, alerts could have been sent to the security team. An announcement could have been made right away for all students and faculty in Building 12 to barricade their doors, and law enforcement could have responded a lot faster to a real-time feed of timely and accurate information. Automatically recognising gun threats Actuate offers such a technology, which the company says enables existing security cameras to automatically recognise gun threats and notify security in real-time. The technology is centred around a convolutional neural network (CNN) that aims to replicate how a human brain would process information. This neural network is trained to recognise what hands holding a firearm look like from hundreds of thousands of images in a proprietary data set. The technology is centred around a CNN that aims to replicate how a human brain would process information Over time, the system is able to mathematically calculate what a gun threat in a security camera feed looks like with a high degree of accuracy (well over 99% detection accuracy within the first 5 seconds), according to Actuate. “Active shooter situations are often marred by chaos and confusion,” says Sonny Tai, Chief Executive Officer of Actuate. “People are in fight-or-flight response and prioritise immediate survival instead of reaching for their phones and calling 911. When the 911 calls are made, callers often provide delayed, conflicting, and inaccurate information, inhibiting law enforcement’s ability to respond.” Enhances law enforcement response Tai says Actuate helps to clear up that chaos and confusion. He says: “It provides visual intelligence of the location of the shooter, what they look like, what direction they’re heading, and what they’re armed with. This real-time information enhances law enforcement response and enables building occupants to make critical decisions that maximise survivability." AI methods including deep learning enable high levels of accuracy in detecting weapons in real-time camera footage Tai is a Marine Corps veteran and a social entrepreneur who co-founded Actuate with the mission of addressing America’s gun violence epidemic. The start of the company stems from Tai’s upbringing in South Africa, where gun violence rates are some of the highest in the world. Growing up, several of his family friends were personally impacted, resulting in a lifelong passion for the issue of gun violence. In early 2018, Tai interviewed dozens of law enforcement leaders across the country and found that their biggest challenge in gun violence response was the lack of timely and accurate information. Actuate mitigates that challenge and enables both first responders and security staff to respond more rapidly, he says. More than 99% accuracy in detecting weapons Actuate's solution is completely AI-based, says Ben Ziomek, Chief Product Officer. AI methods including deep learning enable high levels of accuracy in detecting weapons in real-time camera footage. “Legacy, non-AI based solutions generally rely on older methods like motion detection, which is not reliable in differentiating between objects such as phones and firearms,” says Ziomek. “Our AI solution lets us achieve more than 99% accuracy in detecting weapons with an exceptionally low false-positive rate.” Ziomek runs engineering, data science, and operations for Actuate. Before joining the firm, he led teams of AI engineers and data scientists at Microsoft, leveraging AI to identify high-potential startups globally. Actuate is a software-only solution that plugs into existing security camera hardware and software, including video management systems (VMS). Existing capabilities of a customer’s VMS does initial, basic analysis and then routes the remaining video to Actuate’s processing units for AI analysis. Alerts can then be sent back however a customer wants, including through a VMS. Actuate can also feed information into a PSIM or command-and-control system if requested by a customer. Equipping customers with AI tools As an early-stage company, Actuate is pursuing customers through multiple routes, including directly to end-users and via security integrators, distributors, and dealers. They are currently deployed at diverse customer sites including schools, office buildings, industrial facilities, and public buildings, says Ziomek. Our current focus for the company is to get our technology into the hands of as many customers as possible “Our current focus for the company is to get our technology into the hands of as many customers as possible,” says Ziomek. “We are working closely with customers across segments and industries to equip them with the tools they need to make their spaces safer. We’re currently working on educating the market on our offerings, as this technology is very new to many security organisations.” There are no privacy or compliance concerns because Actuate stores no customer data until a weapon is detected, and even then the data is not cross-indexed with any sensitive information, says Ziomek.

