Face Recognition: Privacy Concerns and Social Benefits

News reports and opinion columns about face recognition are appearing everyday. To some of us, the term sounds overly intrusive, it even makes people shrink back into their seats or shake their head anticipating immoral abuse of power. “I don’t want people to be able to recognize my face wherever I go”, some of us think. Yet to others, face recognition presents technology-enabled realistic opportunities to fight, and win, the battle against crime. What are the facts about face recognition? Should it actually raise privacy concerns? Should it be banned? Let’s take an in-depth look together at this technology.

What is Face Recognition?

Face recognition technology today is (usually) an AI-based video analytics function that compares and matches features in video images with specific, pre-registered faces to be recognized. The user can save images of specific faces in the system, and the system will send the user a notification if and only if the same faces are detected in a camera’s field of view. The keyword here is “detected”, as even the most advanced AI face recognition technology has stringent requirements on what can and cannot be detected, depending on the camera angle, resolution, lighting condition, etc. Hence, the perception that this technology can recognize any person, anywhere, at any time, is a myth. Biometric technologies such as fingerprinting, retinal scan, DNA, and voice recognition are ubiquitous tools in modern history to improve the authentication process with less friction for the user and a reasonable level of confidence. Face recognition is a relatively new but commonly applied biometric technology (only less common than fingerprinting (CSO), which measures and maps facial features from image and video sources to databases. There are several algorithms in advanced AI-based face recognition to detect a face, including:

– Traditional: This is the most common algorithm with this feature. It consists of matching certain facial features, such as the positioning of one’s nose or the space between your forehead and eyebrows. However, this form of face recognition only measures in 2D space, so different face movements and positioning will impair the system’s ability to recognize a face (WGU).

– 3D Recognition: While the traditional algorithm collects data on mainly the positioning and alignment of certain facial features in 2D space, the 3D algorithm collects data regarding the overall shape and structure of a person’s face in 3D space using 3D sensors. Thus, these sensors are able to retrieve a 3D scan of a person’s face, which allows for a change in positioning, lighting, or movement (WGU).

– Skin-texture analysis: Perhaps the most intriguing of them all, this type of face recognition analyzes patches of a person’s skin, then turns the lines and patterns into mathematical values (WGU).

The more advanced AI-based face recognition algorithms use deep learning technology, which essentially allows the software to learn and train itself upon more usage to better detect and match faces in the future, similar to how a baby may learn to recognize the friends and families surrounding her crib. Face recognition is thus a fitting testament to how far deep learning technology has come.

What Is Face Recognition Used For?

In 2017, the market for face recognition software sat at around $4 billion, which is no small number. By 2022, it is predicted that the market for this technology will be up to a staggering $7.7 billion (Norton). For comparison, the market for intrusion detection systems is at $4 billion and is expected to reach $7.1 billion by 2024 (MarketsAndMarkets). Intrusion detection systems are regarded as one of the most utilized AI security software features. So, not only is the face recognition market at the same amount today, but it is growing at a much quicker rate than intrusion detection. Many different industries have found great use for face recognition, such as:

– Schools: Many school campuses want to use this technology to help protect students. With all of the tragic violence that has occurred on school grounds in the last decade, administrators have been using face recognition technology to identify suspicious or dangerous individuals who have been uploaded to their database (Norton).

– Stores: Similar to schools, retail stores are using this technology to identify previous shoplifters to prevent future incidents. Some stores have also found use from this feature with employee recognition to access certain, restricted areas (The Guardian).

– Airports: If there is one place that has been cracking down on security these past two decades, it is airports, and for good reason at that. Face recognition seems to be the latest and greatest tool for airport security in detecting terrorists and/or other dangerous individuals from boarding planes (The Wall Street Journal).

– Law Enforcement: People who have likely gained the most from face recognition software are law enforcement workers. Making it easier to detect and locate criminals, face recognition software has been deployed in countless law enforcement agencies around the world (Norton).


With the increased FR applications, people’s concerns over the technology continuously appear throughout news channels and social media. Some of the concerns include:

– Privacy: As mentioned in the beginning, this is the biggest concern by far. Alex Perry of Mashable sums up his and most other people’s privacy concerns with face recognition technology when he wrote, “The first and most obvious reason why people are unhappy about facial recognition is that it’s unpleasant by nature. Increasing government surveillance has been a hot-button issue for many, many years, and tech like Amazon’s Rekognition software is only making the dystopian future feel even more real”.

