Video motion detectors - Expert commentary

3 reasons why you haven’t adopted AI into your surveillance operation and why you can now
3 reasons why you haven’t adopted AI into your surveillance operation and why you can now

The explosion of artificial intelligence used to enhance business processes, propel innovative products, and further automation has touched essentially every industry to date. The security sector, notable for its maturity and complexity, is not exempt from the AI tidal wave. In fact, quite the opposite, the security sector and more specifically the domain of video surveillance have seen an emergence of AI-powered solutions both hardware and software. The widespread adoption of IP cameras, cloud computing capacities, and smart sensors have paved the way for new AI products and solutions to function at scale. AI-powered video analytics  One application of artificial intelligence for the video surveillance sector is the use of video analytic solutions to analyse video streams in order to extract pre-determined objects, behaviours, or situations. To give some examples, AI video analytics can be used to monitor perimeter crossing for border control, detect fevers or masks in airports or public spaces, arms detection in casinos, or be used to filter out alarms triggered by benign movements versus real intrusions. This application of artificial intelligence leans on its specific branch, machine learning, which uses a complex series of AI models to analyse the content of the video flow, autonomously identifying and classifying the videos according to predefined rules. Adopting technology AI video analytics yields promising benefits, a reduction in operational costs, and an increase in safety and a decrease in risk When AI video analytics are used effectively, they yield very promising benefits. A jump in video flow analysis from an average of 10% by humans to 100%, a reduction in operational costs, and an increase in safety and a decrease in risk. The use of AI video analytics for surveillance sounds simple enough, however, there are several perceived factors inhibiting security organisations from adopting the technology. Adopting AI into your video surveillance operation The security industry is capital intensive, complex in its IT structure, and diverse in situational business needs. Therefore, resulting in a perception of high effort, time and costs required to successfully integrate AI into your video surveillance operation. However, these effort constraints can be debunked due to the flexibility of video analytic solutions. Three areas that deter security organisations from adopting AI Existing capital A surveillance operation contains a network of cameras that film with a range of video qualities. AI video analytics can analyse a range of videos from low to high resolution in thermal, infrared and visible formats AI video analytics often operate on smart cameras that have the appropriate video image quality for the capacity of content analysis. The costs involved in overhauling legacy camera systems, converting videos into higher quality, or waiting until the current camera network is ready to be replaced in order to integrate AI is expensive, time-consuming, and often unfeasible. However, not all AI video analytic solutions need to be deployed on edge with smart cameras. Instead, video analytics can be deployed both directly on to the camera or have server-based integration maintaining and scaling to your existing camera network. AI video analytics can also analyse a range of videos from low to high resolution in a variety of formats: thermal, infrared, visible. Complex IT structure A single central command centre or in-house security network operates in a multi-manufacturer environment. This means cameras, video management systems, and technology partners can be provided by several manufacturers therefore increasing the complexity of successful IT workflows and integrations. Theft or perimeter infringement can take place in a matter of minutes, therefore the transfer of information between solutions is required to function at top speed. To overcome this complexity, the successful integration of solutions in a multi-manufacturer environment is assured through industry enforced standards set by non-profit organisations. This allows for third-party solutions such as AI video analytics to be easily integrated into the bulk of software and hardware technologies. Diversity in security needs To obtain high performance in a diverse security setting is inherently built into AI video analytic machine  The objective of a surveillance operation can vary greatly from one organisation to another. Retailers prioritise theft detection, while city governments may be concerned about arms detection or people counting. The capacity for AI to function with high performance, meanwhile adapting to several organisation’s security needs requires algorithms to be trained accordingly. To obtain high performance in a diverse security setting is inherently built into how AI video analytic machine learning model’s function. AI can be trained to adapt to different environments and uses progressive learning to increase performance overtime. A collaborative effort between security experts, data scientists and business strategists will ensure high performance and an appropriate application of AI to fit each organisation’s specific needs. Surveillance innovation moving forward While for some video surveillance organisations, the costs and time associated with successfully integrating AI into their network may seem daunting, there are ways to adapt new technology into an existing operation with minimal effort. The emerging presence of smart cameras and IoT products will only accelerate the adoption of AI moving forward. If your organisation is looking to enhance its operation with emerging technologies, now can be the time.

