This talk explores how DeepStream enables developers to create high-stream density applications with deep learning and accelerated multimedia image processing, building IVA solutions at scale. Leverage a heterogeneous concurrent neural network architecture to bring in different deep learning techniques for more intelligent insights. The framework makes it easy to create flexible and intuitive graph-based applications, resulting in highly optimized pipelines for maximum throughput.
A major benefit of edge computing is the ability to bring compute and storage with adequate connectivity closer to the point of action, critical for use cases like smart cities. Todays neighborhoods and city blocks have a few thousand sensors and cameras connected to wireless networks. By 2025, its predicted this number will increase by 100 fold. Bringing efficiency and safety to todays cities depends on the ability to deliver real-time situational awareness and control across these high-bandwidth sensors while maintaining high availability. NVIDIA Metropolis delivers a compete framework to build and deploy these applications on edge infrastructure. In this talk, attendees will learn how NVIDIAs core technologies open up new business and service revenue opportunities for the telecom industry.