– Accuracy: People are worried about the possibilities of inaccurate face detection, which could result in wrongful identification or criminalization. An article published by BBC News states, “But biases in the algorithms have led to misidentification. Those accused of crimes because of facial recognition software are often not told the technology has been used”.

– Awareness: Face recognition software allows the user to upload a picture of anyone, regardless of whether that person knows of it. An article posted on The Conversation states, “There is a lack of detailed and specific information as to how facial recognition is actually used. This means that we are not given the opportunity to consent to the recording, analysing and storing of our images in databases. By denying us the opportunity to consent, we are denied choice and control over the use of our own images” (The Conversation).

Concerns: Debunked

The concerns with privacy, accuracy, and awareness are all legitimate and valid concerns. However, let us look at the facts and examine the reasons why face recognition, like any other technology, can be responsibly used:

– Privacy concerns: Unlike the fictional dystopian future where every action, even in one’s own home, is monitored by a centralized authority, the reality is that face recognition technology only helps the security guard monitoring public locations where security cameras are installed. There is fundamentally no difference between a human security guard at the door and an AI-based software in terms of recognizing people on watchlist and not recognizing those who are not. The only difference is that the AI-based face recognition software can do so at a higher speed and without fatigue. Face recognition software only recognizes faces that the user has put in the system, which is not every person on the planet.

– Accuracy concerns: It is true that first-generation face recognition systems have a large margin for error according to studies in 2014 (NIST). However, as of 2020, the best face recognition systems are now around 99.8% accurate (Intelligencer). New AI models are continuously being trained with larger, more relevant, more diverse and less biased datasets. The error margin found in face recognition software today is comparable to that of a person, and it will continue to decrease as we better understand the limitations, train increasingly better AI and deploy AI in more suitable settings.

– Awareness concerns: While not entirely comforting, the fact is that we are often being watched one way or another on a security camera. Informa showed that in 2014, 245 million cameras were active worldwide, this number jumped to 656 million in 2018 and is projected to nearly double in 2021 (The Verge). The purpose is to ensure the safety and security of people and properties in public. Security camera systems, like security guards, are local business and government’s precaution measures to minimize incidents such as shoplifting, car thefts, vandalism and violence. In other words, visitors to locations with security systems have tacitly agreed to the monitoring in exchange for using the service provided by those locations in safety, and visitors are indeed aware of the existence of security cameras. Face recognition software is only another layer of security, and anyone who is not a security threat, e.g., an employee, is unlikely to be registered in the system without explicit consent via the same procedure to obtain a badge or a membership card.

It may sound odd to hear that technology is “on your side”, but it is. Face recognition technology, like all technologies, was created as a tool to help people, not to hurt. Our society today has witnessed numerous benefits from this technology even in its early stage.


– Security/safety: Ranging from identifying criminals to not allowing unauthorized access into a high-risk zone, face recognition’s security capabilities are endless. In addition, face recognition can be paired with other AI functions, such as intrusion detection, gun detection, etc., to maximize the safety of any institution. In August 2019, the NYPD used face recognition software to catch a rapist within 24 hours after the incident occured (New York Post). In April 2019, the Sichuan Provincial Public Security Department in China, found an 13 year old girl using face recognition technology. The girl had gone missing in 2009, persuading many people that she would never be found again (The Telegraph). In the UK, the face recognition system helps Welsh police forces with the detection and prevention of crime. “For police it can help facilitate the identification process and it can reduce it to minutes and seconds,” says Alexeis Garcia-Perez, a researcher on cyber security management at Coventry University. “They can identify someone in a short amount of time and in doing that they can minimise false arrests and other issues that the public will not see in a very positive way.” (Wired). In fact, nearly 60% of Americans polled in 2019 accept the use of face recognition by law enforcement (Statista) to enhance public safety. Forbes magazine writes, “when people know they are being watched, they are less likely to commit crimes so the possibility of facial recognition technology being used could deter crime”.

