The COVID-19 pandemic has presented an unprecedented challenge to businesses. From retail stores to office buildings to warehouses and construction sites, a big question looms: how can landlords, executives, and employers ensure their facilities don’t contribute to the spread of the virus?

A low-tech solution - the face mask - has become a leading preventative measure. But, a high-tech solution is necessary to ensure that everyone is wearing them. Cameras powered by artificial intelligence can now identify whether or not people entering a facility are wearing facemasks and help enforce adherence to mask mandates. This technology is proving to be a cost effective solution that reduces risks of confrontations over masks policies and gives managers the data they need to document regulatory compliance and reduce liability.

Layers of security

They can also be integrated into access control systems or woven into other preventative measures that create overlapping layers of security. These cameras are an ideal solution for low-traffic, remote sites, or areas that are only accessible to employees that need to monitor mask compliance but at which hiring a manned guard is just too expensive.

Cameras with mask detection capabilities are especially useful when the technology piggybacks on existing autonomous devices, such as mobile security drones.

The premise is simple. When a person without a mask is detected by the autonomous robotic security device, the system can generate, depending on customer preferences, audible and visible alerts to remind people to mask up. It also feeds alerts to a cloud-based data storage system so that security executives can analyze data for trends or quickly locate video of important incidents.

Why masks?

One study published in the Proceedings of the Royal Society A highlights the benefits of mask usage. If just 50 percent of people use masks, the rate of COVID-19 transmission will slowly decline. If 80 percent of people use them, the rate will plummet.

Bu,t people don’t love wearing them. They’re hot. They make eyeglasses foggy. It’s hard to make yourself heard when talking to others. We’re all familiar with industries that wear masks of some type or other, on a regular basis - health care, construction, and heavy industry to name a few. But for the general public, wearing a mask for long periods of time is not a regular habit.

For the general public, wearing a mask for long periods of time is not a regular habit

We also know that other measures site managers have used to limit the spread of coronavirus are ineffective. For example, at least three meatpacking plants rank among the top 50 locations for coronavirus clusters. One factor driving that spread: many employees, to avoid missing a day’s pay, masked their mild fevers with ibuprofen to fool the infrared temperature scanners that employers used to protect against the outbreak.

The paradox of masks, however, isn’t that they protect the wearer from infection. It’s the other way around: when an infected person wearing a mask sneezes, coughs, or breathes, they don’t spread the virus as far, and thus masks slow the spread of the virus from infected people, including those that are not showing symptoms.

Prove it

One of the very reasons why county and state governments have instituted mask orders is simple: it’s an easily verifiable sign that an organization is taking steps to limit the spread of coronavirus. Mask detection cameras, coupled with autonomous security systems, can provide the documentation employers need to ensure mask compliance.

Imagine, for example, a warehouse full of manual laborers. The county orders everyone to wear a mask any time they leave home. A disgruntled employee, recently terminated, files an anonymous complaint to local health officials stating that the warehouse isn’t enforcing mask compliance - or worse, preventing employees from wearing masks to prevent theft. The county sends an inspector.

Mask detection cameras provide site managers with the documentation they need to disprove these allegations. The autonomous systems developed by RAD will feed video footage into a cloud database, documenting not only the instances of non-compliance, but also the instances of compliance - with the mask clearly highlighted. Any inspector that arrives on a job site can see hours and hours of footage, without having to pour through hours of video.

Reducing confrontation

We’ve all seen the videos in which angry shoppers confront retail clerks and security guards over mask usage. In some cases, these confrontations have turned violent, resulting in injury or death. For every one of these videos, there may well be hundreds of others.

While most of the videos featuring mask confrontations focus on retail settings, manned guards also face challenges in enforcement. Confrontations over mask usage have the potential to drive up workman’s compensation claims higher when guards are injured. Because autonomous security units generate alerts automatically, the chance of confrontation is minimised.

It’s easy to imagine a couple of scenarios in which autonomous units can be beneficial. In health care settings, where emotions run high, autonomous devices can serve as a force multiplier for patrolling guards in parking areas. For example, roving units can identify people that are not wearing masks, and remind them to do so before they enter the building. These can also be placed in entryways that generate alerts as visitors approach doors.

