Security Cover - Network Security Video Security

Top 5 Video Security & Network Security Tech Solutions Today

What comes to mind when you think about surveillance & security tech? Some companies still only rely on a guard looking at a video wall, strategically placed motion sensors, or badge ID cards for building/office access. Yet many organizations and enterprises are undergoing digital transformations to increase efficiency and upgrade these systems.

In this article we will offer our picks for the top five physical and network security tech solutions that organizations and enterprises are exploring these days.

1. Edge AI & Video Analytics – Video Security

Data Bridge Market Research shows us that the rising need and demand for edge computing programs and services will experience a CAGR of 20.15% with a rise of up to USD 2.7 billion through 2028. To refine that further to include video analytics into the edge AI equation, MarketsandMarkets Research show that video analytics on edge devices improves surveillance and monitoring by reducing the amount of raw data that needs to be transmitted over networks.

Processing facial recognition or other intelligent video analytics to identify things of interest and suspicious activities or behaviors on edge devices is a growing and valuable technology in the surveillance and security fields.

EXAMPLE: The IVAR™ edge AI platform from Gorilla Technology

CCTV - Video Security

2. OT Security Solutions – Network Security

OT Security is different from standard IT Security. (OT stands for Operational Technology while IT is Information Technology.) OT is a type of hardware and software used to monitor and control physical devices, processes, and infrastructure. OT Security is a common form of cybersecurity used to protect Industrial Systems and networks from various attacks. OT is used across multiple industries including manufacturing, power plants, transportation, utilities, and smart city appliances.

As outlined in a recent report from Market Research Future analysis, the global OT security market is forecast to see an increase to USD 3.5 billion at a CAGR of 42.2% through 2025. The driving forces behind the market growth include the integration of IT and OT systems, surge in the risk of cyber threats on critical infrastructure, and increasing dependence on legacy systems.

EXAMPLE: The NSGuard Series of OT Security Solutions from Gorilla

3. Access Control Systems – Video Security

COVID-19 has changed quite a bit in regards to access control systems and what they are expected to do. Edge AI video analytics are being implemented more in access control systems to accomplish things like employee ID verification via face recognition. From monitoring employee health conditions and meeting government mask/temperature regulations to ensuring visitors and employees can gain timed access with privileges to pre-assigned areas on to time-logging every area entry and exit, the desired tasks assigned to access control systems have expanded quite a bit. While its roots are in security, access control systems are now just as important for health and controlling the spread of deadly diseases.

Mordor Intelligence reports that the Access Control market is expected to reach USD 11.7 billion by 2026 and grow at a CAGR of 7.38% until then. The need to enhance the safety and security across various residential and commercial segments is significantly adding to the market growth globally. The advancements in edge AI computing mentioned above and the expanded use cases in this post-pandemic era have both contributed a great deal to the growing interest in access control systems.

EXAMPLE: Post-Pandemic Access Control & Area Management from Gorilla

Access Control - Video Security

4. IoT Sensors – Video Security

The global smart (IoT) sensor market size, according to Allied Market Research, is projected to reach $91.37 Billion by 2027 with a CAGR of 14.30%. IoT sensors enable better control and monitoring of different security operations. These sensors react to physical inputs that occur or change – like light, heat, motion, moisture, or pressure – by producing an output on a display or transmitting data further processing on edge devices or other designated machines with the help of signal conditioning, embedded algorithms, and digital interfaces.

These sensors are often used in the surveillance and security fields along with other technology – specifically enterprise security. The demand for combining video surveillance, edge AI video analytics, and IoT sensors to create comprehensive physical security systems with multiple false-positive checks is increasing rapidly – and so is using OT security solutions to ensure device and health and security.