– Save time: One thing that all AI functions have been proven to achieve better results than manual security is speed. NBC News writes, “Nearly instantaneously, the program gives a list of potential matches loaded with information that can help him confirm the identity of the people he’s stopped ─ and whether they have any outstanding warrants. Previously, he’d have to let the person go or bring them in to be fingerprinted”. With AI, instead of spending hours or days to sift through terabytes of video data , the security staff can locate a suspect within seconds. This time-saving benefit is essential to the overall security of any institution, for in most security threat situations, time is of the utmost importance (Dash Bouquet). Another way in which the technology saves time is its ability to enable employees (but not visitors) to open doors to their office in real time with no badge, alleviating the bottleneck of forgotten badge, keycode or password. It has been reported that IT departments spend over 35% of their time fixing software issues, such as password resets. (Teem). Physicians and patients can save time during check-in and treatment for the patient who opts into the program.

– Save money: A truly high-performance AI software helps save money in many ways. First, if the face recognition software works with your preexisting camera system, there is no need to replace cameras, hence saving cost on infrastructure. Second, AI alleviates much of the required manual security monitoring 24/7, as the technology will detect people of interest and automatically and timely alert the authorities (Dash Bouquet). Third, by enhancing access authentication, employees save time and can maximize productivity in more important processes (Event). A less common application for business owners is to track when an employee comes in to work and when they exit, which prevents lies about work hours (AMG). Insurance companies, financial institutions and their customers can also prevent fraud and the lengthy verification/fraud dispute process if the customers choose to be automatically identified based on their facial features.

– Personalize the experience: Your phone today can recognize your face and unlock only for you. Patrons who opt into FR-based loyalty programs can skip the line and avoid giving out their phone numbers, hence avoiding spam calls. Gym members and boutique customers can also receive customized programs or packages according to their preferences (Retail Touch Points). The possibilities to streamline and enhance the customer experience are endless.


AI-enabled face recognition technology has a lot of benefits if used correctly. Can it be abused? Yes, like all tools that mankind has made from antiquity. Should it be deployed? The evidence indicates that the many benefits of this complex feature outweigh the small chance for abuse of power. It is not only a step in the right direction for the security industry but also for the overall impact on daily lives. It helps to make the world a safer place. Instead of focusing on what could go wrong, let’s ensure that it goes right.

Artificial Intelligence (AI) in Video Security

The number of surveillance cameras are snowballing around the world. The sheer growth of cameras and the security market poses a glaring problem for legacy surveillance systems that cannot keep up with the mounting influx of data. From a Mordor Intelligence report, with a CAGR of 10.35%, the global surveillance system market is expected to reach $86.06 billion by 2024 from $47.40 billion in 2018. In the IP security camera market alone, it is expected to grow to $20 billion by 2025 from $8 billion in 2018 according to a study by Global Market Insights. The commercial sector will likely hold the largest market share as demand for video surveillance grows in industries such as in banking, retail, and entertainment.

In order to keep up with the enormous amount of video data being accumulated, surveillance systems need to greatly augment their storing and analytics capabilities. Legacy systems are struggling to efficiently process and make use of all this data. Human monitoring costs also increase, and the margin for error or missing important events similarly grows. The only feasible solution to solve this ever surging amount of video data is AI.

Artificial Intelligence has the efficient processing and learning capabilities necessary to deal with the amassing stores of video data collected and streamed to surveillance systems. AI is the future of surveillance and will soon be the only viable system capable of keeping pace with increasing video data.

Besides the basic functions of alerting and pinpointing security threats and events, AI can utilize data to its fullest. In the retail sector, AI video surveillance can track the movements of employees, customers, and goods to not only prevent shoplifting but to gain business insights about consumer traffic, habits, and preferences within a specific location, store, or entire shopping mall.

AI is flexible, accurate, and efficient with the ability to improve itself the more it is used. The deployment of AI-based systems continually expands to all levels and areas of various industries. The possible applications are endless as it can identify different species of animals, all types of vehicles and objects, and human behavior in different environments and conditions with near perfect or perfect accuracy. The deep learning and neural networks of AI systems enable them to solve the long-held complaint against traditional rule-based analytics that couldn’t distinguish between objects and behaviors that humans could easily classify. As computing power continues to increase, neural networks will be able to process more data with greater accuracy.