In many buildings, mask detection systems can be integrated into access control systems

Autonomous security units can be deployed for a fraction of the cost of manned security. In healthcare, autonomous units can be used to re-allocate security spending, placing less emphasis on low intensity guards whose primary function is to observe and report - particularly those that patrol parking garages - and more emphasis on trained professionals capable of defusing confrontations inside the hospital. In other words, autonomous units outside allow facilities to hire better quality inside, where confrontations are most likely to take place. In many buildings, mask detection systems can be integrated into access control systems, which might be especially useful at entrances that are not manned by security, but accessible via key card.

Changing behaviors

There was a time when smoking in public was not seen as particularly anti-social. Almost everyone will stop at a stop sign, even when we can see for miles in every direction, and we know that the risk of an accident is zero.

We do these things because we have been trained to. These behaviors make us safer, but we didn’t adopt them overnight. Many of us forget, but the fight over banning smoking in bars and restaurants was filled with confrontation.

So, too, will it be with mask compliance. But time is short, and we all need to do everything we can to encourage good behavior. Mask detection technology can do that, and these solutions are very cost effective. In some cases, the cost may be just 5 percent of using a manned guard. They’re effective too. Autonomous systems enforce mask policies consistently and drive accountability. That can make us all safer.

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

In case you missed it

HID Global Pilot Program Demonstrates Social Distancing and Contact Tracing
HID Global Pilot Program Demonstrates Social Distancing and Contact Tracing

If one employee stands less than six feet away from another employee, a fob attached to a lanyard around his or her neck emits an auditory beep – an immediate reminder to observe social distancing. If an employee were to be diagnosed with COVID-19, a cloud-based database provides a record of who at the company the sick employee had contact with. These capabilities of HID Location Services ensure social distancing and provide contact tracing to enable companies to return to work safely. They have been deployed in a pilot program at HID Global’s Corporate Headquarters in Austin, Texas. Social distancing using a BLE beacon To ensure social distancing, a Bluetooth Low Energy (BLE) beacon is emitted from an employee’s fob (or from a badge that has the same functionality). The beacon communicates peer-to-peer with a beacon emitted by another employee’s fob or badge to alert if the location of the two employees is less than six feet apart. To ensure social distancing, a Bluetooth Low Energy (BLE) beacon is emitted from an employee’s fob For contact tracing, the beacons communicate via a nearby “reader” (a BluFi BLE-to-Wi-Fi gateway) to the Bluzone cloud-based software-as-a-service. The building area covered by each reader constitutes a “zone,” and the system records when two beacons are signaling from the same zone, which indicates contact between employees. In effect, the system records – historically and forensically – who was near whom (and for how long) using the zone-based approach. “In the workplace, we provide organizations with visibility into the location of their workforce,” says Mark Robinton, Vice President, IoT Services Business Unit at HID Global. Pilot program spans variety of environments By documenting where a sick individual moved in the building, the system also can guide any need to close off a certain area for deep cleaning. Instead of quarantining a whole building, a company could quarantine a small subset of employees who were likely exposed. Importantly, the system only reports data, while management makes the actual decisions about how to respond. The site of the pilot program is the 250,000-square-foot HID Global facility in Austin, which includes a variety of environments, including manufacturing areas, an executive suite, cubicles, a training area, a cafeteria, and lobbies. This spectrum of use cases enables the pilot program to evaluate how the system works in various scenarios. The building in Austin has two floors, plenty of natural lighting and emphasises sustainability in its design. HID