Show simple item record

TranslatedTitle: Benchmarkdatensatz historischer Bilder für die Evaluation von Methoden zur Merkmalszuordnung

Metadata

Additional titleTranslatedTitle: Benchmarkdatensatz historischer Bilder für die Evaluation von Methoden zur Merkmalszuordnung
Other contributing persons, institutions or organisationsbmbf - Funder
Other contributing persons, institutions or organisationsSander, Münster - Medienzentrum (MZ) (orcid: 0000-0001-9344-912X) - ProjectLeader
Other contributing persons, institutions or organisationsDeutsche Fotothek - SLUB Dresden (Other: http://www.deutschefotothek.de) - Producer
Person(s) who is (are) responsible for the content of the research dataMaiwald, Ferdinand - Institut für Photogrammetrie und Fernerkundung (IPF) (ORCID: 0000-0002-2456-9731)
Research objectsMedia: Historical images and their relative orientation using the Trifocal Tensor
AbstractImage dataset to the submitted ISPRS GSW2019 publication "Generation of a benchmark dataset using historical photographs for an automated evaluation of different feature matching methods". This dataset contains eight triples of historical images for four different sights. Images were chosen with respect to their possible matching quality. The images show combined differences in illumination, field of view, viewpoints, blurring and slight rotation. Some of the images show building reflections in water or extreme shadowing. The images are saved after digitization in full quality as *.tif files with a maximum sidelength of 3543 Pixels. Since no inner orientation could be determined for all image triples the Trifocal Tensor is provided - calculated using Ressl's method (Ressl, 2003). Additional metadata information, copyright disclaimer and permalinks are provided in License.txt. The purpose of the dataset is the evaluation of different feature detection and matching methods using the given orientation with the Trifocal Tensor. Point transfer calculation is possible using the equation on p. 382 in Multiple View Geometry in Computer Vision (Hartley and Zisserman, 2003). Another method uses the corrected Fundamental Matrices calculated in eq. 15.8 from the Trifocal Tensor on p. 374 in Multiple View Geometry in Computer Vision (Hartley and Zisserman, 2003). Ressl, C., 2003. Geometry, constraints and computation of the trifocal tensor. TU Wien. Hartley, R. and Zisserman, A., 2003. Multiple view geometry in computer vision. Cambridge university press.
Applied methods and techniquesTrifocal Tensor, Fundamental Matrix - Feature matching methods: MSER, ORB/SURF, RIFT - Outlier removal methods: RANSAC, FSC
Additional descriptive information to understand the dataThe images were taken from around 1880-1992 and digitized for the purpose of this publication from 2018-2019.
Counties, the data is referencingGERMANYde
Regions the data is referencingSachsen
Regions the data is referencingDresden
Additional keywordscomputer vision
Additional keywordsphotographs
Additional keywordsphotogrammetry
Additional keywordsorientation
Additional keywordsdetection
Languageeng
Year or period of data production2018-2019
Publication year2019
PublisherTechnische Universität Dresden
References on related materialsIsPartOf: 123456789/1371 (Handle)
Content of the research dataText, Image, Dataset: Text: License and Readme file (License.txt, Readme.txt) - Image: 24 historical images - Dataset: coordinate list, orientation information, matching results
Other specification of usage rights
Holder of usage rightsTechnische Universität Dresden
Holder of usage rightsSLUB Dresden - Deutsche Fotothek
Usage rights of the dataCC-BY-SA-4.0
Additional precise description of disciplineThe data can be evaluated using methods of Photogrammetry and Computer Vision
Discipline(s)Geological Sciencede
Discipline(s)Historyde
Discipline(s)Computer Sciencede
Title of the datasetBenchmark dataset using historical images for an automated evaluation of feature matching methods


Files in this item

Thumbnail
Thumbnail

This item appears in the following Collection(s)

  • Benchmark dataset using historical images for an automated evaluation of different feature matching methods [1]Open Access Icon
    This dataset contains eight triples of historical images for four different sights. Images were chosen with respect to their possible matching quality. The images show combined differences in illumination, field of view, viewpoints, blurring and slight rotation. Some of the images show building reflections in water or extreme shadowing. The images are saved after digitization in full quality as *.tif files with a maximum sidelength of 3543 Pixels. Since no inner orientation could be determined for all image triples the Trifocal Tensor is provided - calculated using Ressl's method (Ressl, 2003). Additional metadata information, copyright disclaimer and permalinks are provided in License.txt. The purpose of the dataset is the evaluation of different feature detection and matching methods using the given orientation with the Trifocal Tensor. Point transfer calculation is possible using the equation on p. 382 in Multiple View Geometry in Computer Vision (Hartley and Zisserman, 2003). Another method uses the corrected Fundamental Matrices calculated in eq. 15.8 from the Trifocal Tensor on p. 374 in Multiple View Geometry in Computer Vision (Hartley and Zisserman, 2003). Ressl, C., 2003. Geometry, constraints and computation of the trifocal tensor. TU Wien. Hartley, R. and Zisserman, A., 2003. Multiple view geometry in computer vision. Cambridge university press.

Show simple item record