HEALTHCARE

Christina Cardoza: Hello and welcome to the IoT Chat, where we explore the latest developments in the Internet of Things. I’m your host, Christina Cardoza, Associate Editorial Director of insight.tech. And today we’re talking about unified security systems with David Trujillo from AxxonSoft. But before we get started let’s get to know our guest a little bit more. David, welcome to the podcast. What can you tell us about yourself and the company, AxxonSoft?

David Trujillo: Hi, Christina. Like you said, I’m David Trujillo, I’m a Sales Engineer at AxxonSoft, so I often give demos about our security systems and some of our VMS platforms, and we’re really excited to share with you today some of the topics to discuss about the Internet of Things and how that relates to some of the platforms and unique capabilities of our VMS.

Christina Cardoza: Absolutely, and I’m excited to learn more about it. You know, security systems aren’t anything that’s new for businesses. They’ve had them for quite a long time, but they have evolved quite a bit over the last few years, especially with new capabilities and features out there. So, David, I’m wondering, to start off this conversation, if we can talk about some of that evolution and changes in terms of new approaches, features, and efficiencies today in the security landscape.

David Trujillo: Yeah, absolutely. So, there’s a few major trends in the physical security industry right now. So, really the first thing I would mention is the service approach in providing security solutions, which in and of itself is connected with cloud technology. So, some examples of those cloud-based solutions offered as a service are things like video surveillance and access-control systems. So, given that security systems themselves have to be on the premise anyways, what does that necessarily mean in practice, you might be asking?

So, a cloud service typically acts as a managing system that collects, stores, and analyzes data from the devices, manages user rights, and provides access to administration and control-monitoring interfaces for multiple users. So, this is akin to a software as a service, or SaaS, approach that encompasses different types of systems depending on their architecture. For instance, video surveillance as a service, or VSaaS, systems can store video archives in the cloud and you can have only cameras installed at a site, or you can have a hybrid deployment with the cameras and video storage both on site but the cloud service is used for remote video monitoring and system management.

So, the market of cloud systems is growing, as they offer users many benefits. There’s low upfront expenditures, there’s easy scaling for large-scale deployments, out-of-the-box remote monitoring, and there’s clear cost planning through a pay-as-you-go model. Of course cloud solutions have their pros and cons, which are an extensive topic for a separate discussion. The other two big trends to take note of are integration, and the use of artificial intelligence—namely neural network video analytics.

So, first of those, integrated solutions, improves efficiency through new and more effective configurations that wouldn’t be possible with standalone systems. Video surveillance can be combined with access control, smoke and fire detectors, intrusion alarms, and even building automation systems using certain interaction scenarios. For example, when an alarm sensor is triggered, the video monitoring software can be configured to immediately give the operator video feeds from nearby cameras, enabling them to quickly assess the situation and react accordingly. Or, another example, when the last employee leaves the premises at the end of the day, you can set it so the lights automatically go out and the ventilation switches to a lower intensity. So—you can also arm the intrusion alarm at the same time. So, there’s plenty of scenarios like this, where automation can make facilities more secure, energy efficient, and cost effective overall.

Christina Cardoza: Great. And I like how you mentioned at the beginning of that physical security. So we’re not talking about necessarily cyber securities or protecting our devices that we’re using like our computers and stuff, but we’re talking about, you said surveillance, so, looking within stores for any alerts or threats, analyzing customer behavior, employee behavior, things like that. And you also mentioned integration is a big part of it, and a big part of the trends that have been happening.

So, when we talk about these type of security systems, I’ve heard people talk about unified security, which we’re talking about today, but also integrated security systems, and I know you mentioned that’s a feature of this. So, is there a difference between integrated and unified security, or are we talking about the same thing in those two terms?

David Trujillo: So, these terms—often you hear them used interchangeably, and there’s no real strict definition for either. But in general, however, the term “integration” usually comprises a wider variety of solutions. So, let’s consider an example where you have video surveillance and access-control systems. So, when someone swipes their access card to the reader, the video-surveillance system receives an event from the access-control systems, which then triggers video recording. So this way you get recorded footage of everyone passing every time someone passes through an access point. The event itself may contain the employee’s name and their ID number, so it can quickly search for the footage with those parameters. So this is an example of event-based integration, but in general the systems are independent, with each one having its own user interface, the separate configuration, hardware, and so forth.