Location Services ensure social distancing and provide contact tracing Pilot starts small and expands For the pilot program, 80 readers were installed in a wide area in the facility, including a variety of environments. Initially 30 badges and 30 fobs, all BLE-enabled, were issued to employees. If a badge identifies another nearby beacon (suggesting a social distancing failure), it emits a blinking LED light, which can be seen by the offending co-worker. The fobs emit an audible beep, which employees have overwhelmingly said they prefer. Observers overseeing the pilot program have documented employee reaction and comments. It emits a blinking LED light, which can be seen by the offending co-worker There were challenges in setting up the pilot program remotely to ensure fewer employees were on site during the pandemic. The equipment was provisioned in Florida and then shipped to the Austin location. Fine-tuning was required to adjust the signal strength of the BLE beacons. The badges were initially more powerful, but the strength was dialed back to be comparable to the fobs and within the six-foot social distancing range. Signal strength is also a variable in diverse environments – the 2.4 Ghz signal tends to reflect easily off metal, so adjustments in signal strength are needed in a factory setting, for example, versus a collection of cubicles.   “This facility is large enough and diverse enough that it provides great test results and quality data to analyze,” says Dean Young, Physical Security Manager at HID Global. “Our employees are eager to be part of the pilot to demonstrate that we use the technologies we provide to our customers, and they want to help us stay in compliance with social distancing and contact tracing.” Ensuring privacy while protecting employees HID Global’s headquarters had approximately 425 employees before the coronavirus pandemic lowered the number drastically to include only essential workers. As more people return to work, additional fobs and badges are being issued to expand the scope of the pilot program. The program is also incorporating contact tracing of suppliers and others who visit the facility. Except when triggered by contact among employees, locations are not recorded. Each employee’s location is always available in real-time (e.g. in case of an emergency), but they are not “tracked.” Through BluFi placement and geofence capabilities, the system closes off private areas where location should not be monitored, such as a rest room. Geofencing also identifies when employees enter and/or exit the area covered by the pilot program. Although each beacon is associated with an employee, the employee’s identity is not part of the data stored in the cloud, so there are no privacy concerns. Data is completely anonymized, and no personally identifiable information (PII) is stored in Bluzone. Other computer systems in a company, such as a human resources (HR) program, can privately and securely store the identities associated with each beacon.   Other applications for HID location services In addition to social distancing and contact tracing applications, HID Location Services offer other use cases ranging from asset tracking and employee safety/security to location analytics. For example, the system can analyze room usage for better building management and operational efficiency. It can also quickly find people in emergency situations. These use cases ensure continued value for a system even after concerns about social distancing and contact tracing have faded. The system can analyze room usage for better building management and operational efficiency Another big selling point is the ability of a company to be better prepared in case of a future pandemic, or a second wave of this one, says Robinton. The HID Location Services social distancing and contact tracing applications will be available at the end of Q3 and will be rolled out through HID Global’s existing integrator channel. Vertical markets likely to embrace the technology include healthcare, where hospitals need to track patients as they come in and to know which other patients or staff they may have been exposed to. The financial sector is another likely market, as is manufacturing, which is looking to avoid the prospect of shutting down an entire plant. It’s better to address the three or four people who were near a sick employee than to shut down the plant. In the hospitality industry, fobs can be used to signal duress by the housekeeping staff.

