An automatic workflow for orientation of historical images with large radiometric and geometric differences

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.

Automated summary

This study proposes a workflow for fully automatic orientation of historical urban images, utilizing a neural network for feature extraction and nearest neighbor matching, as well as vanishing point detection for estimating camera principal distance. Results show that the proposed method outperforms other SfM tools and is planned for knowledge transfer in cultural heritage applications.