3D Reconstruction for Elevation Determination

A 3D-reconstruction method for fast elevation determination on construction sites using few drone-based low-high ortho-images.

An up-forward-down path is designed to capture approximately 2:1 scale images at different altitudes over target stations.

A pixel grid matching and elevation determination algorithm was developed to automatically match images in dense pixel grid-style via self-adaptive patch feature descriptors, and simultaneously determine elevations based on a virtual elevation model.

The 3D-reconstruction results were an elevation-map and an orthoimage at each station.

Then, the large-scale results of the entire site were easily stitched from adjacent results with narrow overlaps.

Moreover, results alignment was automatically performed via the U-net detected ground control point.

Experiments validated that in 10-20 and 20-40 ortho-image pairs, 92% of 2,500 and 4,761-pixel were matched in the strongest and strong-level, which were better than sparse reconstructions via structure from motion.

The elevation measurements were as accurate as photogrammetry using multi-scale overlapping images.