According to the reports of not-for-profit organisation Gun Violence Archive, the year 2018 saw 323 mass shooting incidents as of November. This number is 346 for the year 2017 and 382 for 2016, with ‘mass shooting’ defined as cases where four or more people are shot or killed in the same time period and location. A variety of gunfire detection solutions and other technology approaches seek to address the problem. ShotSpotter SiteSecure and ShotSpotter SecureCampus provide critical outdoor infrastructure protection against active shooter attacks. SiteSecure delivers critical information such as the number of shots fired, a detailed map of the airport or transportation facility, with the shooting location clearly identified. SiteSecure also provides law enforcement and transportation facility management with real-time information that can be useful to identify and address false alarms and reduce mass panic. Gunfire detection and precise shooter location ShotSpotter SecureCampus is a gunfire detection system designed to provide outdoor coverage at university and school campuses. Designed for college campuses and K-12 schools, SST SecureCampus provides gunfire detection, precise location, and number of shooters to first responders and school personnel, enabling faster response to an incident. Designed for college campuses and K-12 schools, ShotSpotter SecureCampus provides gunfire detection Data capture form to appear here! Gunshot detection can offer tremendous benefits in mitigating active shooting incidents occurring in a public facility or commercial environment. Data shows that active shooter attacks often begin outside a building and then progress indoors. Thus, the first line of defence for security professionals lies outside a facility, in a zone of protection surrounding it or comprising the entire outdoor area of a larger facility of many buildings. Audio solutions for perimeter security Video cameras are effective surveillance tools in the event of a shooting incident, but they are not able to capture everything. Deploying audio solutions can automatically flag incidents not caught on camera, as well as alert central station guards of what surveillance zones need to be closely monitored. Audio analytics solutions for aggression and gunshot detection are some of the best security tools in the security market when it comes to detection, intervention and deterrence. They are the next generation of monitoring; equipping security teams with critical information and enhancing perimeter security. End users can identify high-risk situations in real-time and prevent acts of physical aggression before they happen Aggression detectors are capable of accurately recognising duress in a person’s voice. The software automatically and objectively detects the presence of rising human aggression, anger or fear, and subsequently warns staff by a visual alert or alarm trigger. As a result, end users can identify high-risk situations in real-time and prevent acts of physical aggression before they happen. Artificial intelligence to detect weapons A gunshot detector recognises firearm discharge from various firearms in different settings. Within seconds of a gunshot, the software accurately classifies and triggers an immediate notification through a designated VMS. Security staff can then verify the alert, effectively reducing the reaction time of first responders. With the development of artificial intelligence (AI) in object recognition, AI weapons detection offers an efficient alternative to gunshot detection to prevent active shooting: AI can visually detect guns based on their shapes before they are fired. The AI is trained to recognise firearms in different shapes, sizes, colours, and at different angles in videos, so that the AI weapon detector can be deployed with existing camera systems, analyse the video feeds, and instantly notify security staff when a gun is spotted. Audio analytics, processed inside a video camera, are another approach that can quickly pinpoint zones that security staff should focus on, which can dramatically shorten response times to incidents. Audio-derived data also provides a secondary layer of verification that an event is taking place which can help prioritise responses from police and emergency personnel.   Detecting audio levels and alerting operators The first job of a well-configured camera or camera/mic pair is to detect sounds of interest while rejecting ancillary sounds and noise below a preset threshold. Each camera must be custom-configured for its particular environment to detect audio levels which exceed a user-defined level. Since audio levels are typically greater in abnormal situations, any audio levels exceeding the baseline set levels are detected as being a potential security event. Operators can be notified of abnormal situations via event signals allowing the operator to take suitable measures Operators can be notified of any abnormal situations via event signals allowing the operator to take suitable measures. Finding a baseline of background noise and setting an appropriate threshold level is the first step. Well configured audio analytics can deliver critical information about a security event, accelerating response times and providing timely details beyond video-only surveillance. Analytics take privacy concerns out of the equation and allow installers and end users to use camera audio responsibly. Hanwha Techwin's audio source classification technology, available in its X Series cameras, features three customisable settings for category, noise cancellation and detection level for optimum performance in a variety of installation environments.

