Year: 2021

Rahat Jain Managing Director at IDIS India In recent years, the terms ‘intelligent’ and ‘artificial intelligence (AI)’ have been applied to many different types of security systems, but with little apparent agreement when it comes to a precise definition of what AI is. This is despite the fact that 71% of security professionals report that AI video analytics already provides value to their operations or that they expect it to in the future, according to the IFSEC Global Video Surveillance Report 2020, which analyzed feedback from over 700 security respondents globally. So, it’s important to understand that not all solutions labelled as ‘intelligent’ or ‘powered by AI’ are designed to the same standard or deliver equal value. Many of the early iterations of video analytics rely on Binary Large Object (BLOB) technology. This is found on most modern IP cameras, which is why they are commonly referred to as ‘blob type’ analytics. These are formulated to detect an event such as a virtual line cross; they detect and track objects as ‘motion blobs’ and distinguish them from smaller binary objects. For many applications these are still useful. But video analytics capability has moved considerably beyond this. Today security departments can take advantage of deep learning that leverages neural networks made up of multiple layers of algorithms and advanced processing. This is now driving what is widely accepted to mean true intelligent video analytics. Deep learning engines are ‘trained’ using vast datasets of images and video footage of people, objects and vehicles. They can ‘look for’ size, shape, speed and directional information, and they continue to learn while in use. To an extent, deep learning replicates the way neurons work in the brain – it can analyze and prioritize input from video data to decide which inputs are of value, and it will notify security operatives accordingly. Deep learning’s real value comes from being able to detect suspicious activity or unusual events and eliminate those smaller binary objects that are just ‘noise’ and apply rules that meet with specific applications and operational requirements. In addition, deep learning should enable users to use metadata to search multiple camera streams to find the most accurate matches for persons or vehicles of interest within minutes. But again, some caution is needed. Deep learning video offerings can still disappoint, generally as a result of having been launched too early, before engines were fully trained and able to recognize objects reliably and accurately. Systems integrators need to exercise caution regarding claims and jargon. They need to understand which offerings and which functions will genuinely add value for their customers, and help them to increase productivity, provide useful business intelligence, and ensure they deliver RoI, long term. Overcoming the Common Challenges Caused by False Alarms The 2020 IFSEC Global Video Surveillance report cited reducing false alarms as the #1 reason for adopting AI – and for good reason. Traditional blob type analytics cameras are prone to being triggered by environmental factors such as heavy rain, snow or moving foliage, and struggle to distinguish a human presence, which may present a threat from harmless animal activity. For users, this can result in time being wasted investigating the cause of alarms, and the larger the site, or more overstretched the system operator, the worse that problem can be. ALARM OVERLOAD Alarm overload is a common problem. Operators can quickly become desensitized by false alarms and can start missing genuine threats, or even be tempted to shut off the system. Alarm receiving centers and virtual guarding firms typically increase charges for more frequent call outs and they may even withdraw monitoring services from problematic sites until cameras are re-configured or replaced. This can result in organizations needing to draft in additional security officers, to maintain protection, or risk leaving gaps in security. Over time, many organizations find it unfeasible to maintain systems that are prone to false alarms. The solution? By moving to deep learning-based analytics, customers can attain improved situational awareness, with highly accurate AI-assisted notifications for intrusion, object, loitering, and unusual event detection. Security operators will be better able to manage everyday events, and respond to more serious threats and emergencies. In short, safety and security are enhanced by better detection and verification. ELIMINATING OPERATOR FATIGUE AND INCREASING EFFICIENCY Unlike human brains deep learning engines don’t get tired. They can constantly monitor multiple camera streams in search of suspicious behavior, maintaining performance levels even in the busiest scenes such as retail malls, logistics centers, higher education settings and outdoor spaces. Relying on human operators to monitor multiple cameras means hiring enough staff to cope and allowing for regular breaks to ensure they stay alert. Using AI-assisted notifications free-up operators from having to constantly monitor multiple camera streams and video walls. Instead, they can respond quickly and flexibly, and not just from the control room. They can configure alarms to be received to client software, and on mobile devices such as smartphones and tablets, giving the ability to verify and respond to events on the move. Improving the ability of security managers to oversee security operations away from the control room – by giving them more accurate information along with powerful VMS functionality and tools – lets them better manage incidents on the ground and direct their teams. The latest generation of AI-assisted tools can transform the work of security teams. Today’s truly smart video technology can allow security provision to be better focused, with officers being re-deployed to more important tasks that add greater value to their roles, for example giving them time to engage with the people they are helping to safeguard rather than remaining unseen in the control room. And strategically, heads of security can interpret and use accurate real-time and historical data to drive more informed decision-making, to better mitigate risk across their enterprise. Speeding Up Investigations with The Power of Metadata Deep learning and intelligent video analytics capture metadata even when analytics rules are not applied, meaning that users can benefit from advanced…

  For video security cameras and systems, capturing images simulates our sense of sight, extending the power of people’s ‘eyes.’ But what if they could use other kinds of senses like ‘hearing’, ‘smelling’, ‘heat sensing,’ or even detections that are beyond visual range – to identify and respond to security incidents? From single to multiple sensors, video security systems evolve with each new trend to fulfill a new potential, and there are already many beneficial advancements being developed across the industry today – and expanding perceptions is one. There’s no doubt multiple-perception capabilities will make video security systems more powerful – sensing the outside environment, identifying events, and providing more detailed information. This will also create more possibilities for video security systems to be used in ever wider scenarios and applications. Cameras integrated with radar Cameras integrated with centimeter and millimeter wave radars are becoming a popular approach in object detection. Radar has shown great advantages in object detection and movement tracking, which can offer accurate and reliable detection over long distances, unaffected by any kind of weather. Equipped with a deep integration of radar and video, a multi-dimensional camera extends perception in perimeter protection to find objects earlier, track movement, and provide visual images to verify detected objects. Such integration overcomes the technological bottleneck of traditional one-dimensional video perception. It has been applied in traffic safety management to improve detection of potential obstacles or traffic incidents at great distance, out of visual range and in low-visibility conditions. The integration is also ideal for monitoring large, exposed spaces with harsh weather such as sea ports, airports and large open industrial areas. Video cameras equipped with sonar arrays Automobile horn noise bothers residents who live near major roadways, but in many cities it has been difficult for traffic control departments to reduce it. A video camera equipped with sonar arrays capable of collecting both sound and image data can be used for automobile horn detection. The camera integrated with sonar sensors can precisely detect and locate the source of a vehicle’s horn while identifying the vehicle and generating photos and videos of the event as evidence. Local law enforcement can respond as necessary, helping to reduce noise pollution on roadways and in communities with rules against the unnecessary use of horns. Multispectral imagery Multispectral imagery is another promising approach for cameras to perceive information from non-visible light spectra. Popular thermographic cameras use infrared radiation to perceive temperature of objects, and the detection of other non-visible light spectra is currently being explored in the security industry. For instance, electric arc is a key phenomenon to indicate that power grids are aging, and the electrical discharge emits non-visible ultraviolet (UV) lights. Here innovative UV detection can boost the perception capabilities of cameras to capture invisible electric arc phenomena, and finds a critical application in safety-checks at aging power grids in the electricity industry. Alarm systems with wide range of detectors Along with video security devices, other conventional security systems have incorporated multiple perception sensors, too. For example, alarm systems that employ a wide range of detectors and peripherals have borrowed the practice. Today’s wireless alarm systems normally include a compact panel hub and a wide range of detectors and peripherals, covering intrusion detection, video verification, smoke and flood detection etc. With these detectors and peripherals, alarm systems can collect data and multi-dimensional information to fully protect homes, commercial buildings, factories, and more. And there is more to come Increasingly powerful edge computing and intelligent algorithms are becoming available to the security industry, and we are constantly seeing more integrated security devices and systems with multiple sensors. Therefore, we believe that in the near future, additional ‘senses’ – like smoke detection, humidity and temperature measurement, and even gas pressure detection – can be widely embedded in video cameras and systems to precisely monitor and report events or incidents. The multi-dimensional perception trend will very likely and very powerfully shape security systems in the near future and endow them with more capabilities to create safety for users.  