EXAMPLE: Enterprise Security Solutions from Gorilla

IoT - Video Security

5. VMS Systems – Video Security

Kenneth Research reported to MarketWatch that the global Video Management Software (VMS) industry is anticipated to see a CAGR of more than 16.85% through to 2025. Factors pushing this projected industry growth include easier ways of deployment, the rising use of IP videos, third-party integration, and other digital business systems. Mainly due to COVID-19,  safety and security concerns have escalated nearly everywhere and further advancements in edge AI video analytic processing capability have led many VMS users to upgrade their systems to include some form of video analytics as well as OT security.

Control Room - Video Security

Observations in Video Security and Network Security Tech

CCTV cameras only sending video to hard drives, guards staring at video walls, ‘systems’ made up of only motion sensors, and unmanaged device/system health – these old days of security are over. As you read in the sections above, video analytics & edge AI, OT security, access control, and integrated IoT is the combined direction that the field is moving. So meet the future today and contact Gorilla about one or more of the ideas in this article.

AI Appliances in Smart Cities

Top Video Analytics AI Appliances for 2021

AI Appliances are computers that do one thing well – run specific AI software. Smaller devices with more processing power have come together with developments in edge computing to unlock the immense expansion of capabilities and uses these AI Appliances can now offer.

But what are the devices we think will have the greatest impact in the coming year? As recent reports project, the video analytics market is poised to see large growth and Gorilla is a driving force in that projection.

With that in mind and to keep this list more concise we decided to focus on AI Appliances that run video analytic software since AI running on AI Appliances will vary from project to project. (click on the titles or images below to learn more about each AI Appliance)

The LEC-2290 from Lanner is the latest generation of intelligent edge computing systems powered by the 8th generation Intel® Core™ i7 processor. Designed for deployment in diverse environments (-20°C to 45°C) and to meet the high Power POE requirements of network applications, the LEC-2290 brings the most secure, low-latency video AI applications, such as city surveillance, machine vision, and mobile surveillance.

The Behavior Analytics AI Appliance gives government, transportation, enterprise, and retail administrators a better way to monitor, manage, and make decisions on any scale. It has been implemented in many projects globally and excels at superior public safety, enterprise security, and retail analytics. With professional, standard, and custom models to choose from, this AI Appliance runs its preloaded video analytics on up to six video channels – all on Intel® CPUs and without GPU assistance. This is one in a series of AI Appliances from Gorilla aptly dubbed Vision AI. The hardware and software in each AI Appliance in the series is tested for compatibility and stability to give you the optimal combination of accuracy, performance, and efficiency. To go the extra mile, flexible hardware aftercare from service centers all over the world as well as first line tech support from Gorilla is included with each AI Appliance.

The Edge AI Video Analytics platform from Arrow and Gorilla includes a complete technology stack to develop intelligent video surveillance applications. The platform delivers real-time intelligent video analytics and business intelligence.

Core video analytics capabilities of the solution include people/face recognition, behavior analysis, vehicle detection/recognition, and real-time insights. Exception alerts based on key business or security parameters make the platform well suited for video surveillance applications in public safety, smart cities, and enterprise security and for enhancing customer experiences in retail. Moreover, these features provide a complete security convergence platform that safeguards both physical and network security.

Comprised of Gorilla’s edge-computing video analytics software, an AI Toolkit can be placed on hardware devices and boards with different form factors, shortening the time to market for end product manufacturers and solution developers.

More About AI Appliances

Many elements go into making a quality AI Appliance. From form factor, to environmental capability and on to processing power or type of AI being run, the market today is sure to provide the perfect AI Appliance for any setting or project.

You can find out more about AI Appliances and Gorilla Technology here: https://www.gorilla-technology.com/

We also recommend learning more about edge AI here: https://www.gorilla-technology.com/Edge-AI

A firm understanding of video analytics can be ascertained here: https://www.gorilla-technology.com/Video-Analytics

For a deeper dive, download Technical Whitepapers and Case Studies from Gorilla Technology here: https://www.gorilla-technology.com/Edge-AI/Whitepapers

First Aid Tent

New Disaster Shelters Use Edge AI to Manage Pandemics

As we all begin to live with the global aftermath of Covid-19, the challenge is in creating smarter and safer disaster shelters to alleviate the heavy loads put on hospitals when another infectious disease breaks out or when the next natural disaster occurs.

