The creation of a programmable software infrastructure for telecommunications operations promises to reduce both capital expenditures (CAPEX) and operating costs (OPEX) of 5G telecommunications operators. For many of us who work in this field, it is exciting that the convergence of telecommunications, cloud and edge infrastructures will create opportunities for new innovation and revenue for both the telecommunications industry and the cloud ecosystem.

In this blog, we focus on video, the dominant type of traffic on the Internet since the advent of 4G networks. With 5G, not only will the volume of video traffic increase, but there will also be many new solutions for industries from retail to manufacturing to health and forest surveillance that incorporate deep learning and AI for video analytics scenarios. The symbiotic development of video analytics and edge computing offers operators opportunities to offer new services that they can monetize with their customers.

You can find more information about our Azure for Operators strategy in our e-book “A cloud for network operators. “

Video analysis, edge computing and 5G

Our first public disclosure of real-time video analytics was when we called it the Edge computing killer app. Working with the City of Bellevue, Washington, we tracked theirs Vision zero Initiative too conduct a pilot study for live traffic jams and safety at the main traffic intersections of the cities equipped with cameras. We hosted a traffic dashboard in the traffic management center of Bellevue (July 2017 to November 2018), which is supported by our video analysis solution for the detection of cars, pedestrians and cyclists. The dashboard also helped Bellevue’s traffic planners Understand traffic patterns over long periods of time and led to the creation and evaluation of a cycle path on one of its main roads. The project was a great success and the city won several national awards for its vision and pilot projects to integrate video analytics into traffic management.

At the same time, with the advent of 5G, telecommunications operators began large investments in their network infrastructure, with the lion’s share of network capacity planned for video traffic. Interestingly, the operators’ efforts to use their infrastructure to digitize various industries go perfectly with Microsoft’s own investments in edge computing and video analysis. Edge computing is the catalyst leading to the convergence of the two infrastructures, and video analytics is the perfect service 5G operators can host on their edge computing servers.

The figure shows that the investments of 5G operators and Microsoft are coordinated.

A revenue opportunity for 5G operators and Microsoft partners with new age applications

There are several good examples we can think of for 5G operators to monetize video analytics services. Consider traffic monitoring and accident prevention solutions in smart cities, similar to how we implemented it in our Vision Zero work with the city of Bellevue. A related application is integration into self-driving cars with real-time video analysis from their cameras. Also, consider modern smart businesses where end-to-end experiences with video analytics and mixed reality are a natural part of private 5G network solutions. Other examples are the management of machines and robots in networked factories or customer requests and services in retail stores and restaurants or pedestrian traffic in sports arenas. In all of these cases, 5G operators can work with system integrators (SIs) to use Azure Edge Computing products and Azure Video Analyzer to deliver innovative solutions.

The figure illustrates the coming together of 5G operators, Azure Edge video services and system integrators (SIs) to offer future video analytics services for different industries.

The figure illustrates the coming together of 5G operators, Azure Edge video services and system integrators (SIs) to offer future video analytics services for different industries.

Microsoft already has an ergonomic, tethered holographic device with enterprise grade applications that will increase user productivity in all industries from manufacturing to education Microsoft HoloLens. Looking ahead to the not-too-distant future, outsourcing video processing from HoloLens to a nearby Azure Edge over a low-latency, high-bandwidth 5G network is another example of how operators can bring new products to life. Microsoft cloud gaming platform, xCloud, also comes to mind as it features next generation global game streaming. By harnessing the power of 5G networks with low latency, high bandwidth and live video analytics on edge devices, operators can support a significantly improved gaming experience.

How Microsoft’s advanced technology makes all of this possible

Microsoft has invested many years in development large scale live video analytics systems. We have published research with significant platform advances, developed related products, and open source technologies. For example, Microsoft Rocket is an open source platform that enables the simple construction of video pipelines for efficient processing of video streams. Its cascaded video pipeline in combination with Azure Video Analyzer, makes it easy and affordable for developers to integrate video analytics applications into IoT solutions. The combination of Azure Video Analyzer and Microsoft Rocket along with Azure bow enables easy configuration of resource accuracy tradeoffs and orchestration across a distributed edge cloud hierarchy. Azure Video Analyzer and Microsoft Rocket arrive Improve the magnitude of throughput per edge core for video analytics without compromising accuracy, reducing the total cost of ownership (TCO) at the edge.

Respect for privacy was a central pillar of Microsoft Rocket’s goal to democratize video analytics. We used edge computing as a natural ally to protect privacy with video transformation techniques at the edge that prevented the leakage of personal data in the analytics. We also use secure hardware to protect against snooping and ensure confidentiality during the analysis.

Specific to 5G, we have also built extensive network monitoring and adjustments for fault tolerance and load balancing into the video processing pipeline to handle dynamic network conditions that are inevitable in all wireless networks. Our system, which we refer to as Edge Video Services (EVS), works well with heterogeneous edge hierarchies that support different hardware. For this we have developed a new technology for computation partitioning and an inter-edge orchestrator. EVS partitions the calculation in order to optimally use the available hardware at the edge and cloud infrastructure and to coexist with other workloads at the edge, as shown in the following figure.

Demonstrates how the Edge Video Services (EVS) split the computation to get the most out of the hardware available at the edge and the cloud infrastructure while staying with other workloads at the edge.

The figure illustrates how the Edge Video Services (EVS) split the computation to make the most of the hardware available at the edge and the cloud infrastructure while coexisting with other workloads at the edge.

Adapting Azure Video Analyzer for real operation over 5G networks

We have further developed our systems through pilot projects with operators and providers of 5G network equipment. Our engagement with Telstra, a well-known Australian telecommunications provider, is an example of an operator looking to shed light on EVS. As part of Telstra’s mission to build a connected future for all, Telstra acquired Azure Video Analyzer and Microsoft Rocket along with Azure Stack Edge and Azure Percept Preview. Thanks to the intelligent distribution of the AI ​​across Edges, the amount of data processed could be reduced by 50 times, which led to better utilization of Telstra’s 5G network. Telstra develops scalable, cost-efficient solutions that help its customers to optimize the flow of traffic and increase building safety.

In our collaboration with Fujitsu, we tested a private 5G solution for monitoring parking lots by analyzing video feeds from Fujitsu’s intelligent wireless cameras. To build autonomous networks with minimal complexity, Fujitsu adapted Microsoft Rocket to its 5G infrastructure where the RAN containers from Microsoft Rocket and Fujitsu side by side on one Azure Stack Edge. Microsoft Rocket has significantly reduced computing and network requirements while providing low latency and accurate visualization of parking space occupancy.

In another example, Microsoft developed in collaboration with academic colleagues from Princeton University the world’s first 5G-based multi-hop camera network. This relay-based camera network uses edge servers and cameras equipped with WiGig radios to create a fully connected millimeter wave (mmWave) network. This then enables efficient streaming and analysis of live video in areas where direct line of sight to base stations is often problematic, as shown here Demo video.

Look to the future

In the years to come, people around the world will access and use 5G networks on a daily basis. 5G networks will continue to add value across industries, offering high capacity, low latency connectivity to support a plethora of complex and useful applications. At Microsoft, we believe privacy-friendly live video analytics applications are ideal for 5G networks. Our research and innovation described in this post will move us further by paving the way for inventing the next generation of live video analytics applications that will revolutionize our world – making it safer, more efficient, and more fun. For more information on our Azure for Operators strategy, see the Azure for Operators e-book.


Source link

Leave a Reply