Compared to human monitoring and legacy motion-detection-based system, AI doesn’t get tired, has consistently high accuracy, and is therefore more cost-efficient in the long term. Another added value of AI is easy integration. Because it is based on deep learning and fully automated, it is easy to set up. Some AI systems like IronYun’s AI NVR can also integrate with other NVRs and surveillance systems like Milestone to create the most complete security with the most ease and breadth and the least amount of installation effort and cost.

Physical access control systems have benefitted the most from AI. Quick reaction times paired with automatic adjustment of permissions and identification make AI-based solutions leaps and bounds ahead of non-AI-based systems in perimeter defense, and entrance and access control. The reduction in recognition and response times allow a wider margin of safety to extinguish threats before they escalate and result in loss of property and life. This ability to identify anomalous events, insider threats, and hazardous situations is a major breakthrough for the physical security world.

Hence, to properly manage and prepare for the upsurge of video data while gaining valuable business insights, switching to AI-based systems is imperative as the only long-term, highly effective security solution.

AI is the future of video security.


How AI NVR Can Help Create a Smart City

IronYun’s pre-trained and multimodal AI NVR is the security industry’s first all-in-one deep-learning-based video search Network Video Recorder (NVR). All AI NVR appliances have built-in artificial intelligence (AI) software and hardware with video search capability for fast, efficient search of video objects from video inputs including live streaming and video files stored in NVR/DVR devices. These cost-effective and high-performance appliances support all ONVIF IP-based cameras, real-time notification/alerts, live streams and forensic analytics.

The many functions that make up this all-in-one solution include:

  • Face Recognition
  • License Plate Recognition
  • Intrusion Detection
  • People/Vehicle Counting
  • Abnormal-Activity Detection
  • Fire Detection
  • Gun Detection

The grouping of these functions into one single appliance saves time, money, and provides perpetual convenience in building a unified Smart City.


The many functions of AI NVR can be used across several settings in a city. But, the first step most people consider when constructing a Smart City is protecting one’s schools. Our smart-security solution has been deployed in various school campuses across the US, including colleges and K-12 school districts.

Schools have globally been implementing our security platform to increase on-campus safety and comfort. Both Gun and Fire Detection are important features used in schools that prevent catastrophic events from transpiring. Additionally, Face Recognition is commonly being used in this setting to detect and notify campus security of watchlisted or unauthorized individuals. It has also been implemented in access control scenarios on campuses, effectively allowing certain people in particular areas, such as faculty only regions, by sending trigger actions to open doors and/or gates. The same can be said for License Plate Recognition in its use for high-quality access control. Similarly, Intrusion Detection has been utilized to alert authorities and campus security of instances of trespassing in specific custom regions of interest. Other features, which have shown great value in school safety, are falling, illegal parking, and loitering detection, all of which are provided in the Abnormal-Activity Detection function.

Healthcare Facilities:

Another setting, similar to that of schools in terms of being a top security priority, are health care facilities. Examples of places that may benefit from certain functions include but are not limited to: hospitals, urgent care facilities, nursing homes, and private practices. Many of these facilities can benefit from the many functions provided in AI NVR.

Particular functions that will assist management in healthcare facilities include:

  • Fire Detection: an utmost importance in healthcare facilities, particularly hospitals, to prevent damage by detecting smoke/fire in areas such as the generator room of a hospital.
  • Face Search: allows for authorized personnel to locate patients/elders who have wondered out of their rooms or away from designated area.
  • Face Recognition: used for access control, specifically allowing healthcare staff in certain regions within a facility.
  • AI Counting: detect patients falling down to give help in real-time as well as regulate the number of visitors in patient’s rooms.

These advanced functions help secure and maximize productivity within healthcare facilities to help prioritize patients’ needs.

Traffic Management: 

The next step in building a Smart City with AI NVR is using it to manage traffic. As of October of 2019, the world’s population is approaching 7.8 billion people, 55% of which are living in a city or urban region. By the year 2050, this number is expected to rise to a remarkable 68% (CNBC). Consequently, cities have and will become more congested than ever. Traffic is taking the largest hit from these highly dense areas, as there are simply too many cars and pedestrians to manage. AI NVR’s Vehicle Counting function determines the peak hours and analyzes traffic flow to implement smart traffic control. Furthermore, the self-learning system detects vehicles that move in the wrong direction as well as illegal parking scenarios through its AI Counting and Intrusion functions, undoubtedly decongesting city vehicle traffic due to accidents and/or vehicle-towing.



