GPU-Accelerating End-to-End Geospatial Workflows

Both the federal community and the commercial marketplace have critical mission needs to rapidly geolocate imagery that has no associated geospatial information for a wide variety of computer vision applications, such as search and rescue, natural hazards detection, and environmental monitoring. These tasks are extremely difficult due to the computational and time requirements — i.e., being able to process a large landmass spanning hundreds of thousands of square miles in minutes, rather than hours or days. We'll explain how NVIDIA’s AI data processing and GPU acceleration software libraries (Triton Inference Server, DALI, and RAPIDS) are incorporated in an end-to-end geospatial application workflow to implement an extremely fast geospatial search-and-retrieval application.