Video on the edge of smart cities

Share on facebook
Share on twitter
Share on linkedin
Share on whatsapp
Share on email
Share on print
cities

As smart cities evolve, security becomes a core component for the efficiency of an urban environment, how can video surveillance play a part? – sponsored by ASSA ABLOY

By 2025 the global market for video surveillance cameras will grow to nearly $50 billion, according to the latest estimates by IDC. As the demand for smart video grows, paralleled by an increase in the use of Artificial Intelligence (AI), this will drive the development of data architectures at the edge and smart cities. 

AI is excellent at doing specific, narrow tasks incredibly well. The aim of AI is not to teach technology to see the world as humans do, but instead to enable computers to capture, analyse and learn about the human world, in rapid and accurate ways. The profound value of AI comes from taking computer intelligence capabilities – such as object recognition, movement detection and tracking or counting objects/persons – and using these in the right application. Given the utility of these applications, it’s not surprising that the amalgamation of video, artificial intelligence and sensor data is a hotbed for new services across industries and integral to the adoption of smart cities globally. Brian Mallari, Director of Product Marketing, Smart Video, Western Digital, explores exclusively for Security Buyer how smart video surveillance is integral to the running of a smart city and an efficient urban environment. 

Larger and smarter use cases 

Smart video is a keystone of modern security and surveillance activity. However, it should also be recognised that the market is expanding through a growing amount of use cases. These include medical applications, sports analysis, factories, traffic management and even agricultural drones.   

Intelligent technology is making these use cases “smart”, i.e. devices deploying intelligent insights. For example, in “smart cities”, cameras and AI analyse traffic patterns and adjust traffic lights accordingly to improve vehicle flow, reduce congestion and pollution and increase pedestrian safety.  Another example of this is “smart factories”, which implement the type of narrow tasks AI excels in, such as detecting flaws or deviations in the production line in real-time and adjusting to reduce errors. Smart cameras can be very effective in this use case at the level of quality assurance, keeping costs down through automation and earlier fault detection.  

Changes at the edge 

As smart video evolves, it’s developing in parallel to other technological and data infrastructure advancements, such as 5G. As these technologies come together, they’re impacting the architecture of the edge, and what we require from data storage. More specifically, they’re driving a demand for specialised storage. Here are some of the biggest trends currently developing:  

  1. Strength in numbers  

Having more cameras means there is more media-rich data to be captured and analysed. This means it can be used to train AI.   

Simultaneously, cameras are supporting higher resolutions (4K video and above). The more detailed and sharp the video, the more insights can be extracted from it, and thus the more effective the AI algorithms can become. In addition, new cameras transmit not just a main video stream but also additional low-bitrate streams, perfect for low-bandwidth monitoring and AI pattern matching. 

Some of the biggest challenges for these types of workloads is the fact that they’re always on. Especially necessary in the case of security, many smart cameras operate 24/7, 365 days a year, as is needed for their role.  

The challenge here is that storage technology must be able to keep up. One way in which storage has evolved to meet this challenge, is the development of the ability to deliver high performance data transfer speeds and data writing speed, to ensure high quality video capture. Furthermore, on-camera storage technology that can deliver longevity and reliability has become even more critical, in comparison to storage technology at a remote data centre.  

  1. The rich variety of endpoints  

The realm of security relies on more than just visual data. New types of cameras are being developed with new types of data to be analysed. Cameras can be found everywhere – atop buildings, inside moving vehicles, in drones, and even in doorbells.   

The location and form factor of smart cameras impacts the storage technology required. The accessibility of cameras (or lack thereof) needs to be considered – are they atop a tall building? Maybe amid a remote jungle? Such locations might need to withstand extreme temperature variations. For example, security drones monitoring a location of extreme heat. All of these possibilities need to be considered to ensure long-lasting, reliable continuous recording of critical video data.   

  1. AI chipsets 

Increasingly real-time decisions are being made at the edge at device level, due to improved compute capabilities in cameras. New chipsets are arriving for cameras that deliver improved AI capability, and more advanced chipsets offer deep neural network processing for on-camera deep learning analytics. AI keeps getting smarter and more capable.   

As the innovation within cameras continues, there is a rising expectation that deep learning – requiring large video data sets in order to be effective – will happen on-camera too, driving the need for more primary on-camera storage.    