Forensic Investigation:

While improved traffic management will help alleviate traffic issues, the possibility of crimes will always be present, particularly in populated areas suchas a city. To assist the police officers in forensic investigation and overall city security monitoring, AI NVR can provide many useful tools.

  • Video Search: can help speed up the investigation process by allowing the police to search for any abnormal events (accidents), lost children, elders, or pets, as well as stolen or missing items in less than one second.
  • Face and License Plate Recognition: can detect the faces of suspects and criminals as well as locate suspicious vehicles respectively.

Through these functions, the police can also pinpoint where certain vehicles or persons are detected and track them across several cameras with a map view. In terms of preventative action, Intrusion Detection can help set virtual fences to protect any particular areas of interest. Evidently, the No. 1 goal of a Smart City powered by AI NVR is to assist the police in their effective protection of all cities.

Retail Stores:

To make the police’s job easier,  facilities like retail stores, for example, can implement the software to prevent crime. Aside from security, however, it can also be used to help make stores more efficient. For example, Face Recognition can help configure VIP customer’s product preference based on smart analysis. Additionally, AI Counting provides statistics of peak hours of service, customer flow at certain regions within the store, and keep track of occupancy as well as providing real-time alerts for person slip-and-fall accidents.






Check out the video below for a visual representation of how AI NVR can create a Smart City!!

AI NVR has been deployed in many different countries because of its versatility and efficiency. IronYun’s headquarter office is located at 263 Tresser Blvd., Stamford, CT. Feel free to contact us via email at sales@ironyun.com and on the phone at 1-203-273-7089.
We have many support teams and partners globally to assist you with any questions or concerns.
Our products and services are developed with your security in mind, because a Smart City is a more secure city.

What is Artificial Intelligence (AI)?

Technologies that employ artificial intelligence are all around us in our daily lives. AI is not just what’s seen in science fiction movies or lauded by tech giants claiming to be stepping closer to that of human intelligence. From Apple’s Siri and Amazon’s Alexa, to IBM’s Watson and supercomputers, to simply the personal computers prevalent in everyday life, they are all examples of artificial intelligence.

On a fundamental level, AI systems generally demonstrate at least one of the following characteristics of human intelligence: knowledge, perception, motion, manipulation, planning, learning, reasoning, and problem solving.

AI can be further split into two categories: narrow and general AI. The latter is adaptable intellect as found in humans (AGI), a step away from the “superintelligence” found in the likes of science fiction where robots are taking over the world. One of the classic, modern examples of AGI is IBM’s Watson beating human contestants on the trivia game show, Jeopardy.

This branch of AI will take several more decades to fully accomplish and even more to reach a level where it becomes more mainstream. According to ZD Net, the likelihood of so-called “superintelligence” occurring will increase to 90% by 2075. By then, Siri and Alexa will have upgraded to true, fully functional personal assistants. Whether AI will get to the point of Stephen Hawking’s “singularity” is a whole other discussion.

Currently, Siri and Alexa fall into the category of narrow AI as they only recognize speech and language and search information based on those perceived words. Narrow AI are the computers around us which carry out specific tasks without being explicitly programmed to do so. These systems can only learn or be taught to do certain tasks while general AI is being able to learn vastly different tasks or reason based on experience. The scope of actions performed by AGI is unlimited while narrow AI is limited to its code and algorithms. It cannot perform other types of tasks outside of the ones it’s been programmed to do.

Within AI are Neural Networks, Machine Learning, and Deep Learning. AI roughly developed in this order over the decades. Neural Networks are the structures of how basic AI works. They networks of interconnected layers of algorithm inspired by the human brain. Aptly called neurons, these networks feed data into one another at different inputs until the output is close to what is desired. At this point, the system has “learned” the particular task.

Machine Learning is a subset of Deep Learning where neural networks are further expanded into much larger and numerous interconnected networks and layers. The AI is trained using massive amounts of data to learn particular tasks. For instance, an AI is given thousands of photos in order to recognize a human face. The AI infers what it is being given, and validation is done afterwards to test its learning. Machine Learning can be either supervised, where data is annotated for features of interest, or unsupervised where algorithms attempt to identify patterns in data that can be used to categorize future data. Many data analytics tools use this process called classification.