“Unified” implies a deeper level of integration, though usually unified software manages all devices, both video cameras and access-control devices in our example. So, what are the benefits of this? First, there’s a single interface for video and access control, which is complemented by other features like 3D map, for example. So when the door is opened you can see the passage on video in real time; the photo of the ID-card owner from the access-control database might be displayed next to the face image captured by the camera along with, for example, their name, their job title, and any other pertinent information. So you can grant access manually if the photos match, or you can take appropriate action if there’s a mismatch. You can do all of this from just one interface, without a need for switching between windows, and you can monitor technical perimeters like hardware status or system health all in one place.

So, a unified solution provides another benefit in the form of a standard and easy way of configuring complex automated scenarios involving different systems, and allowing complex problems to be solved with less effort. Additionally, integration of standalone systems can be performed using third-party software for monitoring purposes. So all the systems will run themselves with their own management software, but this solution will provide most of the features I mentioned. Often when people say “integrated,” they’re actually implying unified, but that would mean a solution that provides the benefits expected from unification. So integration is a broader concept which can be done in various ways, including unification.

Christina Cardoza: Great. Well I’m glad we went over that, because I know these terms can trip up people very often, so it’s good to know what we’re talking about and how we should be talking about it in that way. I want to talk a little bit about the benefits that customers get from this. Not only the people of buying these systems, but the customers in store being monitored. But I know sometimes when we cross the topic of surveillance it could be a little bit of a scary term. People want to make sure that their privacy is being protected, their identification is being protected. So can you talk a little bit about the benefits and the security itself that AxxonSoft provides with the unified security systems?

David Trujillo: Absolutely. So, in a lot of different regions around the world, especially Europe with the GDPR, and California, for example, in the United States with the CCPA, there’s various regulations on a local level that regulate and protect the rights of people in general. So we don’t want some kind of Big Brother situation where every person is being scrutinized individually, and AxxonSoft of course offers features that allow the VMS to be in compliance with this. And we have plenty of different functions on the video level which are able to maintain this.

So, various things that we can do include a blurring of people’s faces or even their whole body, and this allows you to still see what’s going on on the footage because these privacy features are totally integrated with things like AI analytics, which are able to detect where a person is and accordingly blur only the person’s details instead of blurring, for example, the entire image. We can also block off certain areas of the footage that might not want to be seen, and control exactly who is able to see these in terms of the access control and operators. So, quite a few different things that we can do to ensure the privacy of people that are seen on the cameras, and then not revealing every single detail.

Christina Cardoza: Great. Yeah, thanks for that. It’s always good to hear how companies are protecting their users and their customers, especially as privacy becomes an ongoing trend across all verticals and industries. I want to move on a little bit to how businesses are actually implementing these security solutions, how they’re deploying them. But before we move on to that topic, is there anything else about the benefits of unified security or the different types of unified security systems that is going to be important to this conversation?

David Trujillo: Yeah, absolutely. So, some of the benefits include the enabling of implementation of new features that aren’t available within self-contained systems, which in turn gives several benefits. They can reduce the amount of information that the operator must process, while producing improved situational analysis based on information from multiple sources. Furthermore, you can automate decision making for even mundane situations. This way the operator’s work can be more efficient, which in turn reduces the likelihood of making mistakes. Additionally, open-platform solutions allow you to combine equipment from different manufacturers and manage it from a single control center. So this helps minimize the cost of equipping the facility by reducing the amount of software and hardware needed, as well as connecting existing equipment to the system.

I know one concern that a lot of people have and tend to ask is, will this work with my existing cameras? And that’s something that we definitely keep in mind, is that we want to have our system always work with existing systems, and not need an entirely new setup where people have to tear out all cameras and install new ones.

