CCTV: Why the switch to smart video requires more dynamic data storage

CCTV: Why the switch to smart video requires more dynamic data storage

Brian Mallari, director of product marketing, Smart Video, Western Digital says it is important not to view the evolution of smart video in a vacuum

According to Omdia Research, over 116 million network cameras were shipped in the professional surveillance market in 2019, with the capability to generate almost nine petabytes of video every day. And that number will only increase as demand continues to grow and emerging technologies, like artificial intelligence (AI), get incorporated into the device. As a result, data storage providers need to consider how the solutions they offer work to accommodate increased complexity.

It’s important to note that the evolution of smart video is not happening in a vacuum. The progression of the technology is happening alongside other technological and data infrastructure advancements, such as 5G or the Internet of Things (IoT). As these technologies come together, they are impacting the architecture of data storage solutions. There are five big trends we are seeing within the evolution of smart video:

1. Innovation and growth
The number and types of cameras continue to grow, and each new type brings new capabilities. Having more cameras allows more to be seen and captured. This could mean having more coverage or more angles. It also means more real-time video can be captured and used to train AI.

Cameras are increasingly demanding higher resolution as well, with the likes of 4K, which is more data-intensive than lower quality feeds. The more detailed the video, the more insights can be extracted, and 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 used for low-bandwidth monitoring and AI pattern matching.

Unlike cameras of years gone by, smart cameras are operating 24/7, 365 days a year. This always-on technology naturally leads to a higher workload and more substantial storage requirements to cope with the data transfer and writing speeds. As these cameras are adopted more regularly across manufacturing and public sector industries, on-camera and edge storage will become relied upon to deliver longevity and reliability.

2. Any time, any place

It does not matter if it is for a business, for scientific research or even for our personal lives – we capture data on almost everything. As a result, we are seeing new types of cameras that can capture new types of data that can be analysed.

The onslaught of the COVID-19 pandemic has given rise to thermal cameras that help identify those with a fever and explosion-proof cameras are being used in areas of highest environmental risk. Cameras can be found everywhere – atop buildings, inside moving vehicles, in drones, and even in doorbells.

As companies design storage technology, location and form factor must be taken into consideration. It’s important to think of the accessibility of cameras. Are they in hard-to-reach spaces, will they need to withstand extreme temperature variations? All of these possibilities need to be taken into account to ensure long-lasting, reliable continuous recording of critical video data.

3. Specialising for AI
Improved compute capabilities in cameras means processing happens at the device level, enabling real-time decisions at the edge. New chipsets for cameras that deliver improved AI capability and deep neural network processing for on-camera deep learning analytics, are now in market and ready to be taken advantage of.

According to industry analysts Omdia, shipments of cameras with embedded deep-learning analytics capability will grow at a rate of 64 percent annually between 2019 and 2024. This reflects not only the innovation happening within cameras but also the expectation that deep learning will take place on-camera, too.

Even for solutions that employ standard security cameras, AI-enhanced chipsets and discrete graphics processing unit (GPUs) are being utilised in network video recorders (NVR), video analytics appliances, and edge gateways to enable advanced AI functions and deep learning analytics.

One of the biggest changes is that 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.

4. Deep learning and the cloud
Just as camera and recorder chipsets are coming with more compute power, in today’s smart video solutions most of the video analytics and deep learning is still done with discrete video analytics appliances, or in the cloud, as that’s where big data resides. Broader IoT applications that use sensor data beyond video are also tapping into the power of the deep learning cloud to create more effective AI.

To support these new AI workloads, the cloud has gone through some transformation. Neural network processors within the cloud have adopted the use of massive GPU clusters or custom field-programmable gate arrays too. They are being fed thousands of hours of training video, and petabytes of data. These workloads depend on the high capacity capabilities of enterprise-class hard drives (HDDs) – which can already support 20TB per drive –  and high performance enterprise SSD flash devices, platforms or arrays.

5. 5G’s impact on networks
Wired and wireless internet have enabled the scalability and ease of installation that has fueled the explosive adoption of security cameras – but it could only do so where local area network (LAN) and wide area network (WAN) infrastructures already exist. But 5G is on the way.

5G removes many barriers to deployment, allowing expansive options for placement and ease of installation of cameras at a metropolitan level. With this ease of deployment comes new greater scalability, which drives use cases and further advancements in both camera and cloud design.

For example, cameras can now be stand-alone, with direct connectivity to a centralised cloud – they are no longer dependent on a local network. Emerging cameras that are 5G-ready are being designed to load and run third party applications that can bring broader capabilities. The sky really is the limit on smart video innovation brought about by 5G. Yet with greater autonomy, these cameras will need even more dynamic storage. They will require new combinations of endurance, capacity, performance, and power efficiency to be able to optimally handle the variability of new app-driven functions.

The developments in the world of smart video are both complex and exciting, which means the requisite data storage must respond in kind. To cope with the new workloads that have been created and to prepare for the further innovation that lies ahead, architectural changes must be made at the edge and at endpoints. All the while, deep learning analytics continue to evolve at the back end and in the cloud.

The always-on nature of smart video, teamed with the likes of AI or 5G, means that enterprises who oversee a substantial camera network should be considering the storage requirements behind the technology when making these investments. Durable, reliable data storage is needed to ensure critical data is not lost, to comply with regulations and to track information that is important to the company.