Automated 3D reconstruction of rural buildings from Structure-from-Motion (SFM) photogrammetry approach

Collecting three-dimensional data from indoor and outdoor spaces are prominent for various applications in construction and real estate management. Three-dimensional reconstruction methods for realworld environments based on camera images have recently been studied by many researchers and structure from motion (SFM) has been attracting attention as one of the most practical approaches for 3D reconstruction. Based on photogrammetry, the SfM technique consists in taking photos of the object from all possible angulations and points of view all around the object. In the present work, Structure from Motion is studied and proposed as a low-cost and non-invasive technique for three-dimensional reconstruction of volumes by analysing 6 rural building case studies. Analyses and evaluations of buildings parameters have been made taking advantage of the Agisoft Photoscan software, for reconstruction of three-dimensional volumes from collections of 2-D images. Three-dimensional reconstructions were highly correlated with the manual measurementswith a tape measure considered as references, as demonstrated by high coefficients of determination both for volume (R 2 up to 0.96) and for the wall surface parameter (R 2 up to 0.79).