Even for solutions that employ standard security cameras, AI-enhanced chipsets and discrete GPUs (graphic processing units) are still being used in network video recorders (NVR), video analytics appliances, and edge gateways to enable advanced AI functions and deep learning analytics. With NVR firmware and OS (operating system) architecture evolving to add such capabilities to mainstream recorders, the implications for storage are large, having to handle a much bigger workload.   

For example, there is a need to go beyond just storing single and multiple camera streams. Today, metadata from real-time AI and reference data for pattern matching needs to be stored as well.  

  1. Don’t say goodbye to the cloud 

The majority of the video analytics and deep learning for today’s smart video solutions is completed by discrete video analytics appliances or in the cloud. Similarly, broader Internet of Things (IoT) applications that use sensor data beyond video are also tapping into the power of the deep learning cloud to create more effective, smarter AI. 

To support these new AI workloads, the cloud has gone undergone a transformation. Neural network processors within the cloud have adopted the use of massive GPU clusters or custom FPGAs (field programmable gate array). They’re being fed thousands of hours of training video, and petabytes of data.  

This cloud activity still requires specialised and robust storage: these workloads depend on the high-capacity capabilities of enterprise-class hard drives (HDDs) and high-performance enterprise SSD flash devices, platforms or arrays.   

  1. Reaching for the stars with 5G 

Wired and wireless internet have enabled the scalability and ease of installation that has driven the explosive adoption of security cameras – but it could only do so where LAN and WAN infrastructures already exist.  However, 5G is a game changer here.  

5G removes many barriers to deployment, allowing more options for where a camera can be installed and easily used in metropolitan locations. With this ease of deployment comes new greater scalability, which increases use cases and encourages further advancements in both camera and cloud design.   

For example, cameras can now be stand-alone, no longer dependent on a local network and instead using direct connectivity to a centralised cloud. Emerging cameras that are already 5G-ready are being designed to load and run 3rd party applications that can bring broader capabilities.  With 5G behind it, the sky’s the limit on smart video innovation.   

The flipside is that with greater autonomy, comes the need for even more dynamic storage for these cameras. They will require new combinations of endurance, capacity, performance, and power efficiency to be able to handle the variability of new app-driven functions. 

Storage technologies must not only keep pace with the already growing demands of smart video, but they must also enable and encourage new capabilities and smart use cases. As the proliferation of smart video throughout the security space only continues, the hidden storage complexities should not be forgotten. Smart video is integral to the development of smart cities to help benefit building technology, transportation, public safety and infrastructure.  

From the sponsor – ASSA ABLOY

BIM puts technology to work 

ASSA

Every construction project needs a constantly evolving store of data, where everyone from architects to specifiers can find the information they need 

As our buildings demand smarter, forward-looking solutions on the insidedigitisation of the construction process itself is also becoming necessary. 

Smarter cities and smart buildings will require digital innovations in the construction process, not just of the finished building’s functions. Plus, when done successfully, smart use of technology ensures a project gets delivered faster, more accurately and with less waste. 

Building Information Modelling (or BIM) is increasingly important to architects and engineersbuilding owners and contractorsMore than just a 3D design of a building, BIM is a collaboration process. Its goal is to place every product, component and construction material within a data-rich building model. 

“As security solutions have developed and become more sophisticated, so has their impact on the overall building environment,” says Marc Ameryckx, BIM Development Manager EMEIA at ASSA ABLOY Opening Solutions. “If doors, entrances and access control solutions don’t have the features required by the building manager from the outset, it can become a real challenge to implement this at a later stage.” 

Input from door and security technology experts 

Embedding BIM consultants from the beginning helps to streamline a construction project. A well configured BIM team coordinates specification and design in tandem, ensuring the full implications of every change or tweak are understood. 

With door solutions rendered accurately inside the model, for example, architects can introduce security solutions into early design drafts. The nightmare scenario — disrupting aesthetics and usability with a last-minute change to accommodate smarter security — is prevented.  

Security solutions can pose a particular challenge for construction — one which partnership via BIM can resolve. “Security systems are now crucial components within buildings,” adds Ameryckx. “They should be factored in as early as possible. Partnering with a security manufacturer who has BIM expertise is the best way to do this.” 

Consultants and specifiers with broad access control and door technology expertise also bring something else: an independent security and safety perspective which may otherwise be missing from a project mix built around design and construction. 

