Locks and Security News: your weekly locks and security industry newsletter
5th August 2020 Issue no. 519
Your industry news - first
We strongly recommend viewing Locks and Security News full size in your web browser. Click our masthead above to visit our website version.
Six smart security trends and the role of storage
By Barber Brinkman, Senior Business Development Manager, EMEAI Smart Video at Western Digital
The static surveillance measures we're accustomed to are evolving. Thanks to new capabilities enabled by artificial intelligence (AI), real-time video analytics is now a reality, with AI and smart video promising to extract greater insights from security video.
As more of these always-on systems are rolled out, edge computing will play an important role in capturing, collecting, and analysing higher resolution data. There are six key trends that you can expect to see as a result of this evolution.
1. Transitioning from the standard security camera
The humble security camera has long dominated the conversation on security technology. These systems have focused on streaming a video feed from a fixed security camera to some central location where it's either being manually observed in real-time or recorded for future reference. This has become the standard people expect for security, but today, we're seeing an evolution of smart cameras through the emergence of artificial intelligence.
Thanks to AI, cameras are no longer simple, static lenses, they're being tasked to do more - pattern matching and focusing on specific zones or movements. Cameras that used to catch shoplifters post-crime can now identify shoplifting in real-time and these devices can even be used to analyse shopper habits. For example, what types of shoppers enter a store and what aisles do they go to? By gaining new insights into buyer habits, stores can help to inform the decisions behind more enjoyable and profitable shopping experiences.
But in order for the above to be possible, these smart security cameras require intelligence and storage within the device itself. In addition, there are many more types of cameras being used today, such as body cameras, dashboard cameras, and new Internet of Things (IoT) devices and sensors.
Video data today is so rich, you can analyse it and deduce a lot of valuable information in real-time, instead of post-event.
2. Smart security & edge computing
As public cloud adoption grew, companies and organisations saw the platform as a centralised location for big data. However, recently there's been opposition to that trend. Instead we are now seeing data processed at the edge, rather than in the cloud. There is one main reason for this change in preference: latency.
Latency is an important consideration when trying to carry out real-time pattern recognition. It's very difficult for cameras to process data - 4K surveillance video recorded 24/7 - if it has to go back to a centralised data centre hundreds of miles away. This data analysis needs to happen quickly in order to be timely and applicable to dynamic situations, especially if its regarding public safety. By storing relevant data at the edge, AI inferencing can happen at a quicker rate. Doing so can lead to safer communities, more effective operations, and smarter infrastructure.
3. The rise of smart surveillance in smart factories
Factories are always a hive of activity. In times gone by, this would mean numerous different parts operating separately to one another. Today, thanks to the rise in IoT technology, these elements are inter-connected and often work in unison. From the design stage, to the assembly line, and everything in between - AI and IoT are central to the smart factory. And that means smart surveillance, too.
The business of the modern factory requires a high-definition, 360 smart surveillance that can monitor all activity. In addition to the obvious security uses, smart cameras can be deployed to help analyse the efficiency of warehouse processes and the functioning of the product line. But these extra technological demands require a large amount of data to operate 24/7 and storage of this footage is of course of paramount importance.
4. The demands of UHD
AI-enabled applications and capabilities, such as pattern recognition, depend on high-definition resolutions such as 4K - also known as Ultra High Definition (UHD). This detailed data has a major impact on storage - both the capacity and speeds at which it needs to be written - as well as on the network. Compared to HD, 4K video has much higher storage requirements. Those of 8K, which is also on the horizon, are even higher.
As we know, 4K video has four times the number of pixels than HD video. In addition, 4K compliant video supports 8, 10, and 12 bits per channel that translate to 24-, 30- or 36-bit colour depth per pixel. A similar pattern holds for HD - more colour using 24 bits or less colour using 10 or 12 bits in colour depth per pixel. Altogether, there is up to a 5.7x increase in bits generated by 4K vs. 1,080 pixel video. Larger video files place new demands on data infrastructure for both video production and surveillance. Which means investing in data infrastructure becomes a key consideration when looking into smart security.
5. 24/7 connectivity
Whether designing solutions that have limited connectivity or ultra-fast 5G capabilities, most smart security solutions need to operate 24/7, regardless of their environment. Yet, on occasion, the underlying hardware and software systems fail. In this event, it is important to establish a failover process to ensure continued operation or restore data after a failure, including everything from traffic control, to sensors, to camera feeds and more.
Consider the example of a hospital with dozens or even more than a hundred cameras connected to a centralised recorder via IP. If the Ethernet goes down, no video can be captured. Such an event could pose a serious threat to the safety and security of hospital patients and staff. For this reason, microSD(tm) cards are used in cameras to enable continuous recording. Software tools - powered by AI - can then "patch" missing data streams with the content captured on the card to ensure the video stream can be viewed chronologically with no content gaps.
6. Advancing device analytics
Self-monitoring has become a critical tool in enabling better uptime, proactive support and efficiency for many systems. Whether in smart factories or enterprise settings, an entire system can fail simply due to one component malfunctioning. A hard drive can fail due to a broken fan causing its internal temperatures to rise dramatically, for example. By designing an intelligent platform to track device health, systems can be built to work proactively. With this in mind, companies need to look at investing in hard drives that can monitor a variety of parameters, including temperature, to help administrators take immediate action before reliability is compromised.
The fixed-place security cameras we are used to have been a trusted and well-used monitoring surveillance technology for a number of years, but are not without their shortfalls. The needs of security today demand the use of AI and edge computing, in order to provide that always-on, high-resolution security provision that can keep people safe 24/7. This does mean that the demands placed on security monitoring are higher and the requirements of the supporting data infrastructures need to match that. As a result, companies need to consider their storage capabilities when updating their security provisions.
29th April 2020