Cloud-to-Edge Inference for Smarter AI Cities

Faster Processing for Real Time Insights

Modern cities are dotted with video cameras—a billion of them will be in use by 2020—and those cameras are generating a massive amount of data every day. Deep learning is the best way to turn this raw video data into actionable insight, and GPU-based inference is the only way to do it in real time. Cities powered by the NVIDIA Metropolis platform are becoming smarter and safer for everyone from drivers and pedestrians to retailers and shoppers.

End-To-End GPU Inference

END-TO-END GPU INFERENCE

Extracting valuable, actionable insight from large quantities of video data requires inference from the edge to the cloud. NVIDIA Metropolis uses the low power of NVIDIA® Jetson™ in cameras and appliances at the edge, the massive compute of NVIDIA Tesla® servers in the cloud, and the NVIDIA DeepStream SDK powered by NVIDIA TensorRT™ to deliver a complete IVA solution.

AI For Embedded Devices

AI FOR EMBEDDED DEVICES

The NVIDIA Jetson platform offers the best throughput and performance per watt, the lowest latency, and the highest channel density, which translates into lower operating costs throughout a city’s network.

Superhuman Video Processing For Real-World Applications

SUPERHUMAN VIDEO PROCESSING FOR REAL-WORLD APPLICATIONS

Nearly 100 partner companies are using the edge-to-cloud NVIDIA Metropolis platform to build the AI cities of tomorrow. One partner, Verizon, is working to connect communities by attaching smart cameras powered by NVIDIA to street lights and other urban vantage points.

Verizon’s video nodes leverage Jetson TX1 to collect and analyze data on the furthest edges of a city’s network. This supercomputer on a module accelerates deep learning at the edge, enabling real-time video analytics. All of this edge computing means more efficient, near real-time data analysis, and less high-cost streaming and storing of video over LTE and Wi-Fi networks.

As a result, Verizon is able to track and classify objects such as vehicles, cyclists, and pedestrians, and identify interactions in real time. This provides city officials with a 24/7 data stream of everything from illegal turns to pedestrian movement outside of designated crosswalks and parking lot metrics to create a safer and more efficient city.  

Discover how leading software partners are using NVIDIA Metropolis to transform smart cities.