Trends and challenges we will see in the AI-driven security space in 2021
Trends and challenges we will see in the AI-driven security space in 2021

For decades, the nature of global safety has been evolving. From physical security threats like large-scale terrorist attacks and lone actor stabbings to chemical threats such as the Salisbury poisonings and even microbiological threats such as COVID-19, new challenges are constantly arising and the threat landscape we operate in today is constantly changing. Compounding the complexity of the security issues is the complexity and nature of attacks. With the economic downturn, there is the traditional rise in theft, violence and other crimes. Compound this with unmanned businesses and work-at-home staff, and there is a perfect storm for a rise in security threats. Artificial intelligence (AI) and specifically the branch of AI known as machine learning (ML), was already causing widespread disruption in many industries, including the security industry. AI has been a driving force to replace labour-based business models with integrated data and actionable intelligence that is context-aware. It has become apparent that AI will play a big part in the ongoing fight against both pandemics such as COVID-19, as well as other threats that we may face in the future. With all of this in mind, 2021 is poised to be a big year for AI growth. While AI is going to continue to impact our lives in dozens of ways, from smart sensors to face mask compliance detection, the following reflects a few top trends and challenges that I have my eye on for 2021 as we close out this year. The rise of smart city investments One such example is the increasing development of smart cities and how AI can be leveraged to build safe communities. To date, we’ve seen an increase in the number of smart city programmes around the globe; cities that are beginning to deploy innovative technologies for the management and ease of life services. Compounding the complexity of the security issues is the complexity and nature of attacks Typical development of a city includes standard infrastructure - roads, schools, power, water, transportation. Now, internet, data and AI capabilities are part of the standard infrastructure requirements for all new developments. AI promises to deliver increased efficiencies with the infrastructure that will accommodate growing populations while reducing our impact on the environment, resources, and communities. Global cities now account for more than half of the world’s population, and the United Nations projects the number to balloon to 68% by mid-century. Owing to both demographic shifts and overall population growth, that means that around 2.5 billion people could be added to urban areas by the middle of the century, predicts the UN Department of Economic and Social Affairs (DESA). With an increase in population has come an increase in global spending on smart city initiatives to drive down the impact of growing urban concentration. Global spending on smart city initiatives is expected to total nearly $124 billion this year, an increase of 18.9% over 2019, according to IDC's Worldwide Semiannual Smart Cities Spending Guide, while Singapore, Tokyo, London and New York as the big spenders - expected to spend more than $1 billion in 2020. Using AI-driven technology to create safer public and private spaces Today, security solutions driven by AI are being developed and can be covertly deployed across a range of physical environments to protect the population in a more efficient, and accurate manner. As we look ahead to the future of public safety, it’s clear that new AI technology can dramatically improve the effectiveness of today’s physical security space. One such deployment is the use of video object recognition/computer vision software that can be integrated into existing video monitoring security (VMS) systems. These enhanced VMS systems can be deployed both inside and outside of buildings to identify risks and flag threats, such weapons, aggressive behaviours, theft, and safety compliance. This helps to minimise the impact of a breach by an early alert to onsite security in real-time to the location and nature of the potential threat, allowing them to intervene before a loss occurs. These same AI-enabled video solutions can similarly be used to provide advanced business operations in retail, logistics, and manufacturing organisations. Multi-sensor