Abstract
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.
Highlights
Recent advancements in remote sensing technologies motivate the use of Unmanned Aerial Vehicles (UAVs) in a variety of aerial imaging tasks [1,2,3,4,5]
This study introduces an iterative modeling strategy that provides UAVs with additional autonomy in photogrammetry missions
Overall trends hold true and ground sampling distance (GSD), cloud to cloud comparisons, and qualitative images compliment the evaluation of next best view (NBV) photogrammetry
Summary
Recent advancements in remote sensing technologies motivate the use of Unmanned Aerial Vehicles (UAVs) in a variety of aerial imaging tasks [1,2,3,4,5]. One remarkable use of UAVs as remote sensors is the high resolution topographic models through means of inexpensive equipment and a photogrammetric technique known as Structure-from-Motion (SfM) [6]. SfM organizes the spatial information of multiple images, and structures a 3D model from the various surfaces based on relative distances between common points [7]. The photos are processed, and the resulting incomplete point cloud is analyzed to find deficiencies in the model and calculate an optimal set of views. These subsequent views improve model resolution in each iteration of UAV missions. The photos from each iteration combine with previous models to render a more complete point cloud. The analysis repeats until the model achieves a predefined orthomosaic resolution
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have