EXPERIMENTS WITH METADATA-DERIVED INITIAL VALUES AND LINESEARCH BUNDLE ADJUSTMENT IN ARCHITECTURAL PHOTOGRAMMETRY
Keywords: Bundle adjustment, convergence, initial values, metadata, architectural photogrammetry
Abstract. According to the Waldhäusl and Ogleby (1994) "3 x 3 rules", a well-designed close-range architectural photogrammetric project should include a sketch of the project site with the approximate position and viewing direction of each image. This orientation metadata is important to determine which part of the object each image covers. In principle, the metadata could be used as initial values for the camera external orientation (EO) parameters. However, this has rarely been used, partly due to convergence problem for the bundle adjustment procedure.
In this paper we present a photogrammetric reconstruction pipeline based on classical methods and investigate if and how the linesearch bundle algorithm of Börlin et al. (2004) and/or metadata can be used to aid the reconstruction process in architectural photogrammetry when the classical methods fail. The primary initial values for the bundle are calculated by the five-point algorithm by Nistér (Stewénius et al., 2006). Should the bundle fail, initial values derived from metadata are calculated and used for a second bundle attempt.
The pipeline was evaluated on an image set of the INSA building in Strasbourg. The data set includes mixed convex and non-convex subnetworks and a combination of manual and automatic measurements.
The results show that, in general, the classical bundle algorithm with five-point initial values worked well. However, in cases where it did fail, linesearch bundle and/or metadata initial values did help. The presented approach is interesting for solving EO problems when the automatic orientation processes fail as well as to simplify keeping a link between the metadata containing the plan of how the project should have become and the actual reconstructed network as it turned out to be.