security solutions Also, targeted magnetic and radar sensor technologies, concealed in everyday objects like planter boxes or inside walls, can now scan individuals and bags entering a building for concealed threat objects. Using AI/machine learning, these two sensor solutions combined can identify metal content on the body and bag and match the item to a catalogue of threat items, such as guns, rifles, knives and bombs. Security solutions driven by AI are being developed and can be covertly deployed across a range of physical environments Without this advanced multi-sensor solution, it becomes nearly impossible to discover a weapon on a person's body before it appears in an assailant’s hands. This multi-sensor solution allows for touchless, unobtrusive access to a building, but allows for immediate notification to onsite security when a concealed threat is detected. The hidden technology thus empowers security staff to intercept threats before they evolve into a wider scale attack, while also maintaining the privacy and civil liberties of the public, unless, of course, they are carrying a concealed weapon or pose a physical threat. With the advent of sophisticated surveillance and technological innovation, a level of caution must be exerted. Despite the ongoing global debate, there remains little regulation about the use of AI technologies in today’s physical security space. One thing is certain; it must be deployed in the right place, at the right time, with the right privacy and civil liberty protection objectives. People don’t want to be protected by omnipresent, obstructive and overbearing security systems that infringe on their privacy and civil liberties. They want a proper balance between security and their current way of life, one that must be fused together. Technology and tracing COVID-19 Machine learning-based technologies are playing a substantial role in the response to the COVID-19 pandemic. Traditionally, the key purpose of surveillance systems has been to detect and deter threats, including the detection of visible and hidden weapons and abnormal behaviour. While this, of course, remains a primary focus, today we are seeing how surveillance systems defend against new invisible threats, as well as rapidly automate the process of contact-tracing to capture and contain a virus before it spreads. Again, the ability to track and trace through parsing algorithms that can manage through enormous amounts of data provides a highly scalable and rapid response mechanism to control the spread of threats. AI has demonstrated potential for identifying those displaying symptoms of infectious diseases, without requiring physical human contact Although the threat may not be visible, it is just as destructive. By incorporating AI into existing technologies, government, healthcare and security professionals can monitor public spaces and environments through the combined use of digital and thermal video surveillance cameras and video management systems); just one of the solutions being explored. AI has demonstrated potential for identifying those displaying symptoms of infectious diseases, without requiring physical human contact. By Using AI-powered video analytic software, businesses can monitor face masks, social distancing and large gathering compliance and also detect elevated body temperature. Critically, technology must be capable of both identifying and tracking the virus but also be unobtrusive. An unobtrusive system that is adaptable enough to be deployed across a range of environments where the public gathers in enclosed spaces is necessary to be effective. Security in 2021 Technology has proven itself to be a valuable ally in times of crisis. For smart cities, the use of innovative AI/machine learning technologies will help optimise security solutions in areas that are brimming with potential. As we look ahead to the future of security in a world that is impacted by such a wide range of threats, from physical to chemical to microbiological, it’s clear that new technologies, specifically AI can dramatically improve the effectiveness of security systems and help us to better defend against a wide spectrum of threats. Technology has a huge role to play in making our communities safe in 2021 and beyond, but for security systems to be effective, they must not be oppressive or obstructive. This will ensure they have the full support of the public - the key to success.

