Image rectification for drone photogrammetry

Docente

Mirko Reguzzoni (mail)

Area di ricerca

Intelligenza artificiale, robotica e computer vision, Geoinformatica

Keyword (max 3 separate da virgola)

Photogrammetry, Least-squares, Digital-images

Descrizione (max 500 caratteri)

The goal is to write a software for the photo rectification to be applied when the acquired photo is referred to a planar surface. The software should offer the possibility of selecting double points, linking the photo coordinates with the object ones, in case applying a suitable roto-translation. After computing the homography parameters by least-squares adjustment, the transformation should be applied to all the photo pixels, implementing a proper resampling procedure (for example nearest neighbour or bilinear interpolation). The algorithm can be tested on drone images.

Comments are closed.