ZeroEyes, the creators of the only AI-based gun detection video analytics platform that holds the U.S. Department of Homeland Security SAFETY Act Designation, announced that its proactive gun detection and intelligent situational awareness solution will be deployed at Canyon Hills Community Church to protect its congregation against gun-related threats.  Canyon Hills Community Church Located in the suburbs thirty minutes north of Seattle, Canyon Hills Community Church is a non-denominational, elder-led, bible-teaching church founded in 1995. Since then, it has grown to host over 4,000 people each weekend and several hundred during the week for bible study and youth groups.  Gun violence incidents Canyon Hills Community Church has expanded its security strategy to include ZeroEyes’ proactive solution According to the United States Justice Department, 17.3% of all hate crimes were motivated by bias against religion. Furthermore, data from The ZeroEyes Gun Violence Research Center indicates that of analysed incidents involving religious organisations, 38% of shooters had no affiliation with the place of worship.  As it continues to grow, Canyon Hills Community Church has expanded its security strategy to include ZeroEyes’ proactive solution. This decision reflects the church's philosophy that while the building serves as a place of worship, the true priority is the safety and well-being of its people. Prioritising safety “Our commitment to creating a secure environment for worship and fellowship has never been stronger,” said Jon Huff, Operations Director at Canyon Hills Community Church. Jon Huff adds, “As protectors of our flock, we’ve always prioritised the safety of our community. With ZeroEyes, we are equipped to not only react to potential threats but to prevent them, helping to ensure peace of mind for everyone who walks through our doors.” AI gun detection If a gun is identified, images are instantly shared with the ZeroEyes Operations Center, staffed 24/7/365 ZeroEyes’ AI gun detection and intelligent situational awareness software layers onto existing digital security cameras. If a gun is identified, images are instantly shared with the ZeroEyes Operations Center (ZOC), staffed 24/7/365 by specially trained U.S. military and law enforcement veterans. If these experts determine that the threat is valid, they dispatch alerts and actionable intelligence including visual description, gun type, and last known location to local law enforcement and church staff as quickly as 3 to 5 seconds from detection. Proactive security technology "At a time when places of worship are experiencing increased hostility and threats, Canyon Hills Community Church is setting a standard for others to follow," said Mike Lahiff, CEO of ZeroEyes. Mike Lahiff adds, "We're honoured to be the first proactive security technology they've adopted, and we commend them for their efforts to ensure a safe environment for their members."

ZeroEyes, the creators of the only AI-based gun detection video analytics platform that holds the US Department of Homeland Security SAFETY Act Designation announced that Park City School District (PCSD) of Summit County, Utah has deployed its proactive gun detection and intelligent situational awareness solution to mitigate gun-related violence. Park City School District (PCSD) Nestled within the mountains of the year-round resort town, PCSD encompasses four elementary schools, a middle school, a junior high, a high school, and a learning centre. The district educates nearly 5,000 students annually and boasts a graduation rate in the top 1 percent of the nation. Intelligent situational awareness software AI gun detection and intelligent situational awareness software is layered on existing digital security cameras PCSD is highly focused on student safety, collaborating with the Summit County Sheriff's Department and the Park City Police Department to deploy advanced electronic, physical, and procedural security measures. ZeroEyes' AI gun detection and intelligent situational awareness software is layered on existing digital security cameras at all eight student-occupied PCSD buildings. ZeroEyes Operations Centre If a gun is identified, images will instantly be shared with the ZeroEyes Operations Centre (ZOC), staffed 24/7/365 by specially trained U.S. military and law enforcement veterans. If these experts determine that the threat is valid, they will dispatch alerts and actionable intelligence, including visual description, gun type, and last known location, to local staff and first responders in as fast as 3 to 5 seconds from detection. AI algorithms The platform does not store personal or biometric data or conduct any kind of facial recognition The company's AI algorithms only search for guns, not faces or bodies. Until a gun is identified, the monitoring screens in the ZOC stay blank; the ZeroEyes Operations team does not see a live feed from any cameras. Further, the platform does not store personal or biometric data or conduct any kind of facial recognition. Gun-related violence “We hold a deep commitment to safeguarding our students and staff, and ZeroEyes is a compassionate ally in our mission,” said Michael Tanner, COO of Park City School District. He adds, “By addressing the concerns of gun-related violence while also respecting the need for privacy, this solution allows us to provide a secure yet welcoming campus environment.” Proactive safety measures “Between its collaboration with local law enforcement and the deployment of proactive safety measures throughout its schools, Park City School District has shown that it is on the cutting edge of security,” said Mike Lahiff, CEO, and Co-Founder of ZeroEyes, adding “We are proud to work alongside this dedicated leadership team to protect students and staff against gun-related threats.” Park City School District was introduced to ZeroEyes through the company’s exclusive Utah reselling partner Aegix, a provider of industry-pioneering resources, technology, equipment, and training for first responders.