Securing your business while working remotely
Securing your business while working remotely

It's a very common purchase for people to seek a smart security camera to remotely link them to their home whilst at work. Now the emphasis has shifted, with a lot more people working from home, business owners should consider a surveillance device to deter would-be thieves, protecting valuable equipment crucial for businesses to operate successfully. A robust security camera setup can aid existing security staff, and give business owners peace of mind out of hours.    According to a recent report, police forces are having to carry out extra night patrols in empty city and town centres, as burglars target shops, pubs and other commercial premises during the pandemic. During these unprecedented times, investing in a video security system can save you and your business money – and in more than one way. In addition to preventing loss of property from inside, surveillance cameras also prevent acts of theft and vandalism by outside individuals However, technology, improved mobile connectivity, apps, and cloud technologies has changed the security market and made it easy for anyone to set up a surveillance ecosystem with easy installation and constant round the clock, cloud monitoring. Plus, you can access footage from anywhere in the world via devices and apps – just in case you have to skip the country! The best cameras for SMBs Most good cameras have the much same functionality: excellent video and audio capabilities, remote access and programming, motion and sound detection, and the ability to capture still or video images and audio and save the data to the Cloud. But the burning question is, when you're trying to find a need in a haystack, what will work best for a small to medium sized business? A robust security camera setup can aid existing security staff, and give business owners peace of mind out of hours Now you can buy cameras that come packed with features such as integrated night vision, 1080p resolution, microSD card slot for local recording, two-way audio functionality as well as the latest latest 128bit encryption. They also have wide-angle lenses allowing users to see more of their office with a single camera, and some come with free, intelligent AI-Based motion detection. The AI gives users more choices on what is captured by the camera and when they should be alerted. Users can specify what types of motion they would like to detect, such as an intruder as opposed to a dog, an object crossing a defined boundary or into a specific area. They can also define multiple zones, alerting them immediately when movement is detected in particular areas. Easy installation is crucial These security cameras should also be easy enough to install and use that you don't need to fork out for expensive expert installation, and many can work with existing CCTV and CCTV DVR systems you may already have set-up. Many of the business security cameras are Wi-Fi enabled and come with their own apps, so you can view footage on your smartphone or tablet, no matter where you are in the world. It means you don't need to pay for a security team to watch the footage at all times (though if you can afford it, that won't hurt), and you can store your videos locally with an NVR on a HD, in the cloud with mydlink or do both with a hybrid NVR/cloud recorder. The apps use Rich Notifications which send a push notification with snapshot to the mobile device the moment activity is detected. Users can react immediately without the need to log into the app by accessing the camera’s live view or calling one of two pre-assigned contacts with a single tap. Any motion-triggered recordings can be saved in the cloud, or locally on a microSD card. Indoor, Outdoor or both? Indoor cameras can be smaller, more lightweight and are usually less intrusive than bulkier outdoor cameras The primary distinction between indoor and outdoor security cameras is the types of external factors each camera has to be able to withstand. While both types of cameras usually come in similar styles and with comparable features, outdoor cameras need to be able to contend with all types of weather and varying light conditions. Outdoor cameras are also more vulnerable to being tampered with, so they are typically made of more durable materials, like metal, and may be heavier or even housed in a casing in order to discourage easy removal. Indoor cameras can be smaller, more lightweight and are usually less intrusive than bulkier outdoor cameras. Both indoor and outdoor cameras utilise features like infrared, allowing for clear pictures in low light conditions and easy transitions when there is a sudden change in light-changing automatically from colour images in bright light to black and white when it gets darker. When doing your research, features to look out for include: Wide angle lens for optimum room view or full view of the front of your property Full HD 1080p at 30fps   ONVIF compatible - Open Network Video Interface Forum - The forum aims to standardize how IP products within the video surveillance industry communicate with each other. Night vision - look at length of the night vision - 5m is about right Your options will depend on your budget and specific needs, but the above features are a great start when you come to buy.

Latest Bosch Security Systems news

Global MSC to debate on the ability of AI to handle live incidents at their virtual event
Global MSC to debate on the ability of AI to handle live incidents at their virtual event

