Search for: All records

Unsupervised machine learning algorithms (clustering, genetic, and principal component analysis) automate Unmanned Aerial Vehicle (UAV) missions as well as the creation and refinement of iterative 3D photogrammetric models with a next best view (NBV) approach. The novel approach uses Structure-from-Motion (SfM) to achieve convergence to a specified orthomosaic resolution by identifying edges in the point cloud and planning cameras that “view” the holes identified by edges without requiring an initial model. This iterative UAV photogrammetric method successfully runs in various Microsoft AirSim environments. 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 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. 

Remote sensing with unmanned aerial vehicles (UAVs) facilitates photogrammetry for environmental and infrastructural monitoring. Models are created with less computational cost by reducing the number of photos required. Optimal camera locations for reducing the number of photos needed for structure-from-motion (SfM) are determined through eight mathematical set-covering algorithms as constrained by solve time. The algorithms examined are: traditional greedy, reverse greedy, carousel greedy (CG), linear programming, particle swarm optimization, simulated annealing, genetic, and ant colony optimization. Coverage and solve time are investigated for these algorithms. CG is the best method for choosing optimal camera locations as it balances number of photos required and time required to calculate camera positions as shown through an analysis similar to a Pareto Front. CG obtains a statistically significant 3.2 fewer cameras per modeled area than base greedy algorithm while requiring just one additional order of magnitude of solve time. For comparison, linear programming is capable of fewer cameras than base greedy but takes at least three orders of magnitude longer to solve. A grid independence study serves as a sensitivity analysis of the CG algorithms α (iteration number) and β (percentage to be recalculated) parameters that adjust traditional greedy heuristics, and a case study at the Rock Canyon collection dike in Provo, UT, USA, compares the results of all eight algorithms and the uniqueness (in terms of percentage comparisons based on location/angle metadata and qualitative visual comparison) of each selected set. Though this specific study uses SfM, the principles could apply to other instruments such as multi-spectral cameras or aerial LiDAR. 

This study presents a novel multi-scale view-planning algorithm for automated targeted inspection using unmanned aircraft systems (UAS). In industrial inspection, it is important to collect the most relevant data to keep processing demands, both human and computational, to a minimum. This study investigates the viability of automated targeted multi-scale image acquisition for Structure from Motion (SfM)-based infrastructure modeling. A traditional view-planning approach for SfM is extended to a multi-scale approach, planning for targeted regions of high, medium, and low priority. The unmanned aerial vehicle (UAV) can traverse the entire aerial space and facilitates collection of an optimized set of views, both close to and far away from areas of interest. The test case for field validation is the Tibble Fork Dam in Utah. Using the targeted multi-scale flight planning, a UAV automatically flies a tiered inspection using less than 25% of the number of photos needed to model the entire dam at high-priority level. This results in approximately 75% reduced flight time and model processing load, while still maintaining high model accuracy where needed. Models display stepped improvement in visual clarity and SfM reconstruction integrity by priority level, with the higher priority regions more accurately modeling smaller and finer features. A resolution map of the final tiered model is included. While this study focuses on multi-scale view planning for optical sensors, the methods potentially extend to other remote sensors, such as aerial LiDAR.