“We provide subject matter expertise, as well as software solutions to aid the scheduling and coordination of openings information,” says Robert Akers Commercial Excellence Director, at ASSA ABLOY Opening Solutions EMEIA. 

“Our team has experienced projects of every size — up to thousands of openings. They can input comprehensive specifications and detailed geometry, formatted for seamless integration with architectural design software. Where relevant, inputs include manuals and Environmental Product Declarations (EPDs) required for green building certification schemes — another fast-growing consideration for smart buildings and cities.” 

Software can make the BIM process even more efficient 

Specialist BIM software can play a key role as a conduit between architectural design software and databases which hold detailed specification, data as BIM objects and in other formats. ASSA ABLOY’s own Openings Studio, for example, delivers detailed door solution specifications directly to popular packages such as Revit and ARCHICAD. 

“Openings Studio software introduced us to a whole new way of thinking and efficiency,” says David Zarhy. Zarhy Architects used a multidisciplinary BIM process for the first time, when designing the new Broadcom R&D Center at Tel Aviv University. 

ASSA

 

Jovan Arsovski, Senior Building Intelligence Engineer at Hoare Lea 

If you ask people what they consider a smart building to be, you will get a different answer every time, and the great thing is every answer is correct. Smart buildings are different things to different people.  

The US have a huge focus on green buildings, operational efficiencies, fault detection and diagnostics and portfolio-wide rollouts of digital twins optimised workflows and indoor air quality, etc. 

Jovan Arsovski
Jovan Arsovski

The Canadian market – Statistically speaking, Toronto currently has the most crane’s in North America. This is because there is a huge push to construct buildings – digitally enabling and futureproofing them. Therefore, the vision here isn’t necessarily to create smart buildings from day 1 but to enable the infrastructure so that this can be easily achieved later down the line. Historically a lot of these things were value-engineered out, but as the industry is growing, developers realize that down the line, if a building isn’t a specific standard where technologies can be implemented, it becomes a premium charge to them to change and make upgrades to systems etc. Digital enablement is a key aspect of what they consider to be a smart building.    

The UK is a very competitive market. There is a vast push to return from the pandemic and get people back in the office, looking at human-centric experiences. There is a focus on comfort and safety and empowering occupants through data.  

Demand is increasing, and costs are decreasing, so we’re seeing the rollout of smart buildings now, not just in major cities around the world but also in smaller cities and small to medium-sized businesses. There seems to be exponential growth in smart building strategies.  

Brian Mallari, Director of Product Marketing, Smart Video, Western Digital  

By 2025 the global market for video surveillance cameras will grow to nearly $50 billion, according to the latest estimates by IDC. As the demand for smart video grows, paralleled by an increase in the use of Artificial Intelligence (AI), this will drive the development of data architectures at the edge and smart cities. 

Brian Mallari

AI is excellent at doing specific, narrow tasks incredibly well. The aim of AI is not to teach technology to see the world as humans do, but instead to enable computers to capture, analyse and learn about the human world, in rapid and accurate ways. The profound value of AI comes from taking computer intelligence capabilities – such as object recognition, movement detection and tracking or counting objects/persons – and using these in the right application. Given the utility of these applications, it’s not surprising that the amalgamation of video, artificial intelligence and sensor data is a hotbed for new services across industries and integral to the adoption of smart cities globally.  

Smart video is a keystone of modern security and surveillance activity. However, it should also be recognised that the market is expanding through a growing amount of use cases. These include medical applications, sports analysis, factories, traffic management and even agricultural drones.   

Intelligent technology is making these use cases “smart”, i.e. devices deploying intelligent insights. For example, in “smart cities”, cameras and AI analyse traffic patterns and adjust traffic lights accordingly to improve vehicle flow, reduce congestion and pollution and increase pedestrian safety.  Another example of this is “smart factories”, which implement the type of narrow tasks AI excels in, such as detecting flaws or deviations in the production line in real-time and adjusting to reduce errors. Smart cameras can be very effective in this use case at the level of quality assurance, keeping costs down through automation and earlier fault detection.  

 

To stay up to date on the latest, trends, innovations, people news and company updates within the global security market please register to receive our newsletter here.

Media contact

Rebecca Morpeth Spayne,
Editor, Security Portfolio

Tel: +44 (0) 1622 823 922
Email: editor@securitybuyer.com

 

Subscribe to our newsletter

Don't miss new updates on your email