When a child goes missing in a large, crowded mall, we have a panicking mom asking for help from the staff, at least a dozen cameras in the area, and assuming the child has gone missing for only 15 minutes, about 3 hours’ worth of video to look through to find the child. Typical security staff response would be to monitor the video wall while reviewing the footage and making a verbal announcement throughout the mall so the staff can keep an eye out for her.

There is no telling how long it will take, while every second feels like hours under pressure. As more time passes, the possible areas where the child can be will widen, it becomes more time-consuming to search manually, and the likelihood of finding the child decreases. What if we can avoid all of that and directly search for that particular girl in less than 1 second?

Artificial neural networks are improving every day and now enable us to search for a person across all selected camera streamsWith Artificial Intelligence, we can. Artificial neural networks are improving every day and now enable us to search for a person across all selected camera streams in a fraction of a second, using only one photo of that person.

The photo does not even have to be a full frontal, passport-type mugshot; it can be a selfie image of the person at a party, as long as the face is there, the AI can find her and match her face with the hundreds or thousands of faces in the locations of interest. The search result is obtained in nearly real time as she passes by a certain camera.

Distinguishing humans from animals and statues

The AI system continuously analyses video streams from the surveillance cameras in its network, distinguishes human faces from non-human objects such as statues and animals, and much like a human brain, stores information about those faces in its memory, a mental image of the facial features so to speak.

When we, the system user, upload an image of the person of interest to the AI system, the AI detects the face(s) in that image along with their particular features, search its memory for similar faces, and shows us where and when the person has appeared.

We are in control of selecting the time period (up to days) and place (cameras) to search, and we can adjust the similarity level, i.e., how much a face matches the uploaded photo, to expand or fine-tune the search result according to our need. Furthermore, because the camera names and time stamps are available, the system can be linked with maps to track and predict the path of the person of interest.

The AI system continuously analyses video streams from the surveillance cameras in its network, distinguishing, human faces from non-human objects
AI Face Search is not Face Recognition for two reasons: it protects people’s privacy, and it is lightweight

Protecting people’s privacy with AI Face Search 

All features of face recognition can be enabled by the system user, such as to notify staff members when a person of interest is approaching the store AI Face Search is not Face Recognition for two reasons: it protects people’s privacy, and it is lightweight. First, with AI Face Search, no names, ID, personal information, or lists of any type are required to be saved in the system. The uploaded image can be erased from the system after use, there is no face database, and all faces in the camera live view can be blurred out post-processing to guarantee GDPR compliance.

Second, the lack of a required face database, a live view with frames drawn around the detected faces and constant face matching in the background also significantly reduces the amount of computing resource to process the video stream, hence the lightweight.

Face Search versus Face Recognition

AI Face Search

Face Recognition

Quick search for a particular person in video footage

Identify everyone in video footage

Match detected face(s) in video stream to target face(s) in an uploaded image

Match detected face(s) in video stream to a database

Do not store faces and names in a database

Must have a database with ID info

Automatically protect privacy for GDPR compliance in public places

May require additional paperwork to comply with privacy regulations

Lightweight solution

Complex solution for large-scale deployment

Main use: locate persons of interest in a large area

Main use: identify a person who passes through a checkpoint

Of course, all features of face recognition can be enabled by the system user if necessary, such as to notify staff members when a person of interest is approaching the store, but the flexibility to not have such features and to use the search tool as a simple Google-like device particularly for people and images is the advantage of AI Face Search.Because Face Search is not based on face recognition, no faces and name identifications are stored

Advantages of AI Face Search

Artificial Intelligence has advanced so far in the past few years that its facial understanding capability is equivalent to that of a human. The AI will recognise the person of interest whether he has glasses, wears a hat, is drinking water, or is at an angle away from the camera.