During any given season of the year, countries face the threat of natural disasters – typhoons, tornadoes, hurricanes, flooding, wildfires, earthquakes, and tsunamis.

Pain Points of Traditional Disaster Shelters

As Covid-19 has brought to light, creating and using impromptu shelters for disease control and prevention leaves much to be desired. Here are a few ways that traditional disaster shelters have failed in the wake of Covid-19 and taught us lessons about what we can improve upon:

  • Disaster shelters are typically set up in schools, gyms, public halls or community centers with little or no patient-to-patient or doctor-to-patient separation.
  • They require a large number of front-line staff to manage everything on the ground.
  • Due to the urgency in accommodating large numbers of victims in these places, these makeshift indoor spaces are often overcrowded and utilized as much as possible.

Due to the situations above, an unexpected and innumerable amount of group infections occurred when the first wave of Covid-19 hit. Because of that, however, we can learn how to improve on the idea of how a disaster shelter should be created.

New Disaster Shelter Criteria

In countries like Taiwan and Japan where natural disasters occur frequently, governments have come up with guidelines for new kinds of disaster shelters. For example, the Office of the Cabinet of Japan has formulated the following criteria for the creation of these new disaster shelters: 

  • Prepare more sites in advance for disaster shelters in order to reroute much of the affected population.
  • To avoid gathering in large crowds, it is recommended that affected people seek refuge at the homes of relatives or friends. 
  • All people entering the disaster shelter must be physically examined.
  • Disaster shelters should focus on maintaining good ventilation.
  • Disaster shelters must provide dedicated spaces for people with fevers or other symptoms, and provide a dedicated bathroom to people with abnormal health symptoms if possible.
Field Hospital

In the past and under normal conditions, the government advocated that these items be strictly followed. Yet these key guidelines are quite difficult to maintain in an emergency situation.

Edge AI Solutions in New Disaster Shelters

There are many governments and local authorities in countries that are paying attention to how AI technology can be used in shelters in areas at high risk for natural disasters. For example, using an access control system with contactless temperature detection combined with facial recognition technology can record body temperature and personal data when anyone enters the shelter. That data can then be linked to a specific face identity. Because the system is contactless, it can help avoid transmission between the front-line staff and the admitted person because the device replaces the front-line staff with technology.

Furthermore, physical methods have been used to block people from associating with one another. This is achieved by creating spaces separated by plastic or cardboard dividers. Video analytics can be used to confirm the number of people in each area is within limits. Using AI identification along with personnel management can work together to efficiently strengthen protocols and efficiency.

In addition, mask detection video analytics can be used to identify whether or not an entrant is actually wearing a mask. This cuts the common reliance on staff to check at entry and exit points, thus again reducing the need for front-line staff.

Loss or theft of relief supplies for disaster shelters is often a problem. It’s impossible to allocate people to monitor these materials 24/7. If there are non-staff wandering around the storage area, video analytics can alert the proper personnel and warn them to take necessary action.

Finally, in case an infected person does enter a shelter, focusing on contact tracing methods to effectively locate all the people they have interacted with to prevent further spread of the disease is important as well. Carrying out effective contact tracing, quarantines, and similar measures can benefit from technology and is being closely watched by governments and local administrations.

Covid-19 Alert

Transforming the Traditional with Edge AI

Covid-19 is a pandemic the likes of which the world has never seen and transforming traditional shelters into a more intelligent disaster refuge is an issue that all governments must address. Gorilla’s edge AI technology is leveraged in creating a variety of post-pandemic solutions that governments and countries can adopt. In the future, Gorilla Technology will continue to produce the most advanced video analytics and will continue to develop products that contribute to society.

Digital Transformation in Covid - cover photo

Digital Transformation in the Age of Covid-19

Only 16% of companies in the world highly depend on digital technologies to run their businesses, while the rest are hybrid-digital and non-digital models.[i] The COVID-19 pandemic has changed all that and has forced companies to finally embrace digital transformation.

