Featured NewsSurveillance

How is AI impacting surveillance data storage?

storage

Martin Kruger, Sales Manager for Middle East, Turkey and Africa at Seagate Technology analyses the storage revolution.

Our thirst for data has never been greater. And our desire to be connected, in real-time – at all times – has resulted in the finding that by 2025, an average connected person anywhere in the world will interact with connected devices – smart home security, mobile devices, smart TVs and more – nearly 4,800 times a day. That’s essentially one interaction every 18 seconds.

As our world becomes increasingly connected though, the vast amounts of data being created is also enabling us to refine and improve systems and processes – from security through to smart cities and AI. This is true in the surveillance space too, where data is being analysed more than ever before to provide new and valuable insights.

Opening up new opportunities

By analysing data and distilling it into actionable intelligence, businesses can increase security and improve operations, as well as introduce unique user experiences and mitigate potential risks, opening up a whole new world of business opportunities. This, ultimately, is the true value of data generated by surveillance cameras, sensors and systems.

Data gathered from AI-enabled security systems provides a whole host of benefits. For example, manufacturers can recognise operational inefficiencies in production lines and make immediate adjustments. Medical staff at hospitals can recognise unusual trends in a patient’s health and take action to significantly reduce mortality. Retailers can better understand their customer’s behaviour as well as peak hours for foot traffic.

And going a level deeper, AI also enables intelligent real-time video analysis from a security standpoint. Moving away from the reactionary use of most video technology, forward-thinking organisations can now use their surveillance devices as a more proactive tool that enables preemptive action. AI allows security integrators and end users to identify specific events and triggers in the footage and with this knowledge and insight, gather more accurate alerts and forensics, dramatically reducing the time to act and analyse the video manually.

New frontiers in surveillance storage

By building AI into video systems, this enables them to process, analyse and recognise patterns on-site in real time at the edge, rather than dealing with the latency associated with transferring data and video off-site for analysis. What has spurred this AI evolution, particularly in edge video surveillance applications, is significantly cheaper and faster GPUs with practically limitless storage. Hard disk drives (HDD) must be capable of writing data at high speeds to keep up with these AI applications and simultaneously support both AI and video workloads.

In addition to this increased adoption of GPUs, we are seeing the utilisation of software-defined storage technology. This enables the rapid creation and migration of edge storage environments at the point where live data and big data analytics intersect to meet the need of local and mobile analytic workloads. The growing amount of data creation across the IoT universe in a mobile, real-time world is a fundamental driver of edge storage.

Storage solution providers are responding to the requirement for edge-based processing and analysis by developing drives that offer all the associated benefits. High throughput and enhanced caching ensure these drives deliver low latency and excellent read performance to quickly locate and deliver video images and footage analysis that doesn’t require the power of an off-site data centre.

storage
Martin Kruger

Selecting the right hard drive

The need for more advanced and cost-effective storage options that are optimised for machine learning, deep learning, high-resolution video and advanced analytics streaming, means end users and systems integrators alike are looking for reliable, high-capacity drives. These drives must also be purpose-built for surveillance to support multiple cameras, 24/7 availability and the capability to maximise streaming and frame rate performance.

Deploying the right recording and storage solution for the correct purposes is critical as video becomes a crucial component in the security setup of all businesses. Loss of any data or video integrity is simply not an option anymore. Additionally, storing more data for longer lengths of time is necessary for AI systems to become “smart,” increasing their predictive analytic capabilities. With all these factors in mind, there are a few best practices that integrators can employ to ensure they are selecting the most appropriate hard disk drive for a particular customer application – and the workload associated with it – to ensure long-term success.

What’s next?

The ever-growing datasphere has led to advanced and creative uses for the video and data generated by connected devices. Analysing this virtual sea of data can generate actionable intelligence in real time to enable proactive actions that can mitigate or prevent a security issue from occurring, streamline operational processes, improve customers’ retail experience and much, much more. Among all this data, video plays a key role and AI-enabled surveillance storage solutions enable the faster, more accurate analysis that organisations need to quickly adapt to achieve their security and business objectives.

However, it is vital that integrators carefully evaluate solutions based on the criteria that will impact their performance for the workload specifications of each customer and application. Purpose-built drives with advanced technologies to allow both video streaming and AI analysis ensure the best possible drive reliability and performance, while delivering optimal TCO and the most valuable, actionable intelligence possible.

www.seagate.com

This article was published in the January 2020 edition of International Security Journal. Pick up your FREE digital copy on the link here: https://internationalsecurityjournal.com/digital-magazine-2020/