In summary, the advantages of Face Search:

  1. High efficiency: a target person can be located within a few seconds, which enables fast response time.
  2. High performance: high accuracy in a large database and stable performance, much like Google search for text-based queries.
  3. Easy setup and usage: AI appliance with the built-in face search engine can be customised to integrate to any existing NVR/VMS/camera system or as a standalone unit depending on the customer’s needs. The simple-to-use interface requires minimal training and no special programming skills.
  4. High-cost saving: the time saving and ease of use translate to orders of magnitude less manual effort than traditionally required, which means money saving.
  5. Scalability: AI can scale much faster and at a wider scope than human effort. AI performance simply relies on computing resource, and each Face Search appliance typically comes with the optimal hardware for any system size depending on the customer need, which can go up to thousands of cameras.
  6. Privacy: AI Face Search is not face recognition. For face recognition, there are privacy laws that limits the usage. Because Face Search is not based on face recognition, no faces and name identifications are stored, so Face Search can be used in many public environments to identify faces against past and real-time video recordings.
Face Search can be used in many public environments to identify faces against past and real-time video recordings.
AI Face Search match detected face(s) in video stream to target face(s) in an uploaded image

Common use cases of AI Face Search

In addition to the scenario of missing child in a shopping mall, other common use cases for the AI Face Search technology include:

  • Retail management: Search, detect and locate VIP guests in hotels, shopping centres, resorts, etc. to promptly attend to their needs, track their behaviour pattern, and predict locations that they tend to visit.
  • Crime suspect: Quickly search for and prove/disprove the presence of suspects (thief, robber, terrorist, etc.) in an incident at certain locations and time.
  • School campus protection: With the recent increase in number of mass shootings in school campuses, there is a need to identify, locate and stop a weapon carrier on campus as soon as possible before he can start shooting. Face Search will enable the authorities to locate the suspect and trace his movements within seconds using multiple camera feeds from different areas on campus. Only one clear image of the suspect’s face is sufficient.

In the race of technology development in response to business needs and security concerns, AI Face Search is a simple, lightweight solution for airports, shopping centres, schools, resorts, etc. to increase our efficiency, minimise manual effort in searching for people when incidents occur on site, and actively prevent potential incidents from occurring.

By Paul Sun, CEO of IronYun, and Mai Truong, Marketing Manager of IronYun

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

In case you missed it

Remote Monitoring technology: Tackling South Africa’s cable theft problem
Remote Monitoring technology: Tackling South Africa’s cable theft problem

