While technological breakthroughs and the adoption of digital technologies have brought a new era of progress, it can sometimes be difficult for the untrained eye to recognize cutting-edge innovations in everyday life. However, smart cities are a key area where new technologies, such as smart video, artificial intelligence (AI), machine learning (ML) and internet of things (IoT) directly and visibly raise the level of life, while hiding in the background.

The UAE has championed smart cities, creating innovation hubs across the emirates that support smart integration into everyday life. With the government’s goal to strengthen the country’s position as a global hub by advancing innovation and future technologies, the country is poised to become the epicenter of smart urban planning. With the conclusion of Expo 2020, the world got to see some of these ambitions for the first time. Emerging from becoming a hub for futuristic, innovative and smart data, the UAE is building on an era in which AI, IoT and data analytics are the springboards for successful digital transformation . These intensive activities mean that technology must evolve to meet the demands of ambitious smart city developments and create strong security practices to keep these cities safe. This is where data infrastructure will play a crucial role in the UAE and beyond.

Smart cities use information and communication technologies to improve operational efficiency, share information with the public and provide better quality services to local authorities. For example, advances in IoT technologies have enabled connected public transportation systems, which leverage real-time monitoring capabilities, as well as tracking the locations and routes of public vehicles. Not only does this speed up service times and reduce congestion, but it also reduces passenger waiting times and keeps them informed.

Smart cities also have an important element of security. Smart video cameras use AI algorithms and deep learning (DL) to analyze visual data in real time and can send commands from a hub to AI-powered devices faster than a human cannot process them. Going beyond simply delivering data, smart technologies can actually enable devices to deploy intelligent information. For example, cameras and AI-analyzed traffic patterns can adjust traffic lights accordingly to improve vehicle flow, reduce traffic congestion and pollution, and most importantly, increase pedestrian safety.

Smart video is also being deployed in connected cities to provide critical assistance to help reduce crime. Business owners, for example, need security cameras to protect their property, reduce shoplifting, and monitor employee or customer incidents. On a larger scale, real-time video analytics is also capable of identifying and differentiating objects, for example distinguishing humans from animals, and alerting people or systems if they are in a place or a prohibited place.

The Process Behind Smart Video
Smart cameras must “learn” to recognize objects and actions and classify identified actions into categories such as abnormal or normal. This is where AI and DL are needed for training and learning; DL has to analyze a huge amount of data to be very accurate. The development of higher video resolutions, such as 4K, is essential here, allowing CCTV cameras to capture more data in high quality and from different angles, facilitating analysis and strengthening the future of intelligent video.

The smart video industry is going through a transition phase for large-scale video recording: it has moved from recording raw data from a standard camera to performing analytics on the AI itself. In the past, data analysis was only possible at a centralized location, such as a data center; however, the rise of embedded AI chips used in smart city technology helps distribute the analytical load. The ability to distribute work is crucial when working at smart city scale, allowing data to be processed faster at endpoints.

As artificial intelligence and 4K are increasingly adopted on smart video cameras, higher video resolutions drive a demand for more data to be stored on the camera. There are many other types of cameras in use today, such as body cameras, dash cams, and new IoT devices and sensors. Video data is so rich these days that you can analyze it and derive a lot of valuable information in real time, rather than after the event.

The role of storage
Therefore, storage is critical to the evolution and efficient operation of intelligent video systems. Intelligent video architectures require innovative data storage technologies that provide the necessary flexibility, performance, capacity and reliability. Robust on-board storage should be purpose-built to meet the needs arising from multi-streaming devices, on-device deep learning systems, and AI training solutions. Data storage solutions have evolved to provide high data transfer and write speeds, along with the ability to deliver world-class video capture.

Storage-enabled AI
Having the right workload and performance is important to ensure drives can meet AI feature requirements, including pattern matching and object recognition. By combining optimized video stream recording with class-leading durability and capacity, intelligent video solutions and AI analytics have the foundation to perform at peak levels for thousands of hours. .

NVRs and VMS (video management systems) are getting smarter and smarter. Deep learning algorithms go beyond simple motion detection to enable advanced functionality to drive improvements across many industries and environments, including retail, smart cities, and entertainment, to n to name a few. AI-enabled VMS is being architected for a new graphics processing unit (GPU) and central processing units (CPUs) to improve overall deep learning capability and accelerate algorithms related to the identification of objects. NVRs with this deep learning require greater data storage capacity and more sophisticated processing, compared to individual cameras, allowing them to perform more advanced analyses, such as finding a particular image to from weeks or months of stored video, or creating traffic heatmaps from hours of retail CCTV.

Behind the innovation
Intelligent video plays a critical role in many public safety use cases, including safe driving, retail, fleet management, and home security. However, the success of intelligent video relies on a robust and resilient storage architecture that can efficiently keep up with heavy workloads. As intelligent video use cases proliferate in the security and logistics landscapes, the hidden complexities of data storage should not be overlooked. As data demands for video continue to evolve, innovations to address industry challenges must do the same.

Khwaja Saifuddin, is the Senior Director of Sales – Middle East at Western Digital

Read: DIC and Khazna Data Centers announce two data storage facilities in Dubai