Global MSC Security will debate the ability of artificial intelligence to help Security Managers and Surveillance Camera Operators improve how live incidents are handled. Experts in facial recognition, criminal behaviour will participate in the Developing Smart Surveillance Operators free-to-attend online broadcast on 16th March at 13:00 (GMT). Keynotes will be presented by Dr. Craig Donald, Professor James Ferryman, and Tony Porter QPM LLB, with the broadcast, also featuring an in-depth Q&A panel with technology companies - Genetec, Bosch Security & Safety Systems, and Hanwha Techwin. Automatic visual surveillance Tony Porter is the former Surveillance Camera Commissioner and recently joined the facial recognition company Corsight AI as its Chief Privacy Officer, where is focused on the technological, legislative, and ethical aspects of a technology. James Ferryman is a Professor of Computational Vision at the University of Reading. He will discuss the computer analysis behind CCTV images, focusing on the latest research into automatic visual surveillance of wide-area scenes, using computational vision. Providing insight into the human factors involved in security technology integration will be Dr. Craig Donald, an esteemed organisational psychologist, with a specialist involvement in crime behavioural analysis and detection. Video management systems Technology such AI is placing intelligence in cameras and video management systems" “AI technology has the potential to support operators in making smarter decisions,” comments Dr. Craig Donald. “However, as we move to world where cameras are capable of learning, then both the camera and the operator will need good teachers, to ensure they understand crime behaviour, strategy, and dynamics.” Managing Director of Global MSC Security, Derek Maltby, states: “We are not talking about replacing operators, but enabling them to harness technology that is available right now to work smarter. Traditionally cameras have provided the lens through which operators observe, monitor, and respond to behaviours and actions. However, technology such AI is placing intelligence in cameras and video management systems, enabling them to not only see, but understand, interpret and guide the operator on the appropriate course of action.” Video analytics data A Q&A panel will provide insight into the latest technologies that enable smart surveillance operators. The speakers will be joined by Christian Morin, Vice-President of Integrations & Cloud Services at Genetec who will demonstrate how its Security Centre provides a single intuitive unified interface that enables operators to make sense of complexity. Bosch Security and Safety Systems will be demonstrating how video analytics data and alerts can be optimised by machine learning to support operators with better situational awareness, and Hanwha Techwin will explain how new technologies can enable operators to work smarter not harder. The Global MSC Security ‘Developing Smart Surveillance Operators’ Special Online Event is free-to-attend and takes place on 16th March at 13:00 (GMT).

Bosch releases a new version of AIoT video software solution supporting safe social distancing
Bosch releases a new version of AIoT video software solution supporting safe social distancing

The latest release of ‘Intelligent Insights’ from Bosch offers a software widget update that supports safe social distancing. Intelligent Insights is an ‘AIoT’ video software solution – which combines the connectivity of physical products with the application of artificial intelligence (AI) – that gives customers the power to predict based on live and historical data. Intelligent Insights taps data from Bosch video cameras with built-in AI and pulls it into a single dashboard to support informed decision-making before a potential situation occurs. Minimising coronavirus spread One of the most notable changes caused by the current pandemic is social distancing. Maintaining a precise distance and upholding a maximum threshold of people in gathering areas such as workplaces, shopping centers, and train stations has become critical to minimise coronavirus spread (COVID-19). In light of the challenges imposed by this situation, Intelligent Insights supports social distancing regulations with its latest software widget update. Intelligent Insights supports social distancing regulations with its latest software widget update The new Area fill level traffic light widget offers an intuitive graphical interface that helps users comply with social distancing regulations. The widget visualises the current and maximum number of people allowed in a particular area at a specific time. It illustrates three different states – normal, serious, and critical – as green, yellow, or red, along with corresponding info text, so the user instantly knows when to take action. Traffic light widget Users can opt to live stream the Area fill level traffic light widget on a monitor at an entrance to a supermarket or grocery store, for example, to inform customers whether they may enter the store. When a threshold is reached, the widget can activate and trigger a connected device that will inform visitors with a public announcement, simple alert, or message displayed on a monitor. Intelligent Insights uses built-in AI from Bosch cameras to interpret video images and captures camera metadata from situations involving moving objects, people counting, and crowd detection. The software tool then collects, aggregates, and displays this information using a series of pre-defined widgets enabling users to visualise and evaluate a complete scene from a simple overview screen. Intelligence beyond security Users can select the needed widgets to provide the required information to help predict unwanted situations The dashboard enables users to quickly understand what they see, which helps them respond before a potential situation occurs and delivers business intelligence beyond security. For detailed post-analysis and to help users adjust and alter future actions, Intelligent Insights offers a report function. Intelligent Insights comes with a series of intuitive dashboard widgets that enable users to evaluate a complete scene to support security, safety, and well-being in varying applications. Depending on the application, users can select the needed widgets to provide the required information to help predict unwanted situations or uncover new opportunities. Object positioning widget Area fill level, Occupancy counting, and Crowd detection offer the ability to monitor and detect crowds accurately and count individuals and objects. The user can specify the desired occupancy rate of an area by determining the maximum number of people allowed to be in that area within a given time. Intelligent Insights also offers Object counting and People counting to count objects or people accurately such as when entering or leaving a building. These widgets help identify peak and low times on specific days or over an extended period. Intelligent Insights uses only anonymous data from cameras, ensuring people’s privacy is protected at all times. With the Object positioning widget, users can get a real-time overview of all objects moving in a specific area. Based on their GPS position, which can be determined by cameras that feature built-in AI, the objects are plotted onto a map and classified with icons. Video management system Intelligent Insights, an AIoT video software solution from Bosch, supports social distancing regulations, helps customers respond before a potential situation occurs, and delivers business intelligence beyond security. Intelligent Insights is not only a powerful standalone software package but also designed for seamless integration with other software solutions like the video management system of Bosch (BVMS).