For decades, cable theft has caused disruption to infrastructure across South Africa, and an issue that permeates the whole supply chain. Here, Ian Loudon, international sales and marketing manager at remote monitoring specialist Omniflex, explains how new cable-alarm technology is making life difficult for criminals and giving hope to businesses. In November 2020, Nasdaq reported that, “When South Africa shut large parts of its economy and transport network during its COVID-19 lockdown, organised, sometimes armed, gangs moved into its crumbling stations to steal the valuable copper from the lines. Now, more than two months after that lockdown ended, the commuter rail system, relied on by millions of commuters, is barely operational.” Private security firm Despite this most recent incident, cable theft is not a new phenomenon to sweep South Africa Despite this most recent incident, cable theft is not a new phenomenon to sweep South Africa. In 2001, SABC TV broadcast a story following two members of a private security firm working for Telkom, a major telecoms provider. In the segment, the two guards, working in Amanzimtoti on the south coast of KwaZulu-Natal, head out to investigate a nearby alarm that has been triggered. They reach a telecoms cabinet and discover that it has been compromised, with the copper cable cut and telephone handsets strewn across the ground. In the dark, they continue to search the area when one of the guards discovers the problem: 500 metres of copper wire has been ripped out. In their haste, the thieves have dropped their loot and fled. Widespread cable theft Had they managed to get away, they would have melted the cable to remove the plastic insulation and sold the copper to a local scrap dealer for around 900 Rand, about $50 US dollars. For the company whose infrastructure has been compromised, it may cost ten times that amount to replace and repair the critical infrastructure. The disappointing takeaway from this story is that two decades on from this incident the country still faces widespread cable theft, whether it’s copper cables from mines, pipelines, railways, telecoms or electrical utilities. In fact, the South African Chamber of Commerce and Industry estimates that cable theft costs the economy between R5–7 billion a year. The answer to the problem must go further than the existing measures used by companies. Detect power failure Most businesses already invest in CCTV, fences, barriers and even patrol guards, but this is not enough. Take the mining sector, for example. These sites can be vast, spanning dozens of kilometres - it’s simply not cost effective to install enough fences or employ enough guards or camera operators. As monitoring technology gets better, the company has seen site managers increasingly use cable alarms in recent years that detect when a power failure occurs. The idea is that, if one can detect a power failure, they can detect whether the cable has been cut The idea is that, if one can detect a power failure, they can detect whether the cable has been cut. The problem is though: how does one distinguish the difference between a situation where a cable has been cut intentionally and a genuine power outage? Power outages in South Africa are an ongoing problem, with the country contending with an energy deficit since late 2005, leading to around 6,000 MW of power cuts in 2019. Remote terminal units Eskom Holdings SOC Ltd., the company that generates around 95 per cent of South Africa’s power has already warned of further blackouts as the company works to carry out repairs to its power plants. According to a statement on the company’s website, “Eskom spends in the region of R2 billion a year replacing stolen copper cables." The result is that criminals take advantage of the gaps in power to steal cable, timing their robberies to coincide with the published load shedding schedules. The basic alarms used to detect power outage won’t recognise the theft because they register a false-positive during a power cut. By the time the power comes back on, the deed has been done and the criminals have gotten away with the cable. The good news is that recent breakthroughs in cable monitoring technology are helping tackle just this problem. New alarms on the market now combine sophisticated GSM-based monitoring systems that use battery powered remote terminal units. Legitimate supply chain Unlike the basic alarms that look for the presence or absence of power, these new systems monitor whether the cable circuit is in an open or closed state. In the event of a power outage, the unit continues to run on battery power and can detect if a cable has been cut, sending a priority SMS alert to the site manager immediately, giving them a fighting chance to prevent a robbery in progress. Beyond the opportunistic theft carried out by petty criminals, the theft of copper cables forms a wider problem Beyond the opportunistic theft carried out by petty criminals, the theft of copper cables forms a wider problem across the supply chain in South Africa. In recent years, the combination of unscrupulous scrap dealers, the alleged involvement of large scrap processing companies and lax penalties meant that much of the stolen copper ended up back in the legitimate supply chain. However, recent changes in the law have sought to take a tougher stance on copper theft. Alarm monitoring technology According to the Western Cape Government, “The Criminal Matters Amendment Act, regulates bail and imposes minimum offences for essential infrastructure-related offences." The act, which came into effect in 2018, recommends sentencing for cable theft, with the minimum sentence for first-time offenders being three years and for those who are involved in instigating or causing damage to infrastructure, the maximum sentence is thirty years. It seems to be working too. In January 2021, the South African reported that a Johannesburg man was sentenced to eight years behind bars for cable theft in Turffontein. While the longer-term outlook is a positive one for industry, the best advice for businesses seeking to alleviate the problem of cable theft in the immediate future is to invest in the latest cable-theft alarm monitoring technology to tackle the problem and make life difficult for criminals.

What are the positive and negative effects of COVID-19 to security?
What are the positive and negative effects of COVID-19 to security?

The COVID-19 global pandemic had a life-changing impact on all of us in 2020, including a multi-faceted jolt on the physical security industry. With the benefit of hindsight, we can now see more clearly the exact nature and extent of that impact. And it’s not over yet: The pandemic will continue to be top-of-mind in 2021. We asked this week’s Expert Panel Roundtable: What have been the positive and negative effects of Covid-19 on the physical security industry in 2020? What impact will it have on 2021?

Maximising supermarket safety with real-time surveillance solutions
Maximising supermarket safety with real-time surveillance solutions

