Whitepaper: Delivering accelerated video analytics at the edge for AI Cities

Oct. 12, 2018
HPE Edgeline and NVIDIA IVA enable rapid time-to-insight for AI capabilities at the edge

Thirty billion images a second; one hundred trillion images an hour! Thatā€™s how much content will be captured by 2020 by surveillance cameras across the globe. These one billion cameras, twice todayā€™s number, will be at traffic intersections, transit stations, and other public areas, helping to make our cities safer and smarter. Theyā€™ll also be in retail stores, service centers, warehouses, and more, ensuring safety and security, gathering information to boost sales, track inventory, and improve service.

In order to make sense of this staggering number of pixels, traditional methods of video processing either using human monitoring or handcrafted computer vision algorithms, will not be able to meet the speed and accuracy demands. Instead, a branch of Artificial Intelligence (AI) called deep learning offers a powerful and scalable method for extracting detailed information out of these vision systems. However, deep learning requires orders of magnitude more compute and memory than is typically available in a general-purpose server system.

Download this whitepaper, sponsored by HPE OEM Solutions, to learn how HPE Edgeline Converged Edge Systems and NVIDIA Tesla P4 IVA can enable rapid time-to-insight for video surveillance at the edge with AI capabilities.Ā