Automated and Accurate Orientation of Large Unordered Image Datasets for Close-Range Cultural Heritage Data Recording
暂无分享,去创建一个
Summary: Reconstruction of image orientationsand geometry from images is one of the basic tasksin photogrammetry and computer vision. A fullyautomated solution of this task in terrestrial appli-cations is still pending in case of large unorderedimage datasets especially for close-range and/orlow-cost applications. Current solutions requirehigh computationaleffortsforimagenetworkswithhigh complexity and diversity regarding acquisi-tion geometry. Unlike the methods suitable forlandmark reconstruction from large-scale Internetimage collections we focus on datasets where onecannot reduce the number of images without losinggeometric information of the dataset. Within thepaper, an automated pipeline for the reconstructionof reliable and precise camera orientation from un-ordered image datasets is presented. Results for aclose-rangeculturalheritageapplication, theexam-ple ofthe Amsterdam project, are shown to demon-strate the performance ofthe presented pipeline forapplications with low cost and high accuracy re-quirements.
[1] John Law,et al. Robust Statistics—The Approach Based on Influence Functions , 1986 .
[2] Dieter Schmalstieg,et al. Robust Incremental Structure from Motion , 2010 .
[3] K. Wenzel,et al. Multi-Sensors and Multiray Reconstruction for Digital Preservation , 2011 .
[4] Andrea Fusiello,et al. Structure-and-motion pipeline on a hierarchical cluster tree , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.