Christina Cardoza: Yeah, that’s great to hear. Being able to leverage existing infrastructure I know is always a huge benefit to end users, and all of these benefits sound great, but I know when it comes to actually putting systems in use or taking advantage of some of these new features and capabilities we talked about, it can be challenging sometimes for businesses. So, can you talk about what are some of the challenges businesses are facing as they add new devices or these new advanced capabilities?

David Trujillo: Definitely. So, implementing a unified security system is more complex than implementing a standalone one. For this you’re going to need a more qualified integrator, who can connect and set up each of the devices as well as configure the interoperation of all the systems. Additionally, you might need custom integrations and functionality enhancements to get a well-honed solution for your needs. This is crucial for high-end installations like systems for large enterprises, or citywide–public safety setups. So, most common requirements can be solved through standard tools, but either way, a more qualified integrator will be necessary for unified security systems than it would be for standalone ones.

Christina Cardoza: Great. And, you know, since we were talking about, it is possible for businesses to leverage some of their existing infrastructure, I’m wondering, how do you know when you can leverage your existing infrastructure? And what type of new investments businesses do need to make—so, other necessary components or investments to implement a unified security system versus a standalone system?

David Trujillo: One of the most notable investments is getting it set up properly. So, there may be situations where it’s not necessarily a plug-and-play situation, where you can expect to just install the software, install the cameras and other access-control devices, and then expect to have your solution ready to go right away. You’ll need to know exactly what you want and what you’re trying to do, and for certain tasks—like automation, I mentioned earlier, for example—situations where it might just be even to increase efficiency, like, we want to turn off the lights at the end of the day; we want to lower the air conditioning system when no one’s in the building—you will need to set up these kinds of scenarios, and automation configurations and these sorts of things might not always be available or set up by default. So you may need to do that on your own or have an integrator for that.

Christina Cardoza: Great. And we mentioned that this is physical security we’re talking about, where analyzing customer behaviors and workers for, I’m guessing, industrial settings for worker safety. We’ve mentioned a couple of these use cases throughout the conversation already, but I’m wondering if you can expand on some of the additional use cases or business opportunities that unified security systems are presenting.

David Trujillo: Certainly. So, like you mentioned, integration isn’t just limited to security only, for example, time and attended systems that are typically included as part of access-control systems can be integrated with corporate accounting, which provides for an efficient and automated workflow. Traffic-enforcement cameras can be integrated with systems for issuing fines for violations. So, I also mentioned earlier the example of building automation and energy efficiency. So there’s plenty of solutions where interoperation cannot just improve security, but also optimize business processes.

Christina Cardoza: Great. I love that this is hitting across manufacturing, smart cities—I’m thinking even, like, healthcare and education for that. Monitoring retail environments. You know, it’s great to see all of this, and I’m assuming since they are integrated or unified security systems they’re continuously monitoring different parts of a building or a store, and so that’s creating a lot of data and a lot of information. And we mentioned how that information overload can sometimes be challenging to businesses, and how AI is really playing a role in this. So I want to talk a little bit more about the role of AI in enabling some of these opportunities across these multiple different verticals.

David Trujillo: Yeah, absolutely. So, we see AI used in video analytics in the security industry, as well as other verticals exactly like the ones you mentioned, like healthcare and retail, industrial use cases, as well as many others. So, AI is often used for accurate detection of specific shapes and objects. So, in the context of security-related applications the greatest demand for this, of course, is detection of humans when you need to detect intrusion in a protected area and there’s a large amount of nonrelevant motion, such as foliage moving around, glare off of rippling water, or precipitation, weather events, etc. A simple motion detection will produce numerous false alarms when it picks up everything that’s moving. So AI helps to filter out false alarms so operators won’t be distracted and can focus only on real threats. When every single possible thing is causing an alarm, operators will quickly learn to ignore those alarms. So you don’t want that happening because they’re going to miss when something actually serious happens.

AI models can also be trained to detect specific objects for special applications. Besides video analytics, AI is also used in biometric devices that are applied in access-control and time-attendant systems. For example, palm-vein scanning utilizes neural network–based pattern-matching algorithms. That’s one of the most accurate methods available today. And returning to integration for a moment, it can be complemented by access-card reading via the same device or using entirely separate readers and integration software. So this kind of multifactor authentication can ensure the highest degree of security.