Digital transformation is the process whereby businesses adopt new technologies and fundamentally change the way they deliver services to customers. Namely, digital transformation is how enterprises integrate digital technologies into business operations.

Because of the lockdown policies and work-from-home guidelines from Covid-19, many workforces have had to shift their operations to the digital world in order to maintain stability/profitability. This unprecedented and unpredictable crisis has shown the world just how important technologies are to modern businesses. Enterprises now have to rethink their digital transformation strategies and the pace with which to roll them out.

Woman wearing mask working from home

But the barriers for companies to rapidly overhaul their business environments are many. No clear strategies and budget shortfalls are the two biggest challenges most companies face. Yet many businesses are taking the leap since the pandemic leaves them no other options.

Levi’s is an example of a company that has successfully reduced losses by accelerating their digital transformation. They automated most of their logistical processes, deployed an omni-channel e-commerce and delivery system, and invested heavily in data and artificial intelligence, thereby keeping them afloat.  By strengthening their connection between digital technologies and operations has been beneficial for both customers and employees.

It’s not just retail—factories, hospitals and governments can also take an advantage of transforming digitally. To embrace a data-driven future, the following technologies are the key trends which we’re already seeing help people adapt to the new normal:

icon - video iot

Video IoT

• Video analytics helps to enhance the authentication systems (using facial recognition for touchless entry) • Additional functions are being released, such as mask & temperature detection or crowd density detection to follow Covid-19 regulations.

icon - cybersecurity

Cybersecurity

• As enterprises embrace digital transformation, their data needs to be saved and shared safely. Cybersecurity solutions help organizations to avoid hackers and to ensure the internal and external networks are well guarded.

icon - big data

Big Data

• By transforming unstructured data into structured information, big data optimizes and accelerates data analysis much better than before. Big data solutions can collate disparate information and allow organizations to make more informed decisions.

During this challenging time, companies should stay open to digital transformation. Not only the pandemic but also the development of Edge AI/computing are pushing companies to speed up their plan of digital transformation. Gorilla who has specialized in edge computing can really help organizations easily transition and make operations smoother in the long-run.

Click here to learn more about Gorilla’s post-pandemic solutions:  https://www.gorilla-technology.com/IVAR/Post-Pandemic-Area-Management

 

[i] Harvard Business review

https://hbr.org/resources/pdfs/comm/microsoft/Competingin2020.pdf

virus-5308335_1920

5 Ways Video Analytics Can Help Manage Covid-19

Since the pandemic began, wearing face masks and social distancing have been used as preventive guidelines for individuals, organizations, and governments to follow. Many governments have gone so far as to make those guidelines into mandates and laws.

Whether guidelines or laws, it’s still the responsibility of society to maintain these and make sure a second wave of the pandemic does not accelerate out of control. But how can organizations or governments monitor or even execute these rules with limited human resources and no smart methodologies on hand?

We recommend intelligent video analytics — AI technology interpreting IP video sources. Preventive measures like mask wearing and social distancing guidelines can be easily monitored as well as executed. Below are five examples of intelligent video analytics from Gorilla Technology and their use cases that can help you make a proactive difference in responding to the Covid-19 pandemic:

 

1. Facial Recognition

Employing no-touch access control reduces physical contact with devices and people, which can drastically reduce transmission of the virus.

 

2. Mask/No-Mask & Eyewear Facial Recognition

Mask guidelines and mandates are in effect to some degree all over the world and leveraging edge AI to assist in enforcing these regulations decreases required manpower and increases efficacy in areas where personal protective equipment is required.

 

3. Crowd Detection with Occupancy Analysis

As social distancing is part of the new normal, people counting and crowd detection can help keep transmission risks to a minimum.

 

4. Crowd Detection

Once offices reopen, management can ensure break rooms and other gathering spots remain safe and not overcrowded with edge AI zone capacity alerts.