Supermarket employees have been the hidden key workers of the past year, keeping shelves stocked and queues under control as panic buying gripped the nation. As a result of being expected to enforce face covering and social distancing regulations, they also been asked to act as de-facto security guards alongside their existing duties. This is problematic as many employees have never had to deal with this kind of responsibility before, let alone received any conflict de-escalation training. In order to maintain the safety and security of their staff retailers must take additional steps to uphold their duty of care, with the NPCC recently specifying that it is the responsibility of retailers ‘to manage entry to their stores and compliance with the law while customers are inside’. Supermarkets in particular need to be aware of this requirement, as the big four recently announced that their employees would now be challenging customers shopping in groups and those not wearing masks. Verbal abuse from the public Crime against retail employees has already been a major issue over the course of the pandemic, confirmed by research from the Union of Shop, Distributive and Allied Workers that found 90% of retail staff in the UK experienced verbal abuse last year. The Co-op has recently been vocal about the effects of the pandemic and lockdown-related frustrations on its employees.90% of retail staff in the UK experienced verbal abuse last year The supermarket reported a 140% increase in crime within its stores over the past year, with many of the 200,000 cases related to verbal and physical abuse experienced by employees. Jo Whitfield, Co-op Food chief executive, confirmed that the number of issues has already increased drastically as a result of staff enforcing COVID-secure guidelines. So, what steps must retailers take to ensure their duty of care remains intact as employees take on new enforcement responsibilities? Introducing real-time surveillance technology to support security guards and shop floor employees alike is vital. Bolstering front line defences Security guards posted at supermarket entrances are the first line of defence against shoppers determined to break the rules. However, they are now being pulled in multiple directions with queues to monitor and occupancy to manually keep track of, along with the usual security alarms to respond to. With one person usually posted at the entrance at any one time it’s simply impossible to have eyes everywhere, which is where automated video surveillance comes in. COVID-specific technologies, such as mask detection and occupancy management systems, are now the golden bullet to retail safety and security.Mask detection and occupancy management surveillance tools can automatically alert a shopper Mask detection and occupancy management surveillance tools can automatically alert a shopper whether or not they are allowed to enter the store on their approach to the door. The system surveys the person and a screen will automatically display different instructions depending on the situation: whether they must put a mask on before they enter, wait until capacity is low enough to enable social distancing or, if the previous criteria are fulfilled, that they are free to enter. COVID-secure safety This stand-off technology minimises the need for contact between security personnel and shoppers, allowing security guards to complete their usual duties, safe in the knowledge that the store is being managed in a COVID-secure way. With a hands-off approach enabled by surveillance technology, the potential for tense confrontation is greatly diminished as customers will usually comply to the reminder shown to them and put on a mask or wait without further prompting from staff. With security personnel able to better focus their attention on the stubborn rule-breakers,It is crucial that retailers choose a solution embedded in real-time connectivity this responsibility will no longer land with staff on the shop floor who are often ill-equipped to deal with this situation. It is crucial that retailers choose a solution embedded in real-time connectivity that will allow all store entrances to be screened simultaneously. Nobody can be in multiple places at once, but this connectivity allows alerts to be streamed instantly to any connected device that can be monitored by just one employee, meaning they can review the alerts that require their attention without needing to be physically present or re-tasked away from their day-to-day duties. Instant reassurance with body worn tech As a customer-facing role, there can be no guarantee that shop workers will never experience a potentially violent confrontation with a customer, which is where the presence of live streaming body worn cameras can help. While they may not always be trained to de-escalate a risky situation, being able to discreetly call for assistance can provide the reassurance employees need to feel safe and supported at all times. If an employee asks a customer to put a mask on while they’re in the store or step back from another shopper and the situation turns abusive – verbally or physically – a live streaming-enabled body worn camera can be triggered to stream a live audio and video feed back to a central control room manned by trained security personnel.A live streaming-enabled body worn camera can be triggered This real-time footage gives security staff exceptional situational awareness, allowing them to fully assess the situation and decide on the best course of action to support the employee in distress, whether that is going to the scene to diffuse the situation or contacting the police in more serious circumstances. Bolstering front line security This goes one step further than record-only body worn cameras, the capabilities of which these next generation devices match and exceed. Record-only cameras are well-suited to provide after-the-fact evidence if a customer interaction turns sour, but they do little to provide reassurance to out of depth employees in the moment. The duty of care grocery retailers must provide to their employees has never been more important, with staff taking on new mask and social distancing enforcement responsibilities and managing interactions with frustrated customers. Bolstering front line security and giving staff extra reassurances with the introduction of real-time video surveillance technology is a crucial step for retailers striving to keep employees and shoppers safe during these challenging times.