Christina Cardoza: So, I’m curious how AxxonSoft is making this all possible, is helping businesses reach some of these opportunities that we talked about, as well as addressing some of the challenges we mentioned earlier. And if you have any customer examples or use cases you want to provide that would be great also.

David Trujillo: Certainly, absolutely. We have a few great examples. For an example of AI human detection we have several implementations of this technology across wildlife refuges in South Africa. So, systematic poaching of wildlife is devastatingly epidemic in the region, within the last decade especially. Most of the parks where these poaching crimes occur are fenced, but attempts to protect these areas with perimeter security systems and video surveillance weren’t really effective. The system generated quite a few false alarms because the animals themselves frequently bump into the fences. So because of this, security staff could not possibly monitor every single event, and they frequently misread the threats when poachers intruded in the park.

AI human detection has helped solve this problem by being able to distinguish humans from animals. As soon as there is a breach and a person is detected the surveillance center is immediately notified. The camera can identify where the breach has occurred, and the staff can know the exact location of the threat. The guard center immediately has the necessary information, and they can dispatch an antipoaching unit. So this has proved very successful in preventing killings, as a team is now quickly able to get to the scene of the crime.

A particular example of custom-trained AI analytics is detection of personal-protective equipment. So, this tool is used for enforcing workplace safety by locating individuals not wearing their hard hats, high-visibility vests, or protective clothing. So this is actually really quite a powerful analytic, if you’ve ever seen it in operation. It can actually detect someone’s head and their arms and their torso and even the legs for boots, for example, independently. So you can have cameras for monitoring personal-protective equipment and install them throughout construction sites or production facilities, and integrate that with access control so the system becomes even more efficient through preemptive detection. You can have the camera mounted at an access point where people go in through a certain barrier, and when an employee swipes their access card the turnstile will open only if they’re wearing their protective equipment.

Another example of combining custom-trained AI and integration is monitoring maintenance of railcar wheel sets. So, video analytics detect when wheel sets are passing by a certain area, while ignoring, like, a person moving by the same area. And with the use of virtual line-crossing detection they can detect when wheel sets roll onto a vibration platform and when they roll off. So, these events are sent to third-party software that measures how long each wheel set is on the platform, and then counts the number of wheel sets that have been serviced. So, this is an example in business automation that involves integration with a nonsecurity system. Integration of video surveillance with third-party systems is widely used for cashier operations and supervising the operation of a point of sale. So, the video-surveillance system receives data from cash registers themselves, and then links it to video feeds. So, what you can do is you can superimpose the text of a receipt, for example, on the video, or even display on a different pane. So you can use a receipt’s data, such as product names or prices or certain transaction amounts, to quickly search for transaction videos and recorded footage. So this really offers a full picture of what’s happening at the checkout, and could be used to reveal violations that would be almost impossible to detect via conventional video surveillance. Another example is how video surveillance could be integrated with truck-weighing scales in the same way, by displaying scale readings on the video corner, or in a panel just like that cashier stand information.

Christina Cardoza: I love all those examples, because when you hear about the security systems you’re often thinking about theft or damage, but in the examples you just provided it really is helping improve everyday life and solve real-world challenges. And an ongoing trend that I’ve been seeing with all of this is that it really takes the work of multiple companies and partners to make this happen and to make some of these impactful changes that you’ve just mentioned. And, I should mention, the IoT Chat and insight.tech as a whole, we are sponsored by Intel^®, but I would love to hear how AxxonSoft is working with other partners in the industry, like Intel, to unify these security systems to make changes, and what the value is of working with others.

David Trujillo: Yeah, absolutely. So, mentioning Intel, we’re in constant cooperation with Intel, as well as other software and hardware manufacturers. But Intel processors are at the core of most security-systems servers our clients use. So, our software is developed and tested using Intel computing platforms. AI video analytics are very resource intensive, so hardware-AI acceleration is crucial for building cost-effective solutions, while GPU is often used for AI acceleration. We also use Intel’s OpenVINO toolkit for computer-vision applications, which maximizes performance by extending workloads across Intel hardware, including accelerators. So therefore our AI analytics can run on both Intel processors and accelerators. This includes support for integrated GPUs and AI-acceleration features and Intel processors, as well as support for Intel Vision Accelerator Design products with Movidius video processing units, like Mustang acceleration cards.