 

5. Heatmap and People Counting

Good air quality in high foot traffic areas is important and heatmap & people counting analytics can empower HVAC systems to circulate air appropriately to keep infection risks low.

We firmly believe in and see the benefits of implementing intelligent video analytics that can adapt to many situations — it saves time, money, and makes it easier to quickly solve new and unforeseen challenges, like what we are experiencing now with Covid-19.

For more info about this topic, refer to our solutions on Post-Pandemic Area Management. Also, if you’d like a deeper dive on the technology or specific cases, our whitepapers offer more details.

DataCenter16x9

Post-Pandemic Situational Monitoring with Big Data

The period of lockdowns around the world is coming to an end. It is inevitable that business and operations need to reopen for economic survival. However, the possibility of new waves of the virus after re-opening is an issue that requires close monitoring.

Balancing Economic Activities and Epidemic Control

The answer to this problem is actively sought out by various government agencies. From gradual re-openings within borders, to the conditional re-openings at borders (such as travel bubbles), these policies and measures are already starting to be implemented in many areas.    

The most important supporting measure after a lockdown – apart from wearing masks, social distancing, and frequent hand-washing – should be epidemic surveillance. This means monitoring those in home quarantines and self-isolation. For example, once a confirmed case is discovered, the history of who they came in contact with needs to be determined in the shortest time possible. Once those potentially infected people are discovered, monitoring them and possibly enforcing home quarantine and self-isolation is a high priority.  

When monitoring is not automated, the staffing required will be massive and it may not be possible to execute quickly. A failure like this could cause a large-scale community-based spread of the virus that cannot be traced, which would then lead to the city needing to return to lockdowns yet again.

Considering automated monitoring, it can be applied via the deployment and use of post-pandemic area management solutions like big data analysis. From monitoring home quarantines and whether the monitoring device of a quarantined person strays from its designated location, to understanding the previous movements of a newly diagnosed person – automated big data analysis can be applied to identify possible connections quickly, accurately, and efficiently.

The monitoring devices used for quarantine and self-isolation are IoT devices that can report back to the big data platform at set times. Once an irregular report from the IoT device is recorded, the big data platform can immediately issue an alarm to notify personnel.

Understanding Contact History with Big Data

To accurately understand the contact history of a newly diagnosed person, data from multiple sources is required. For example, the logs from a telecommunication company’s cell tower, check-in/out times from locations using ID verification, CCTV recordings, credit card spending history, etc. would all be utilized in contact tracing. These data can ultimately be analyzed to find possible contacts with location/time crossovers.

For integrating heterogeneous data from multiple sources, Gorilla’s big data analysis platform provides real-time event notifications and space–time analysis functionality, making it an optimal solution for contact tracing.

Contact us to learn more about post-pandemic area management solutions like our big data platform. If you’d like to read more in-depth on the topic, please check out the whitepaper we recently published here: https://www.gorilla-technology.com/Edge-AI/whitepapers

architecture-buildings-business-city-325185

Post-Pandemic Workplace Wellness & Intelligent Building Automation Systems

The Pandemic

The world was caught unprepared for Covid-19 and its profound consequences on public health and the economy. In just the first six months following its discovery, the highly contagious virus was able to infect over ten million people globally, and has been responsible for at least half of a million deaths around the world in as much time.

Since the outbreak, the pursuit of workplace wellness has dramatically accelerated. Workplace wellness encompasses the physical health and safety of its employees, also how they can successfully perform their jobs and how they interact with one another.

Workforce Vulnerabilities

Most jobs (office, engineering, construction, government, etc..) can be broken down into daily tasks that have at least some element of human interaction – this may act as a channel for the virus to spread. Jobs that involve these tasks not only expose employees to risk of infection, they can also increase the spread of the virus by acting as a distribution network for it.

The challenge is in reformatting these jobs to keep our workforce healthy and productive. Checking temperatures at entrances, maintaining social distancing during working hours, assisting health professionals with contact tracing – these are just a few examples of what offices will need to do in order to reopen safely.

