How to Overcome the Storage Challenges of Adopting Surveillance AI
Businesses are using sensors, Internet of Things (IoT) devices, and surveillance cameras to manage assets and resources more efficiently than ever before. Facial recognition, remote patient monitoring, and wrong-way driver detection are just a few of the advanced, insight-driven technologies seeing greater adoption today. At the center of it all is data, which is continuously being gathered, analyzed and utilized for real-time decision-making. This data collection places a greater workload on the storage systems behind the sensors. Smart solutions are only as good as the data they store, analyze and deliver in a timely manner. This white paper discusses rapid changes in the global data-sphere, the impact of real-time data analysis in safe and smart cities, and the storage best practices that system integrators should implement to improve data flow and insights for customers. Global Data-sphere Evolution Data is in flight all around us and has become an essential part of the human experience. The global market intelligence firm – IDC – forecasts that the global data-sphere will increase from 33 zettabytes in 2018 – where one zettabyte equals to a trillion gigabytes – to 175 zettabytes in 2025. That is by 2025, on an average every connected person in the world will have a digital data engagement over 4900 times per day. This breaks down to about 1 digital engagement every 18 seconds. IDC reports that the number of IoT devices will grow to 80 billion by 2025, and these smart solutions will monitor business processes and enhance everyday life activities. Harnessing the Power of Data Executives are ultimately looking to interpret the data aggregated by IoT devices, sensors and security solutions, and leverage it to improve operations, cost-savings and customer satisfaction. The deployments of cognitive systems such as machine learning, natural language processing and AI that actively analyze this data for proactive decision-making are on the rise. IDC indicates that the amount of analyzed data that is ‘touched’ by cognitive systems will grow by a factor of 100 to 1.4 zettabytes in 2025. The use of cognitive systems is opening the door to new business opportunities and a greater return on investment in all markets. Storage in the Era of AI New enhancements allowing security solutions to be used for business intelligence are driving the demand for data-hungry applications. The increased use of AI systems in security has warranted a shift in recording and storage technologies. Standard surveillance systems primarily recording footage were typically write-only applications. Today surveillance systems with AI have mixed read/ write workloads. Previously, users relied on cloud data centers to manage the unstructured data and analysis. However, this setup often causes latency and delays as all video and metadata must be transferred off-site for analysis. To remedy this issue, storage providers are building AI into video NVR systems and harnessing the power of micro-datacenters so that initial processing, analysis and pattern recognition may occur in real time at the edge. The edge refers to servers and appliances outside of data centers that are located regionally and are closer to endpoints, like surveillance cameras and sensors, where the data is first captured. Development of AI-enabled NVRs and edge computing devices is driven by cheaper graphics processing units (GPU) with enhanced analysis capabilities, as well as better storage options. In particular, new hard disk drives with fast writing data speeds, high read performance, and support for both AI and video workloads have become attractive solutions for system integrators. Innovation in telecommunications with 5G, advanced sensors and intelligent surveillance cameras are also driving the evolution of surveillance beyond traditional security for AI applications. After the initial video ingestion and analytics at the edge, video is pushed to the back end or cloud. In this centralized environment, video and AI metadata are consolidated for deep learning activities to train the system to be more predictive and provide a more holistic view of the video data collected. In the past, users primarily used cloud storage to satisfy legal and corporate retention policies; however, that has since changed. Data no longer languishes in the back end to eventually be discarded. Now data in the cloud is used to bring predictive power and intelligence for better decision-making like never before. Ultimately, implementing robust storage solutions from edge to cloud enables smarter surveillance systems over time through AI training and rapid insights for command center operators to quickly respond to time-sensitive scenarios. Biggest Impact: Safe and Smart Cities The development of safe and smart cities continues to be one of the sectors where surveillance systems and data will have the greatest impact. Research firm IHS Markit indicates that the global market for city surveillance exceeded $3 billion in 2017 and is expected to increase each year by 14.6% from 2016 through 2021. IHS reports that China is one of the strongest adopters of safe city surveillance technologies. SMART CITY SECTORS Beyond citywide surveillance, smart cameras, IoT sensors, and edge computing devices with AI are being deployed in smart cities to equip businesses and citizens with data that can enhance the urban experience. IHS Markit predicts that there will be at least 88 smart cities worldwide, a substantial increase from 21 cities in 2013. The collection and delivery of data is the crux of the smart cities operation. Here are three segments within smart cities where organizations are using data to address urban woes. HEALTHY LIVING AND SAFETY Data captured by IoT devices and video are utilized to not only improve the quality of healthcare, but also the kind of preventative measures implemented to ensure a healthier population. In hospitals, IoT sensors and video devices enable re mote patient monitoring, providing real-time alerts of blood pressure and other body indicators to staff who can intervene before a situation escalates to a crisis. The end result is lower mortality rates. When it comes to preventive health measures, advanced IoT devices and video solutions are employed for air quality monitoring, alerting sensitive groups to potentially dangerous conditions. Population health programs are using data collection…