Bosch secures Granarolo plant at Soliera with their Intelligent Video Analytics system
Bosch secures Granarolo plant at Soliera with their Intelligent Video Analytics system

Situated near the picturesque small town of Soliera in northern Italy, the dairy plant of Italian food company Granarolo is anything but small: More than 600 farmers, 70 trucks for the collection of milk and 720 vehicles handle 850,000 tons of milk every year. Its dairy products such as milk, yogurt, ice cream, cheese, and lately also ham and pasta, supply several million Italian families every day. The plant’s huge production capacity is reflected in the size of the perimeter: The Soliera facility stretches out over 45,000 square metres. Furthermore, it is located near a wooded land which is important when it comes to designing a security system aimed at protecting the plant against intrusion. Video surveillance system Granarolo wanted to replace an old analogue video surveillance system by a digital one as its security challenges exceeded the limits of the old installation. The project posed several challenges. The most significant being the vast area of the factory itself, as well as the location of the perimeter near an area that can only be poorly overseen. Since the factory is located in a heavily wooded area, building an appropriate video security system is more challenging because it needs to be safeguarded against false alarms, triggered by ever-changing lights, shadows and the constant movement of trees and plants. Tackling these challenges, Naples-based Bosch partner Gruppo Sirio worked out the modernisation of the plant’s security system, with Bosch cameras featuring built-in Intelligent Video Analytics (IVA) at the heart of the system. Detecting suspicious objects Bosch provided a video surveillance system with 48 cameras of the Dinion series With the help of the security cameras’ integrated video analytics, virtual lines were drawn around the area to be protected against intrusion. When these lines are crossed by intruders, the programmed rules automatically generate alarms, alerting on-site security personnel to intervene. Whether the cameras are tasked with detecting suspicious objects or unusual movements in daylight or night-time, constant surveillance with a special focus on sensitive areas ensures security. In total, Bosch provided a video surveillance system with 48 cameras of the Dinion series. The system, which is managed on one central platform, is completely autonomous and entirely separate from any other system or network in the plant. This ensures maximum security even in the event of potential failures of other systems on site. Perimeter protection solution As a result of the modernisation process, Granarolo can now rely on a system specifically designed for its needs. The newly established, digital video surveillance and perimeter protection solution supports the security personnel in maintaining maximum levels of security through the entire area. It also guarantees that food safety standards in the protected facility are guarded against outside influences. Ultimately, the system allows the staff to fully focus on keeping the production running at all times, thereby contributing to secure the sensitive chain of the Italian food supply against interruptions.

Related white papers

Cloud video and smart cities

Security investments retailers should consider for their 2021 budget

Market Report: Cannabis at a glance