Pranali Chaudhari Sr. Data Scientist at Dimensionless Technologies Pandemic brought the travel industry to a standstill last year but with vaccinations being administered around the globe, things are starting to look up and the normalcy would return sooner than later. Public transport systems, monuments and places of mass gathering are always under serious threat from radical organisations. There have been multiple security incidents due to the failure of personnel at security checkpoints – 9/11, London Bombing or Mumbai blasts are prime examples of this. Millions of people pass through security checkpoints daily across airports, metro stations, railway stations, prisons, government buildings, stadiums etc. With the pandemic receding and travel picking up the queues have started to get longer at these checkpoints now The current baggage screening process uses X-ray scanning technology which has not had any upgrades in the past many years. Any security lapse has always been attributed to human screeners, policies and processes focused on better training methods for improving their performance. One such example could be reducing the duration for which a screener looks for threats in the x-ray scan to 20 minutes. But the incidents continue to happen, at least 3 firearms are missed by TSA (transportation security agency). Manual detection of banned items in x-ray images is an intricate task and is highly prone to human error due to fatigue. Baggage handling and security are major operational challenges, and sometimes contribute to flight delays as well. To mitigate these challenges, a high-performance intelligent baggage scanner system is needed. Dimensionless Technologies, an AI company founded by IIT alumnus has developed BaggageAI, using artificial intelligence and data processing technology, to completely overhaul this manual process and automatically detect and locate threat items in x-ray scan images. It is a sophisticated high-performance artificial intelligence (AI) based system for automatic object detection of banned items in baggage through x-ray images. It looks at each image like a human eye, outlines banned objects and sends alerts to the screen. Existing scanners work on manual detection, but this solution automates the process of finding and locating prohibited items in the x-ray image of the scanned baggage. BaggageAI has been developed for the most frequent common items, which are contraband like guns, knives, sharp objects, power bank, battery, coconut, lighter, e-cigarette etc. Solution readily deployable for The solution has been selected by the Airport Authority of India for pilot and deployment to improve efficiency of security personnel. The pilot run of the solution was successfully conducted at Pune International airport last year and is being put into other airports like Ahmedabad International airport and Delhi International airport. Metro Corporations like DMRC and Mumbai metro are also trying out the solution and the pilot run is scheduled at a couple of metro stations in March. BaggageAI is a very fast solution that can process up to 3 images per second or up to 180 bags/ minute. This will greatly reduce the time taken at security checkpoints and make it highly convenient to the passengers. It helps detect threats with high accuracy and efficiency, and reduces false alarms, saving invaluable time. High throughput helps airports handle more passengers and flights per day, resulting in higher revenues and profits. This boosts passenger security significantly by removing human errors in the baggage screening process. It can be effectively deployed at places with high passenger traffic such as airports, metros, malls and railway stations where there is a security risk. Another amazing benefit of the solution lies in the fact that it can get integrated to any existing x-ray baggage scanner system. This greatly enhances the possibility of upgrading all existing machines and improving the security checkpoints to the next level. “Human screeners are expected to be correct 100% of the time – which is an impossible task. That’s why we have brought machines into play to ensure the stress on screeners reduces significantly and the process is automated. It will go a long way in enhancing security and customer experience across the globe. With central monitoring of the baggages through a combination of human and AI can significantly reduce operational cost across various application areas,” explained Kushagra and Himanshu, the founders of the organisation.