Debunking The Myths Of EBT Cameras In A COVID-19 World
Debunking The Myths Of EBT Cameras In A COVID-19 World

The new buzz in the thermal imaging world goes by many names. In a short time, a small niche in the world of IR, which was previously sidelined to make way for more lucrative markets such as security and defence, has taken the top spot in the attention, production and sales for many manufacturers and integrators.  It’s no surprise considering the size of this new market. Suddenly, hotels, cinemas, malls, hospitals, critical services, public transportation, office buildings and more have become consumers of thermal imaging cameras. Along with that, the more traditional markets, such as security, defense and industry are suffering from budget cuts, project cancellations, or postponements. Combine two of these elements, and the new elevated body temperature (EBT) camera market is easily 3-4 times the size of the other markets combined. Thermal imaging cameras and common misconceptions Can thermal cameras detect viruses?  The answer is NO. The best the camera can do is tell you if someone has a higher skin temperature than others. There are many reasons for an elevated body temperature which are not all health-related, such as exercise or even sitting in a warm environment without air-conditioning. Are the cameras accurate? The accuracy debate is a significant and controversial discussion with much misinformation running around. When discussing accuracy, there are two considerations: The first consideration is the accuracy of the camera itself versus a blackbody. Blackbodies are devices which can regulate temperature very accurately (although not all are equal) and have a high emissivity level, which means they are almost not affected by surrounding heat or energy. All thermal cameras are calibrated against blackbodies. Still, some manufacturers have been using them in their EBT solutions to give the camera a consistent temperature reference to which it can adjust. The accuracy of the camera in this discussion talks about the camera itself. How sensitive the detector is, internal reflections, lens aperture, noise level and the calibration process itself. Also, if you read the fine print, most manufacturers quote accuracy levels which are valid only in a controlled or laboratory environment. As in, a room with a steady 25°C and a slow shift in temperature (not more than 1°C per hour). Most field conditions don’t allow this – so this low level of accuracy is challenging to replicate in practice.Blackbodies are devices which can regulate temperature very accurately The other focuses on the fact we are not looking for COVID in black bodies. We are looking for it in humans. And, the substance known as human skin acts very differently. To date, there are no medical models which can predict how skin will behave in different scenarios. We don’t know what the external skin temperature of a man weighing X who was exposed for X minutes to direct or indirect sunlight would be. So, while the black body may be spot on – it has no bearing on the temperature reading of humans.  So, while we can improve the first issue, the second one is more complicated. One way to circumvent it is by using population statistical analysis and looking for the gradient between the healthy population (which does have existing medical models) to the people with a higher temperature which are statistical anomalies for such a camera. Thermal cameras and their suitability  Are all thermal cameras suitable for temperature readings? There is a difference between a thermal camera and a thermometric camera. A thermal camera developed for security and defence are used to detect threats and give situational awareness. We don’t care that two trees with different temperatures will have different colors – we care about the person standing between them. We manipulate the image, so the viewer has a better understanding of what he sees. With thermometric measurement (as in – thermal temperature reading) we do the exact opposite. We want accurate temperatures readings for each pixel in our screen. A thermometric camera will go through a rigorous calibration together with the lens, which often takes longer. We need to offset, in the calibration tables, minute pixel-sized blemishes in the detector and lens. Those blemishes would be invisible in a thermal image – but can skew the temperature reading and produce inaccurate results. We regularly see suppliers who are using regular thermal cameras with blackbodies to auto adjust the temperature reading as described above. But, if you take that same blackbody and move it a meter to one side, you may discover the camera suddenly registers a different temperature – as not all pixels have a uniform calibration. Does it matter where we scan in humans? Yes and no. The inner canthus of the eye (the tear duct) is the most relevant external point with the best correlation to internal temperature. People looking at the inner canthus will manage to avoid a lot of the effects of ambient temperature on the skin. The tradeoff is that the inner canthus is a tiny area, and people would need to remove their glasses. Most of the world’s health organisations consider the difference between a healthy and sick individual to be 1.5° C (or 2.7° F). That change is consistent whether you’re looking at the tear duct, the forehead or a mouth. Thus, the solutions that look at the gradient temperature (population-based solutions) are just as effective when measuring the ambient temperature on the skin of the population tested.  Do people need to stop in front of the camera? Not necessarily. It depends on the speed of the camera and the temperature detection algorithm. Some cameras can detect people walking very quickly as they only need a few frames to detect the temperature. Will the camera work outdoors? Most outdoor cameras will suffer from false alarms and misses. Some cameras have very advanced compensation algorithms for this, but they can’t take into account all the dynamic temperature changes, humidity, sporadic energy readings and the “bane of thermal imaging” - turbulence. Therefore, the conditions can strain even the most advanced algorithm.  Why invest in this technology? The WHO states, that while asymptomatic transmission exists, it’s much less contagious then symptomatic transmission. Some doctors claim that a person with a fever sheds the virus five times more aggressively than a person with no fever.  There are clear regulations for businesses to screen individuals for fever In some countries, there are clear regulations for businesses to screen individuals for fever as they come into the establishment. While you can have a person in the entrance with a contactless thermometer, they must stop people for a 5-second check each time they come in. That would cause long lines in many places with high traffic. And, during testing, standing less than 2 meters from the individual would throw social distancing out the window. If the tester got sick, the next day they would start endangering everyone else they checked. It’s better to screen automatically and only use the IR thermometer in cases where an alert was triggered and needed to be verified. Various forms of technology  We’ve also seen much use of the IR tablets recently. While they are low cost, a person usually needs to stand very close (less than 1 meter) from the monitor to be caught by the camera. Thus, spreading his germs on the glass or plastic cover of the tablet while being screened.  In conclusion – Thermal EBT cameras are important. They aren’t a miracle cure, and they won’t stop the spread of the virus. And one should be careful of false promises. But along with other solutions (most importantly – masks), they can help protect us during these times and allow the wounded global economy to rejuvenate itself.

Beyond Video Analytics, What Are the Benefits of AI and Machine Learning?
Beyond Video Analytics, What Are the Benefits of AI and Machine Learning?

Artificial intelligence (AI) and machine learning have made a big splash in the physical security market, transforming video analytics to a new level of accuracy. In fact, the terms have become common buzzwords throughout the industry. However, the potential for AI and machine learning to impact the physical security industry goes far beyond their ability to improve video analytics. We asked this week’s Expert Panel Roundtable: Beyond better video analytics, how can artificial intelligence (AI) and/or machine learning benefit the physical security market?