Enhancing Building Automated Systems with Edge AI

Edge AI driven video analytics from Gorilla provide reliable solutions to slow the spread of the virus. Integrating and deploying facial recognition access control, attendance systems, and smart parking solutions with current building automation systems to automatically monitor compliance in many ways are now possible. To name a few:

  1. Performing screening for fevers and masks at entrances and other key zones.
  2. Using crowd detection in cafeterias and break rooms to ensure proper social distancing is followed.
  3. Assisting health authorities with link analysis & contact tracing when positive cases come to light.

Post-Pandemic Area Management solutions from Gorilla can also help maintain public safety and order – something that will prove to be a challenge as lockdown measures result in closed businesses and greater economic hardship for many people.

Gorilla’s offerings of behavior analytics, intrusion detection, loitering detection, direction violation detection, fighting detection — these can all help minimize the prospect of looting, vandalism, robberies. Gorilla is reaching out to assist law enforcement in preserving public order during this trying time.

While the health crisis is far from over and the full impact of the virus and global lockdown is still to be seen, we know we will get through this. We will return to our workplaces as they are re-tooled into safer and smarter environments – and Gorilla will help get us there.

woman-holding-face-mask-3902883

A Tense Encounter at the Grocery Store

Any parent will understand that your kids are at home with you all day and every day. Every chore and every errand you have to run, your child is with you – there are no schools and no childcare available. This includes errands like grocery runs.

Last Wednesday morning, I geared up to go to the grocery store with my child. Masks? Check. Sanitizing wipes? Check. Hand sanitizer? Check. Snacks for cranky kiddo? Check. We got to the store and I noticed there wasn’t a security guard standing outside to ensure everyone abided by the ‘no face mask, no entry’ rule. I figured it would be ok because the store looked pretty empty – I had strategically chosen the morning to conduct this task because this shop is usually slow before lunch.

We entered the store, I grabbed a shopping cart and wiped it down with an alcohol wipe before putting my child in it – then went about my shopping.

Once I completed our shopping, we got in the checkout line and stood on the strip of red tape six feet behind the shopper ahead of us to follow the store’s social distancing policy – there was another strip six feet behind me, and so on.

There were only two of the ten cashier lines open, which is normal for mornings. Yet as I looked at the impulse buys in front of the register, the line behind us grew. My strategic plan of going shopping in the morning to avoid a crowd was crumbling.

I turned from looking at gum and noticed that the man behind us wasn’t wearing a mask and was mumbling to himself. Visibly agitated, he was muttering profanities about the slightly longer wait and had moved to within whispering distance of me. Did he even notice the red tape?! I think all parents, everyone for that matter, can imagine the fear and panic snowballing in the pit of my stomach as I hovered closer and closer to my child – hoping to shield her from harm with my body. Enough was enough.

At that point, I took a breath from through my mask, turned, and firmly told the man behind us that we’re all in this together and he should kindly withdraw to the red strip of tape six feet behind us and offered him an extra mask I had packed. He momentarily balked at my comment, but then begrudgingly took the mask and moved back to the strip of red tape. We got home without further incident, but it got me thinking – was that whole episode really necessary?

Since I work for an edge AI and computer vision company, I know there are better ways to manage and control situations such as the one I experienced. Firstly, deploying mask detection at store entrances can avoid the issue of not having security personnel on duty. If the store wants to invest further, they can include crowd density detection throughout the store as well as at the checkout. Computer vision is quick to implement. It isn’t complicated and there is no breach in privacy. In any case, if it can help protect my child without me having to step in and confront an agitated stranger, I really don’t mind a little bit of surveillance. 

As an active member of the community, I do my civic duty whenever I can. I hope grocers and other retail shops will do the same by implementing extra measures to protect their shoppers.

To read more, click on what interests you below:

Post-Pandemic Area Management

Video Analytics

Edge AI

Whitepapers

Video Analytics Technology Main Image

Video Analytics Technology

What is Video Analytics?