ZeroEyes, the creators of the only AI-based gun detection video analytics platform that holds the U.S. Department of Homeland Security SAFETY Act Designation, announced that its proactive gun detection and intelligent situational awareness solution has been deployed by Michigan’s Pontiac School District (PSD) to protect students and faculty against gun-related threats. Pontiac School District (PSD) PSD includes nine schools and takes pride in offering its students work-based learning opportunities in industries such as Health Sciences, Business/Finance, and Hospitality/Tourism. The district is also at the forefront of security innovation, adding ZeroEyes to a multi-layered approach that includes a visitor check-in system, smart sensors, and video management software, among others, to provide a safe and secure educational environment. Enhance security and safety “At Pontiac, we've dedicated significant resources to fostering opportunities for students, and we've witnessed the positive impact rippling throughout our community,” said Dr. Kimberly Leverette, Interim Superintendent of Pontiac School District. Dr. Kimberly Leverette adds, “Our mission is to cultivate our schools as safe havens, and with ZeroEyes, we can enhance security and safety both during and after school hours.” AI gun detection and intelligent situational awareness software If a gun is identified, images are instantly shared with the ZOC, staffed 24/7/365 by specially trained U.S. military ZeroEyes' AI gun detection and intelligent situational awareness software layers onto existing digital security cameras. If a gun is identified, images are instantly shared with the ZeroEyes Operations Centre (ZOC), staffed 24/7/365 by specially trained U.S. military and law enforcement veterans. If these experts determine that the threat is valid, they dispatch alerts and actionable intelligence including visual description, gun type, and last known location to local law enforcement and PSD staff as quickly as 3 to 5 seconds from detection. Gun-related violence “In the past few years, the state of Michigan has experienced great hardship when it comes to gun-related violence,” said Mike Lahiff, CEO of ZeroEyes. He adds, “Pontiac School District continues to show its dedication to safety and eye for innovation with its deployment of ZeroEyes.”

The holiday season is marked by festive spirit and family celebrations, but it is also the busiest time of year for retailers. Busy shoppers willing to spend money are an upside to the holiday shopping season, and many businesses depend on the holiday rush as a critical element to having a successful year. A downside of a busy holiday season is an increase in retail security threats including shoplifting. We asked this week’s Expert Panel Roundtable: How can technology address loss prevention challenges during the holiday shopping season?

Cost is a reality to be managed. No matter how powerful or desirable a technology may be to a customer, the sale often comes down to the basic question: Can I afford it? And affordability extends not just to the purchase price, but to the cost of technology over its lifespan. In addition to advances in technology capabilities, the security industry has also achieved inroads to make its offerings more worth the cost. We asked this week’s Expert Panel Roundtable: What is the physical security industry doing to make more affordable and cost-effective technology solutions for end users?

The new school year is a good time to reflect on the role of security in protecting our schools. From video to access control to some newer technologies, our Expert Panel Roundtable found plenty to talk about when we asked this week’s question: How does security technology make our schools safer?