The new multi-camera tracking reference workflow unifies tracking of people, objects, and behavior insights with high accuracy from multi-camera feeds, providing a single, comprehensive view of the space. It provides a production-ready reference recipe to build your vision application, eliminating months of development time. The workflow includes state-of-the-art AI models pretrained on real and synthetic datasets. It covers the entire lifecycle—from simulation to analytics—and integrates NVIDIA’s cutting-edge tools, including Isaac Sim™, Omniverse™, TAO, and DeepStream, and is packed with real-time video streaming modules and is built on a scalable, cloud-native microservices architecture.
Read the tech blog Optimize Processes for Large Spaces with the Multi-Camera Tracking Workflow | NVIDIA Technical Blog.
Get started with the developer guide.
Watch the step-by-step video tutorial.
More resources about NVIDIA Metropolis microservices.