An automatic workflow for orientation of historical images with large radiometric and geometric differences
The Photogrammetric Record · 2021-06 · 36 (174) · 77-103
DOI: 10.1111/phor.12363 ↗Kurz gefasst
Fachartikel in der Zeitschrift The Photogrammetric Record, online erschienen am 06.06.2021. Verfasst von Ferdinand Maiwald und 1 weiteren Autor:innen. Die Arbeit wurde bisher 19-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
This contribution proposes a workflow for a completely automatic orientation of historical terrestrial urban images. Automatic structure from motion (SfM) software packages often fail when applied to historical image pairs due to large radiometric and geometric differences causing challenges with feature extraction and reliable matching. As an innovative initialising step, the proposed method uses the neural network D2‐Net for feature extraction and Lowe’s mutual nearest neighbour matcher. The principal distance for every camera is estimated using vanishing point detection. The results were compared to three state‐of‐the‐art SfM workflows (Agisoft Metashape, Meshroom and COLMAP) with the proposed workflow outperforming the other SfM tools. The resulting camera orientation data are planned to be imported into a web and virtual/augmented reality (VR/AR) application for the purpose of knowledge transfer in cultural heritage.
Zitieren
APA
Maiwald, F., & Maas, H. (2021). An automatic workflow for orientation of historical images with large radiometric and geometric differences. The Photogrammetric Record, 36(174), 77-103. https://doi.org/10.1111/phor.12363
Vancouver
Maiwald F, Maas H. An automatic workflow for orientation of historical images with large radiometric and geometric differences. The Photogrammetric Record. 2021;36(174):77-103. doi:10.1111/phor.12363
BibTeX
@article{Maiwald2021,
author = {Maiwald, Ferdinand and Maas, Hans‐Gerd},
title = {An automatic workflow for orientation of historical images with large radiometric and geometric differences},
journal = {The Photogrammetric Record},
year = {2021},
volume = {36},
number = {174},
pages = {77--103},
doi = {10.1111/phor.12363}
}
EUVIMED