Picture this, you’re in a crowded train station and have lost your friend in the mix. How do you and your brain go about picking your friend out of the crowd? Do you go through the same process each time you look for something or does it depend somewhat on what you’re seeking? From a human perspective, looking for stuff seems rather straight forward and although we can describe those processes easily to others, the way we search for and identify things generally differs and depends on what we’re searching for. How one goes about finding a lost friend in a station is different than searching for your keys before going to the office.

Video analytics to find someone in a busy station.

Now imagine how we might go about getting computers to look for things. They would need some kind of input to detect specific objects, recognize and differentiate between those, and then notify us somehow when the requested result is found or not. This process is what we call intelligent video analytics, IVA for short.

This article will go into how different kinds of IVA work and also give some examples along the way.

What Video Analytics Does

The processes involved in getting IVA output from software is similar to how people visually detect and recognize things. The essence of what video analytics does is generally described in three steps.

    • Video analytic software breaks down video signals into frames. This article will not describe this step, but understanding digital video and how it works is an interesting topic and good to know before we break down the next steps.
    • The software then splits the video (frames) into video data and analytic data, then uses algorithms to process the analytic data to output specifically desired functions.
    • And finally, it delivers the result in a predetermined manner.
Working through the process.

Approaches to Video Analytic Processing

Let’s get into the details for number two from the above list as it’s what most people have been talking about recently.

Depending on the goal, video needs to be processed using different methods in order to deliver relevant results. Gorilla has categorized the most widely used types of analytics into five fundamental IVA groups which are described in more detail below.

1. Behavior Analytics

These analytics use algorithms that are designed to look for a specific behavior.

Thinking more deeply, a behavior could be defined as action over time. With that in mind, each Behavior Analytic needs more than one frame from the video to determine if an event or behavior has occurred. So it follows that the algorithms in Behavior Analytics look for changes from frame to frame over time to identify a very specific and predefined event or action. We’ve broken down and classified the Behavior Analytics that are used in our solutions here:

People Counting

People Counting Video Analytics

The People Counting IVA does just that, it detects and counts people for a specified amount of time as they enter a zone and/or cross a line which users define in the software.

Line Crossing

Line Crossing Video Analytics

This IVA detects when people cross a line (or lines) of user defined length and position.

Intrusion Detection

Intrusion Detection Video Analytics

Intrusion Detection monitors user created zones to detect any activity or entries by moving objects (like people).

Direction Detection

Direction Detection Video Analytics

This IVA monitors a user created zone for people moving A) within the zone AND B) in the marked direction. Movements in the opposite direction do not trigger an alert.

Direction Violation Detection

Direction Violation Detection Video Analytics

Same as the direction detection IVA but detects and alerts to movements in the opposite direction. As an example, security checks at airports and other transportation hubs stand to benefit from this type of IVA.

Loitering Detection

Loitering Video Analytics

The Loitering Detection IVA monitors figures or people entering and then remaining in a user created zone for a specified period.

2. People/Face Recognition

People and Face Recognition could easily be sliced into two core groups, but we keep them as one since they are so closely related. As Behavior Analytics need to detect human shapes to perform effectively, People/Face Recognition IVAs are next on our list.

Human Detection

Human Detection Video Analytics

The Human Detection IVA detects human figures within the video. Once detected, features like clothing color, gender, eyewear, masks, and age group can be detected as well.

Face Recognition

Face Recognition Video Analytics

This IVA recognizes and identifies faces. This is used in conjunction with Gorilla’s BAP software and its facial recognition database. While uses for this are myriad (and often in the news), we most often see Face Recognition used for Watch Lists, VIP identification, Attendance Systems, and Black Lists.

3. License Plate Recognition

Some people collect license plates and like them because different places have different plates. However, this variety makes it incredibly difficult for one License Plate Recognition (LPR) IVA to work globally (or even just from state to state). Currently, we generally see this IVA added as a customized feature because adding all the different and beautiful plates into the general release of the software would require too much space.