We also apply Intel Quick Sync Video technology, which is available on Intel processors with embedded GPU. It provides hardware acceleration for video decoding. Other compressed video feeds would have impractical storage- and network-bandwidth requirements. So, IP video cameras transmit video feeds as compressed streams using codec, like H.264 or H.265. You don’t need to decode the video for recording, but you do need to decode it when applying video analytics on the server, or just displaying the video feeds on the client.

So, AI analytics are not the only processes with heavy computer requirements. This video recording can be a demanding task too, so we use Quick Sync on both the server and client side. In terms of other collaborations we have, we collaborate with IP-camera manufacturers to support embedded video analytics, and other advanced capabilities, such as smart codec.

So when I speak about embedded video analytics, that in particular refers to cameras that are running their own kind of AI detection, and that kind of detection will integrate perfectly with our own. AxxonSoft is a contributing member of ONVIF, which is an open-industry form that provides and promotes standardized interfaces for the interoperability of IP-based physical-security products. We strive to support the newest standards as they appear. So, for example, ONVIF develops new interface profiles to allow software and cameras to communicate, and AxxonSoft is one of the first video-management software vendors to support the new ONVIF M profile when it was released. This profile provides a standardized way for devices and services to communicate metadata and events collected by analytics. You can use ONVIF—any ONVIF M–compliant camera—with our video-management software, which allows you to integrate those embedded video analytics I mentioned earlier seamlessly.

Speaking of third-party security, our physical-security information-management platform, or SIM, was initially developed as an open platform for unified integration. So it offers unified interfaces, flexible configuration of system interactions, and it supports as many as 59 access-control, fire alarm, and perimeter-intrusion-detection systems. We’re now expanding the integration capabilities of our other product, Axxon One; it’s video-management software. And in the next major release we will be adding integration with access-control alarms and perimeter detection, as Axxon One is intended to be our new unified security-management platform.

One more important thing to know is that AxxonSoft is an extremely partner-oriented company, and many integrations and functionality enhancements have been made based on partner requests and their specific project requirements. We’re always open to listening to our partners and customers, making for the most suitable solutions for a wide range of industries and applications.

Christina Cardoza: I love hearing all of the Intel tech going on in these systems, as well as how you’re working with some other third-party partners in the ecosystem. You know, this has been a great conversation. Unfortunately, we are running out of time, and I know we’ve only scratched the surface of some of this—like you mentioned the cloud piece or the AI piece could be a whole separate conversation. But it was great to learn about what unified security systems are, the impact they’re making, and the business opportunities out there, as well as how businesses can start implementing some of these things. Before we go, David, I just want to turn it back to you one last time. Are there any final key thoughts or takeaways you want to leave our listeners with today?

David Trujillo: Yeah, absolutely. Today, artificial intelligence and integration are major trends in the physical-security industry. More businesses and public agencies are taking advantage of integrated and intelligence solutions to enhance security and optimize business. So you can visit our website, AxxonSoft.com—that’s with two x’s—to learn more about our products, intelligent technologies, integrations, and case studies. You can also find links there to watch our videos on YouTube, and follow us on social media. Stay connected, and don’t hesitate to contact us using the forum on the website if you have any questions. We really appreciate your time today, listening and giving us some really great questions as well that I think we managed to fit in. So thanks for having us on today.

Christina Cardoza: Great. Yeah, thanks again for the insightful conversation. I can’t wait to see what else AxxonSoft does in this industry, and thanks for joining the podcast. Thanks to our listeners for tuning in. If you liked this episode, please like, subscribe, rate, review, all of the above on your favorite streaming platform. Until next time, this has been the IoT Chat.

The preceding transcript is provided to ensure accessibility and is intended to accurately capture an informal conversation. The transcript may contain improper uses of trademarked terms and as such should not be used for any other purposes. For more information, please see the Intel^® trademark information.

This transcript was edited by Erin Noble, copy editor.