Thesis Defense: Samuel Arce Muñoz

Thesis: Automated 3D Reconstruction Using Optimized View-planning Algorithms for Iterative Development of Structure-from-Motion Models

Abstract: Unsupervised machine learning algorithms (clustering, genetic, and principal component analysis) automate Unmanned Aerial Vehicle (UAV) missions and the creation and refinement of iterative 3D photogrammetric models with a next best view (NBV) approach. The UAV-based Structure-from-Motion’s (SfM) iterative strategy, without the use of previous models to initialize the UAV mission, demonstrates automated iterative mapping of different terrains with convergence to a specified orthomosaic resolution. This iterative UAV photogrammetry successfully runs in various Microsoft AirSim environments: mountain landscape, suburban neighborhood, and petrochemical plant (refinery). Simulated ground sampling distance (GSD) of models reaches as low as 3.4 cm per pixel, and generally, successive iterations improve resolution. Besides analogous application in the simulated environments, a field study of a retired municipal water tank illustrates the practical application and advantages of automated UAV iterative inspection of infrastructure using 63% fewer photographs than a comparable manual flight with analogous density point clouds obtaining a GSD of less than 3 cm per pixel. Each iteration qualitatively increases resolution according to a logarithmic regression, reduces holes in models, and adds details to model edges.

This work is sponsored by the Center for Unmanned Aircraft Systems, an Industrial Innovation and Partnerships (IIP) of the National Science Foundation. More information is at https://c-uas.org

source