License Plate Recognition Video Analytics

Having said that, there are currently two approaches to LPR.

      • Parking LPR detects the license plates of parked vehicles in user created zones, vehicles travelling slowly, or vehicles stopped at boom gates.
      • Road Traffic LPR detects the license plates of moving vehicles, or vehicles stopped at a stoplight.

4. Object Recognition

Object Recognition Video Analytics

Replace the Face Recognition IVA with any given object and you’ll get the Object Detection IVA. This is where algorithms are used in training the software to detect and recognize a specific object, like a hot dog. There are a lot of different objects in the world (even more than there are license plate types!), so the training and size requirements add up quickly.

5. Business Intelligence

Dashboards in software showing data about various business activities are a valuable asset in just about any retail or enterprise setting. Using video analytics from within a dashboard to enrich and increase results should be a part in everyone’s toolbox.

While the IVAs in numbers one through four above are widely used for surveillance scenarios, there are a magnitude of business scenarios that can reap the benefits that video analytics offers. To see some great examples, check out how Gorilla is applying these to create intelligent solutions for multiple business markets and industries.

Putting the Video Analytic Idea Together

As you read above, these IVAs all orchestrate various algorithms to achieve and deliver results. Essentially though, IVAs detect for and determine if a defined event or behavior has been found or occurs within a video camera’s field of view and then notifies the designated user of the finding.

In a similar manner, most of us go through varying processes depending on if we’re searching for keys at home or for our friend in a busy station.

Video Analytic Processing Power

Thinking about the entire process, could there be a single solution that can do everything effectively? It seems like an insurmountable amount of tasks: from processing each single frame’s analytic data to displaying it together with the video, into creating a complete video system with an array of user selectable & customizable IVA in a building or any other scenario, all the way to putting multiple systems together that report back to a central control center.

It’s not impossible. To demonstrate this, let’s look at what IVAR™ from Gorilla can do and how it operates.

CPU and GPU Video Analytic Processing

Video analytics as a whole requires a lot of dedicated processing power. We should keep in mind here that before optimization and edge devices with capable CPUs, video analytics was processing both video and analytic data on one machine and required additional GPUs to do most of the work. Technology and the ability to split these two up has advanced to the point that it’s now possible to keep the video data at the edge while pushing the analytic data up the network for quick processing.

One technology, which Gorilla was the first to adopt, is the Intel® distribution of the OpenVINO™ toolkit. Using the OpenVINO™ toolkit to optimize IVAR keeps deployment and upkeep costs low while decreasing operating temperatures by minimizing the need for expensive GPUs.

Delivering and Deploying Video Analytics

Considering the multitude of IVA capabilities and applications in the world today, Gorilla is asked about many things regarding delivering and deploying video analytics and the IVAR platform.

Q: How many video feeds can IVAR handle?

A: IVAR is a highly scalable solution that fits nearly any size system, from a single camera with one IVA to multiple systems with hundreds of cameras running multiple IVAs.

Q: I need a complete VMS with integrated IVA, is IVAR right for my company?

A: From using it as a standalone all-in-one video surveillance solution, to integrating via IVAR’s open API, to adding it to an existing Milestone Xprotect® system, IVAR excels at being versatile in suiting your needs.

IVAR Edge AI Video Analytics Dashboard

Final Thoughts on Video Analytics

The next time you find yourself in a crowded station and need to locate a missing friend (which is hopefully never), think of how a computer attached to a camera might go about doing it. The way that video analytics works is an incredibly interesting and broad topic to cover in one article.  If you made it this far in the article, you should now have a solid understanding of how video analytics operates and how video analytic software solutions like IVAR are driving technology forward.

Further Reading on Video Analytics

To read more about edge AI, click here

For more info on IVAR, click here

You’re also welcome to contact us here at any time: Contact Us

If you liked this article, why not share it or leave a comment below? We love conversation and talking about our tech!