A paradigm shift in processing large UAV image datasets for emergency management of natural hazards

Over the past two decades, natural hazards have claimed the lives of tens of thousands of people worldwide, every year. Unmanned Aerial Vehicles (UAVs) are pivotal in natural hazard management, offering rapid deployment, flexibility, and cost-effectiveness. Advances such as Beyond Visual Line Of Sight (BVLOS) missions, swarm surveying, Artificial Intelligence (AI), edge-computing, and Structure from Motion (SfM) photogrammetry enhance their high-resolution spatiotemporal data capabilities, but the need for large datasets poses challenges in terms of storage, computational resources and, especially, processing time. This work introduces an original high-performance UAV photogrammetry workflow through the implementation of an open-source distributed approach using the ReCaS-Bari HPC cluster. Performance tests of the workflow, that includes computing parallelism, GPU usage, and hybrid bundle adjustment, demonstrate a significant reduction in processing time for large UAV image datasets. The workflow outperformed current methods, reducing processing time from 908 down to 104 min for 2,691 images and handling 11,549 images in just 7.8 h (a 70 % improvement over leading commercial software). Comparative analysis with cluster-based state-of-the-art approaches revealed noteworthy reductions, reaching up to 86 % for about 7,000 images. A case study, focusing on the Basento river (Southern Italy) flood event occurred in May 2023, proved the workflow practical implications in emergency management. A change detection assessment facilitated the identification and quantification of flood-induced morphological alterations along a 3 km of river reach length within about 3 h. The results highlight the workflow utility in providing accurate and near real-time information for emergency management, enhancing situational awareness and facilitating informed decision-making during disastrous events.