Today’s AIs are in the stage of deep learning, and its evolution and resurgence into the limelight is fueled by the easy availability of large amounts of data and parallel computing. Artificial intelligence automates repetitive learning and discovery. Besides being potential sources of human assistance such as through the development of self-driving cars, AI allows businesses to gain insights from big data generated everyday with more accuracy, speed, and depth.

AI is the only feasible and cost-efficient method of managing and analyzing data as technologies generate greater and greater quantities of data from all sorts of sources and devices. Soon, Artificial Intelligence will no longer be on the backburner of everyday people’s minds. It’ll be at the forefront, paving the way for more streamlined businesses and comfortable lives.


IronYun AI NVR Video Analytics is now available on NVIDIA GPU Cloud (NGC)

October 21, 2019 – IronYun is excited to officially launch our AI NVR Video Analytics container on Nvidia GPU Cloud (NGC). The user can now install and start an AI NVR docker on a Kubernetes-ready machine (e.g., Google Cloud) with one command.

Image modified from original on Nvidia webpage.

By making AI NVR Video Analytics available on NGC, IronYun and NVIDIA deliver together an intelligent, real-time AI service to help keep business agile and improve the efficiency and safety of structures in smart cities. IronYun real-time, automated intelligence for schools, police departments, stores, hospitals, factory floors, even city streets. Then, NGC EGX, as a cloud-native, scalable, and accelerated platform, securely deploys and manages the AI workloads, wherever they’re needed, at the edge or in the data center. It is optimized to run container-based applications on the Kubernetes infrastructure with rapid installation via Helm charts. With NVIDIA NGC’s state-of-the-art Helm integration and NVIDIA’s new NGC-Ready for Edge server certification, EGX can accelerate even the most demanding AI workloads to the edge with ease.

Link to obtain IronYun AI NVR container from NGC (Free 30-day Trial):

For license and other information, please email us at sales@ironyun.com or contact your regional IronYun representative.


IronYun is No. 2 Most Fundable Company of 2019!


On Thursday October 17, IronYun was announced as the Second Most Fundable US Company by Graziadio Business School of Pepperdine University, Los Angeles, California. Taking into account the credentials of over 3,500 early-stage U.S. companies spanning 46 states, the Graziadio School ranked the 15 Most Fundable Companies, all of which have strong business plans and impressive near-term growth projections – see Business Wire report on the event.

The annual Most Fundable Companies initiative is designed to bridge the gap between startups and the capital they need to succeed. The initiative evaluates several company variables including financial projections, market opportunity, intellectual property, and the strength of the management team, all of which are used to produce a fundability score for every company that participates. The evaluation and selection were done by the Pepperdine Private Capital Markets Project in partnership with The Venture Alliance (TVA). For 2019’s list, the honorees are located across the country and come from a variety of industries, including medical devices, software services, and agriculture technology. Among the top 15, IronYun is the only company in the physical security industry.

The selection process was extensive and thorough. Based on every survey submission, all participating companies were provided with objective and customized feedback to improve their readiness for funding. Approximately 100 companies were selected for the semi-finals and completed a more in-depth fundability assessment to further refine and verify their score. During the final stages, high potential companies were invited for an interview with the selection team, and the winners were announced. Making it to the top 0.05% of more than 3500 companies across the United States marks the achievement of IronYun’s teams in developing and bringing to market products with real potential for the full spectrum of the industry decision-makers, from investors to end-users.

IronYun’s main product line today covers multiple aspects of security, from real-time alerts for people and object detection to quickly obtaining results in forensic investigation.
For more information about IronYun’s solutions, please email us directly at sales@ironyun.com or contact your local IronYun representatives.

How AI NVR Can Prevent Mass Shootings:

Tragedy struck West Texas early Sunday afternoon when a disturbed shooter left seven dead and 22 wounded after firing freely down several streets in Odessa (CNN). Regardless of one’s political views on gun possession in the U.S, all are in agreement that these mass shootings must come to an end. We, collectively as a population, have suffered enough from these dreadful acts of violence, as yet another town falls victim to catastrophe. Not only do the mass quantities of these shootings signify both gun violence and mental health problems, but they also show a larger problem at hand, which is the lack of gun detecting security systems in the United States of America. While gun violence may never fully cease to exist, there are ways to drastically reduce the damage of these devastating instances.

AI NVR’s Weapon Detection engine is the solution to this gun violence predicament that our country is currently facing. This model of the immensely accurate system can detect and alert authorities of any handguns and/or rifles in real-time for immediate action. By utilizing multiple cameras across several different locations, this model can efficiently track any weapons within the field of view, and tracking guns concurrently tracks the potential active shooters, which warns authorities prior to an eventual calamity.

Additionally, AI NVR’s Face Recognition can identify dangerous individuals with criminal background or in publicly available wanted lists. In any event similar to the one in question, this highly accurate face recognition software could have potentially helped, for the now deceased shooter had a criminal record. This function detects, matches the face to one previously uploaded into the database, and sends an alert in real time to the security authorities, all within 3 seconds. If the gunman moves across many locations, such as different school campuses or stores, the Map View and Face Recognition functions will allow one to track his movement across all cameras that spotted him and predict his next target location.

Gun violence is one of the most important issues in need of fixing in America today and for good reason. Artificial-Intelligence-powered security software with Deep Learning is beneficial for its highly accurate results and tremendously fast real-time alerts, unrivaled by manpowered or other comparatively primitive security systems. AI NVR is not only today’s answer to gun violence, but the future of gun security.

IronYun AI Won Best in Video Surveillance Data Storage!

ISC West New Product Showcase 2019

ProActive AI powered by IronYun was selected as the winner of New Product Showcase at ISC West 2019 in Best Video Surveillance Storage Solution!

IronYun teamed up with our partner Proactive this year at ISC West security show to display our new products and developments, designed with the most complete accessibility for end users in mind. We thank you for your support and look forward to new collaborations with you!

Learn more about our AI Solutions !

Web Article


How AI NVR Can Identify Potentially Dangerous Objects in Train Stations

On August 16, 2019, two rice cookers were reported as suspicious objects in a subway station in Lower Manhattan and near a garbage can in Chelsea, New York City (NY Post). All were eventually deemed safe and non-explosive, but surely caused an unnerving sense of panic for the NY police, street pedestrians, and subway passengers. Witnesses, such as the ones who reported the suspicious activity, are encouraged to continue to relay such information to prevent catastrophes. With that said, for maximal public safety without delays and inconveniences, what can be done to make the investigations even more efficient?

First, AI NVR’s Face Recognition can identify a dangerous criminal/terrorist in publicly available wanted lists. By simply uploading images of suspicious individuals to the database, AI NVR will then alert the security authorities if that person appears on premise. In this scenario, if a suspicious individual indeed left a potentially dangerous object at the subway station, he or she could have potentially been identified in real time to prevent the anticipated disaster. Face Recognition can also be used after the fact. For instance, after the person who placed the rice cooker in that location left the scene, the police can upload their image, search for any sightings on other cameras to track and determine whether they proceed to act in a suspicious manner. One may even track a suspect back to his or her car, the vehicle can then be identified on cameras based on its color and possibly license plate number. The vehicle itself can then be tracked across all traffic intersections in the city using the AI License Plate Recognition function.

Video Search is another of several tools in AI NVR to help speed up the investigation in situations like these. This feature allows people to search for and be alerted of objects of interest, such as a backpack, handbag or suitcase in which the cooker (or weapon) was transported. Without manually viewing hours of videos, the security staff can easily search for the object dropped off at that camera, identify when and by whom it was dropped off, and track the person using such criteria as “person wearing blue with a black backpack” across all cameras within, say, a 10-mile radius. This whole process can be accomplished in less than 5 minutes if not seconds with AI NVR.

While there is no way to fully eradicate false alarms and/or false claims, AI NVR allows for a drastic reduction and a much easier way of finding a suspect. AI NVR pin-points faces, plates, objects, vehicles, etc. so that you don’t have to. The time and energy saved, as well as the overall efficiency of AI NVR may be lifesaving in comparison to the manual labor and time that it would take to find the suspect of a particular scene without the technology.